Customer relationship management method and system based on big data analysis

Abstract

The invention relates to the technical field of business systems, in particular to a customer relationship management method and system based on big data analysis. A customer relationship management method based on big data analysis comprises the following steps: S1, acquiring public sea customer data and customer data in a seller private sea, and preprocessing the customer data; s2, based on the historical periodic purchase data of the customers, the public-sea customer recommendation public-sea pool comprises a first recommendation public-sea pool in which unallocated public-sea customers are matched with public-sea customers conforming to the historical short-term periodic purchase data; and a second recommendation public sea pool matched with the unallocated public sea customers and the public sea customers conforming to the historical long-term periodic purchase data and the advanced contact time. According to the method, the purchase cycle of the public seller is obtained, recommendation is performed according to the cycle of the public seller, the waiting duration is set for the customers who do not complete replacement by the salesman, and recommendation is performed after adjustment is performed according to the interest weight of each replaced customer.

Description

Technical Field

[0001] The present invention relates to the technical field of business systems, and in particular to a customer relationship management method and system based on big data analysis. Background Art

[0002] Customer relationship management is a strategy that helps companies establish, maintain and optimize relationships with customers through systematic management methods. With the increasingly fierce market competition, companies are paying more and more attention to the management and maintenance of customer resources. Traditional CRM systems are mainly used to store and manage customer information for the convenience of sales staff. However, with the development of new technologies such as big data, artificial intelligence and cloud computing, the functions of modern CRM systems are no longer limited to basic data management, but are gradually expanding to more intelligent and personalized areas. In real life, when sales staff use CRM systems, they will constantly replace customers in their private seas in order to occupy better customer resources, and will exchange privately between sales staff, that is, when sales staff A releases customer resources, he will immediately tell sales staff B. This phenomenon does not allow customer resources to be properly allocated. Summary of the invention

[0003] In order to overcome the shortcoming that sales personnel cannot obtain reasonable allocation of customer resources, the present invention provides a customer relationship management method and system based on big data analysis.

[0004] The technical solution of the present invention is: a customer relationship management method based on big data analysis, comprising the following steps:

[0005] S1: Obtain customer data on the high seas and customer data on the salesperson’s private seas, and pre-process them;

[0006] S2: Based on the historical periodic purchase data of the customer, the public sea customer recommendation public sea pool includes a first recommended public sea pool that matches the unallocated public sea customers with the public sea customers who meet the historical short-term periodic purchase data, and a second recommended public sea pool that matches the unallocated public sea customers with the public sea customers who meet the historical long-term periodic purchase data and meet the advance contact time;

[0007] S3: Based on the correlation between the customers in the private seas of the target salesperson and the high seas customers, the high seas customer recommendation high seas pool includes a third recommended high seas pool with matching correlation between the allocated private seas customers and the unallocated high seas customers, and a fourth recommended high seas pool for replacement and recovery in the private seas of the salesperson;

[0008] S4: Make customer recommendations to target sales staff based on the high seas customer recommendation pool.

[0009] Preferably, the obtaining of high seas customer data and sales personnel's customer data in private seas and preprocessing thereof includes: performing data cleaning processing on the customer data to remove duplicate values, fill in missing values, and remove abnormal values.

[0010] Preferably, the high seas customer recommendation high seas pool based on the customer's historical periodic purchase data includes a first recommended high seas pool that matches unallocated high seas customers with high seas customers that meet historical short-term periodic purchase data, and a second recommended high seas pool that matches unallocated high seas customers with high seas customers that meet historical long-term periodic purchase data and meet the advance contact time, including: obtaining the high seas customer's historical periodic purchase data, using fuzzy reasoning to obtain a period threshold judgment rule based on the high seas customer's historical periodic purchase data, and dividing the high seas customer's purchase periodicity according to the period threshold judgment rule to obtain short-term periodicity or long-term periodicity.

[0011] Preferably, the high seas customer recommendation high seas pool based on the customer's historical periodic purchase data includes a first recommended high seas pool that matches unallocated high seas customers with high seas customers that meet historical short-term periodic purchase data, and a second recommended high seas pool that matches unallocated high seas customers with high seas customers that meet historical long-term periodic purchase data and meet the advance contact time, including: obtaining the conversion time of each high seas user based on a Bayesian algorithm, wherein the advance contact time is the conversion time of the high seas user, and obtaining high seas users whose conversion time intersects with that of each high seas user within a first preset time period of the current time period as the second recommended high seas pool.

[0012] Preferably, the step of obtaining the conversion time of each high seas user based on the Bayesian algorithm includes:

[0013] S201: sorting the historical records of each customer to form a sample set of conversion time;

[0014] S202: Select a probability distribution model and use the gamma distribution, where the probability density function of the gamma distribution is:

[0015]

[0016] Where x is the transformation time, α is the shape parameter, β is the scale parameter, and Γ(α) is the gamma function;

[0017] S203: Determine a prior distribution, and determine initial probability distribution parameters as the prior distribution based on historical data;

[0018] S204: Using the Bayesian update rule, the posterior distribution is:

[0019] α n =α 0 +n;

[0020]

[0021] Where n is the number of observed samples, is the sum of all observed transformation times;

[0022] S205: Use the updated posterior distribution to make predictions. The predicted purchase cycle is obtained by calculating the expected value of the posterior distribution. The expectation of the gamma distribution is:

[0023]

[0024] Where E[x] is the predicted value of the customer purchase cycle, α n and β n are the updated shape and scale parameters.

[0025] Preferably, the high seas customer recommendation high seas pool based on the correlation between the target salesperson's private seas customers and high seas customers includes a third recommended high seas pool that matches the correlation between allocated private seas customers and unallocated high seas customers, and a fourth recommended high seas pool for replacement and recovery in the salesperson's private seas, including: obtaining the target salesperson's private seas pool, and analyzing the target salesperson's customers based on a correlation analysis model trained with big data, obtaining correlation values ​​between private seas customers and high seas customers, and placing high seas customers whose correlation values ​​are greater than a preset correlation threshold into the third recommended high seas pool.

[0026] Preferably, the public seas customer recommendation public seas pool based on the correlation between the target salesperson's private seas customers and public seas customers includes a third recommended public seas pool in which the correlation between the allocated private seas customers and the unallocated public seas customers is matched, and a fourth recommended public seas pool for replacement and recovery in the salesperson's private seas, including: according to a replacement time calculation formula, obtaining the waiting time for the private seas customer to become a public seas customer when the salesperson replaces the private seas customer, and obtaining the fourth recommended public seas pool after sorting according to the waiting time, wherein the replacement time calculation formula is:

[0027] in is the replacement duration, is the preset standard replacement time, ω is the adjustment factor, T 0 is the waiting time of the customer in the private sea, T 标 is the preset standard waiting time, T max It is the maximum waiting time for customers in private seas.

[0028] Preferably, the fourth recommended high seas pool is obtained after sorting according to the waiting time, including: taking private sea customers with a waiting time less than or equal to a preset waiting time as a first preset adding sequence, taking private sea customers with a waiting time greater than the preset waiting time as a to-be-processed sequence, obtaining a first pre-processed private sea customer based on the to-be-processed sequence, wherein the first pre-processed private sea customer is a private sea customer who purchases the same type of sales item within a preset time period, obtaining interest-specific parameters of each private sea customer based on the proportion of the sales item type purchased by the first pre-processed private sea customer within the preset time period, obtaining an adjustment weight based on the interest-specific parameter and the number of purchases of each private sea customer, and placing private sea customers with a waiting time greater than a weight threshold into the first preset adding sequence to obtain a fourth recommended high seas pool.

[0029] Preferably, the method of making customer recommendations to the target salesperson based on the high seas customer recommendation high seas pool includes: obtaining the intersection of the first recommended high seas pool, the second recommended high seas pool and the third recommended high seas pool in the high seas customer recommendation high seas pool as the fifth recommended high seas pool, removing the customers who have been replaced by the target salesperson from the fourth recommended high seas pool, and taking the remaining customers as the sixth recommended high seas pool, and making recommendations to the target salesperson based on the fifth recommended high seas pool and the sixth recommended high seas pool.

[0030] Preferably, a customer relationship management system based on big data analysis includes:

[0031] Data preprocessing module, used to clean data of high seas customers and private seas customers;

[0032] A cycle determination module, used to obtain the short-term periodicity or long-term periodicity of the customer's purchase periodicity;

[0033] The conversion time acquisition module is used to obtain the customer conversion time with long-term periodicity;

[0034] The first recommendation acquisition module is used to acquire high seas customers that meet historical short-term periodic purchase data;

[0035] The second recommendation acquisition module is used to acquire customers among long-term periodic customers who have the ability to be contacted by sales staff in advance;

[0036] The third recommendation acquisition module is used to select customers with a correlation greater than a preset threshold between the private sea customers and the high seas customers of the target salesperson;

[0037] The fourth recommendation acquisition module is used to obtain qualified customers replaced by each salesperson according to the replacement time and adjustment parameters;

[0038] Recommendation module, which makes recommendations to users based on all recommendation modules.

[0039] The present invention has the following advantages: the present invention recommends customers with short-term purchasing periodicity by analyzing the purchasing cycle of high seas customers, analyzes customers with long-term purchasing periodicity, and recommends sales personnel according to the customer conversion time. This method allows sales personnel to contact personnel in advance and increase the customer's consumption probability. The replacement time is set for the customer replaced in the private sea of ​​the sales personnel, and the time for the replaced customer to enter the high seas pool again is adjusted. This method reduces the occurrence of collusion and exchange among sales personnel, so that customer resources are reasonably allocated. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 This is a flow chart of a customer relationship management method based on big data analysis of the present invention;

[0041] Figure 2 This is a flow chart of the use of the Bayesian algorithm of the present invention. DETAILED DESCRIPTION

[0042] The preferred technical solutions of the present invention are described in detail below with reference to the accompanying drawings.

[0043] Embodiment 1: A customer relationship management method based on big data analysis, such as Figure 1-2 As shown, the following steps are included:

[0044] S1: Obtain customer data on the high seas and customer data on the salesperson’s private seas, and pre-process them;

[0045] Data cleaning is performed on customer data to remove duplicate values, fill in missing values, and remove outliers.

[0046] S2: Based on the historical periodic purchase data of the customer, the public sea customer recommendation public sea pool includes a first recommended public sea pool that matches the unallocated public sea customers with the public sea customers who meet the historical short-term periodic purchase data, and a second recommended public sea pool that matches the unallocated public sea customers with the public sea customers who meet the historical long-term periodic purchase data and meet the advance contact time;

[0047] The historical periodic purchase data of high seas customers are obtained, and a periodic threshold judgment rule is obtained using fuzzy reasoning based on the historical periodic purchase data of the high seas customers. The purchase periodicity of the high seas customers is divided according to the periodic threshold judgment rule to obtain short-term periodicity or long-term periodicity.

[0048] The conversion time of each high seas user is obtained based on the Bayesian algorithm, wherein the advance contact time is the conversion time of the high seas user, and the high seas users whose conversion time intersects with that of each high seas user within the first preset time period of the current time period are obtained as the second recommended high seas pool.

[0049] S201: sorting the historical records of each customer to form a sample set of conversion time;

[0050] S202: Select a probability distribution model and use the gamma distribution, where the probability density function of the gamma distribution is:

[0051]

[0052] Where x is the transformation time, α is the shape parameter, β is the scale parameter, and Γ(α) is the gamma function;

[0053] S203: Determine a prior distribution, and determine initial probability distribution parameters as the prior distribution based on historical data;

[0054] S204: Using the Bayesian update rule, the posterior distribution is:

[0055] α n =α 0 +n;

[0056]

[0057] Where n is the number of observed samples, is the sum of all observed transformation times;

[0058] S205: Use the updated posterior distribution to make predictions. The predicted purchase cycle is obtained by calculating the expected value of the posterior distribution. The expectation of the gamma distribution is:

[0059]

[0060] Where E[x] is the predicted value of the customer purchase cycle, α n and β n are the updated shape and scale parameters.

[0061] It should be noted that by using Bayesian, companies can use historical data to form a prediction model for customer conversion time, and update the prediction results in real time based on new data, thereby more accurately estimating the customer's purchase cycle. This method combines the flexibility of the gamma distribution and the adaptability of Bayesian updates, and is very suitable for dealing with time prediction problems in customer relationship management.

[0062] Through the use of fuzzy reasoning based on historical data, the cycle threshold judgment rules for each high seas customer are obtained, and the cycle threshold judgment rules are used to divide them into short-term periodicity or long-term periodicity.

[0063] Users with short-term purchasing periodicity are directly used as the first recommended public sea pool. If they are users with long-term purchasing periodicity, the time data from the salesperson contacting the user to the user purchasing the item is analyzed, and the Bayesian method is used for prediction. Salespersons are recommended based on the purchasing periodicity and conversion time of each user. For example: when a customer only purchases in June every year, and the current time is March, the first preset time period is half a month, and the customer's conversion time is two months, the salesperson should contact the customer in mid-April. This condition is not met in the current month, so it is not used as the second recommended public sea pool. Those that meet the condition will be used as the second recommended public sea pool to facilitate early contact by the salesperson.

[0064] S3: Based on the correlation between the customers in the private seas of the target salesperson and the high seas customers, the high seas customer recommendation high seas pool includes a third recommended high seas pool with matching correlation between the allocated private seas customers and the unallocated high seas customers, and a fourth recommended high seas pool for replacement and recovery in the private seas of the salesperson;

[0065] The private seas pool of the target salesperson is obtained, and the customers of the target salesperson are analyzed based on the correlation analysis model trained by big data to obtain the correlation value between private seas customers and high seas customers, and the high seas customers whose correlation value is greater than a preset correlation threshold are placed in the third recommended high seas pool.

[0066] According to the replacement time calculation formula, the waiting time for the private sea customer to become a high seas customer when the salesperson replaces the private sea customer is obtained, and the fourth recommended high seas pool is obtained after sorting according to the waiting time, wherein the replacement time calculation formula is:

[0067]

[0068] in is the replacement duration, is the preset standard replacement time, ω is the adjustment factor, T 0 is the waiting time of the customer in the private sea, T 标 is the preset standard waiting time, T max It is the maximum waiting time for customers in private seas.

[0069] Private sea customers whose waiting time is less than or equal to the preset waiting time are taken as the first preset adding sequence, and private sea customers whose waiting time is greater than the preset waiting time are taken as the to-be-processed sequence, and a first pre-processed private sea customer is obtained based on the to-be-processed sequence, wherein the first pre-processed private sea customer is a private sea customer who purchases the same type of sales items within a preset time period, and based on the proportion of the types of sales items purchased by the first pre-processed private sea customer within the preset time period, an interest-specific parameter of each private sea customer is obtained, and an adjustment weight is obtained based on the interest-specific parameter and the number of purchases of each private sea customer, and private sea customers whose waiting time is greater than the weight threshold are put into the first preset adding sequence to obtain a fourth recommended high seas pool.

[0070] It should be noted that based on the frequency and total amount of communication between high seas customers and the target sales personnel's private seas customers, the big data is acquired and input into the correlation analysis model trained using the deep model to obtain the correlation value between them, and the ones with correlation values ​​greater than the preset threshold are used as the third recommended high seas pool.

[0071] According to the replacement time calculation formula, the replacement time of the customer replaced from the salesperson's private sea is obtained. This replacement time is the time it takes for the customer to be put back into the public sea pool. The replacement time formula can make the customer who has been waiting in the salesperson's queue for too long enter the public sea pool earlier, and enter the public sea pool later when the replacement time is too short. ω can be a random adjustment factor within a certain range to increase the uncertainty when entering the public sea pool, where T 标 Less than T max , T 0 In T 标 With T max Notification reminders can be sent to sales staff during the process.

[0072] Obtain all customers replaced by sales personnel, and based on the preset waiting time, add private sea customers with a waiting time less than or equal to the preset waiting time as the first preset adding sequence, wherein the interest-specific parameter of each private sea customer is obtained based on the first pre-processing of the private sea customers, and if the interest-specific parameter is less than or equal to the preset parameter, use it as the first weight of the private sea customer, for example: if the type of the sales item is life and the preset parameter is 0.4, and the purchase type of private sea customer A within the preset time period is life and fitness, then the interest-specific parameter of private sea customer A is 0.5, and the interest-specific parameter is multiplied by the number of purchases to obtain an adjusted weight, and the private sea customers with a weight greater than the weight threshold are put into the first preset adding sequence to obtain a fourth recommended high seas pool.

[0073] S4: Make customer recommendations to target sales staff based on the high seas customer recommendation pool.

[0074] The intersection of the first recommended public sea pool, the second recommended public sea pool and the third recommended public sea pool in the public sea customer recommendation public sea pool is obtained as the fifth recommended public sea pool, the customers who have been replaced by the target salesperson are removed from the fourth recommended public sea pool, and the remaining customers are used as the sixth recommended public sea pool, and the target salesperson is recommended based on the fifth recommended public sea pool and the sixth recommended public sea pool.

[0075] Embodiment 2: Based on Embodiment 1, a customer relationship management system based on big data analysis includes:

[0076] Data preprocessing module, used to clean data of high seas customers and private seas customers;

[0077] A cycle determination module, used to obtain the short-term periodicity or long-term periodicity of the customer's purchase periodicity;

[0078] The conversion time acquisition module is used to obtain the customer conversion time with long-term periodicity;

[0079] The first recommendation acquisition module is used to acquire high seas customers that meet historical short-term periodic purchase data;

[0080] The second recommendation acquisition module is used to acquire customers among long-term periodic customers who have the ability to be contacted by sales staff in advance;

[0081] The third recommendation acquisition module is used to select customers with a correlation greater than a preset threshold between the private sea customers and the high seas customers of the target salesperson;

[0082] The fourth recommendation acquisition module is used to obtain qualified customers replaced by each salesperson according to the replacement time and adjustment parameters;

[0083] Recommendation module, which makes recommendations to users based on all recommendation modules.

[0084] The above is a detailed introduction to the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A customer relationship management method based on big data analysis, characterized in that: The following steps are involved: S1: Obtain customer data on the high seas and customer data on the salesperson’s private seas, and pre-process them; S2: Based on the historical periodic purchase data of the customer, the public sea customer recommendation public sea pool includes a first recommended public sea pool that matches the unallocated public sea customers with the public sea customers who meet the historical short-term periodic purchase data, and a second recommended public sea pool that matches the unallocated public sea customers with the public sea customers who meet the historical long-term periodic purchase data and meet the advance contact time; S3: Based on the correlation between the customers in the private seas of the target salesperson and the high seas customers, the high seas customer recommendation high seas pool includes a third recommended high seas pool with matching correlation between the allocated private seas customers and the unallocated high seas customers, and a fourth recommended high seas pool for replacement and recovery in the private seas of the salesperson; S4: Make customer recommendations to target sales staff based on the high seas customer recommendation pool.

2. A customer relationship management method based on big data analysis according to claim 1, characterized in that: The method comprises obtaining the customer data on the high seas and the customer data on the private seas of the sales personnel, and pre-processing the customer data, including: performing data cleaning processing on the customer data to remove duplicate values, fill in missing values, and remove abnormal values.

3. The customer relationship management method based on big data analysis according to claim 1, characterized in that: The method based on the historical periodic purchase data of the customers, wherein the high seas customer recommendation high seas pool includes a first recommended high seas pool that matches unallocated high seas customers with high seas customers that meet the historical short-term periodic purchase data, and a second recommended high seas pool that matches unallocated high seas customers with high seas customers that meet the historical long-term periodic purchase data and meet the advance contact time, includes: obtaining the historical periodic purchase data of the high seas customers, using fuzzy reasoning to obtain a period threshold judgment rule based on the historical periodic purchase data of the high seas customers, and dividing the purchase periodicity of the high seas customers according to the period threshold judgment rule to obtain short-term periodicity or long-term periodicity.

4. The customer relationship management method based on big data analysis according to claim 1, characterized in that: The high seas customer recommendation high seas pool based on the customer's historical periodic purchase data includes a first recommended high seas pool that matches unallocated high seas customers with high seas customers that meet historical short-term periodic purchase data, and a second recommended high seas pool that matches unallocated high seas customers with high seas customers that meet historical long-term periodic purchase data and meet advance contact time, including: obtaining the conversion time of each high seas user based on a Bayesian algorithm, wherein the advance contact time is the conversion time of the high seas user, and obtaining high seas users whose conversion time intersects with that of each high seas user within a first preset time period of the current time period as the second recommended high seas pool.

5. The customer relationship management method based on big data analysis according to claim 4 is characterized in that: The method of obtaining the conversion time of each high seas user based on the Bayesian algorithm includes: S201: sorting the historical records of each customer to form a sample set of conversion time; S202: Select a probability distribution model and use the gamma distribution, where the probability density function of the gamma distribution is: Where x is the transformation time, α is the shape parameter, β is the scale parameter, and Γ(α) is the gamma function; S203: Determine a prior distribution, and determine initial probability distribution parameters as the prior distribution based on historical data; S204: Using the Bayesian update rule, the posterior distribution is: α n ＝α0+n； Where n is the number of observed samples, is the sum of all observed transformation times; S205: Use the updated posterior distribution to make predictions. The predicted purchase cycle is obtained by calculating the expected value of the posterior distribution. The expectation of the gamma distribution is: Where E[x] is the predicted value of the customer purchase cycle, α n and β n are the updated shape and scale parameters.

6. The customer relationship management method based on big data analysis according to claim 1, characterized in that: The public seas customer recommendation public seas pool based on the correlation between the target salesperson's private seas customers and the public seas customers includes a third recommended public seas pool that matches the correlation between allocated private seas customers and unallocated public seas customers, and a fourth recommended public seas pool for replacement and recovery in the salesperson's private seas, including: obtaining the private seas pool of the target salesperson, and analyzing the customers of the target salesperson based on the correlation analysis model trained by big data, obtaining the correlation value between the private seas customers and the public seas customers, and placing the public seas customers whose correlation value is greater than a preset correlation threshold into the third recommended public seas pool.

7. The customer relationship management method based on big data analysis according to claim 1, characterized in that: The public sea customer recommendation public sea pool based on the correlation between the private sea customers of the target salesperson and the public sea customers includes a third recommended public sea pool matching the correlation between the allocated private sea customers and the unallocated public sea customers, and a fourth recommended public sea pool for replacement and recovery in the private sea of ​​the salesperson, including: According to the replacement time calculation formula, the waiting time for the private sea customer to become a high seas customer when the salesperson replaces the private sea customer is obtained, and the fourth recommended high seas pool is obtained after sorting according to the waiting time, wherein the replacement time calculation formula is: in is the replacement duration, is the preset standard replacement time, ω is the adjustment factor, T0 is the waiting time of the customer in the private sea, T 标 is the preset standard waiting time, T max It is the maximum waiting time for customers in private seas.

8. The customer relationship management method based on big data analysis according to claim 7 is characterized in that: The fourth recommended high seas pool is obtained after sorting according to the waiting time, including: taking private sea customers with a waiting time less than or equal to a preset waiting time as a first preset adding sequence, taking private sea customers with a waiting time greater than the preset waiting time as a to-be-processed sequence, obtaining a first pre-processed private sea customer based on the to-be-processed sequence, wherein the first pre-processed private sea customer is a private sea customer who purchases the same type of sales items within a preset time period, obtaining interest-specific parameters of each private sea customer based on the proportion of the sales item types purchased by the first pre-processed private sea customer within the preset time period, obtaining an adjustment weight based on the interest-specific parameter and the number of purchases of each private sea customer, and placing private sea customers with a waiting time greater than a weight threshold into the first preset adding sequence to obtain a fourth recommended high seas pool.

9. The customer relationship management method based on big data analysis according to claim 1, characterized in that: The method of making customer recommendations to the target salesperson based on the high seas customer recommendation high seas pool includes: obtaining the intersection of the first recommended high seas pool, the second recommended high seas pool and the third recommended high seas pool in the high seas customer recommendation high seas pool as the fifth recommended high seas pool, removing the customers who have been replaced by the target salesperson from the fourth recommended high seas pool, and taking the remaining customers as the sixth recommended high seas pool, and making recommendations to the target salesperson based on the fifth recommended high seas pool and the sixth recommended high seas pool.

10. A customer relationship management system based on big data analysis, characterized in that: include: Data preprocessing module, used to clean data of high seas customers and private seas customers; A cycle determination module is used to obtain the short-term or long-term periodicity of the customer's purchase periodicity; The conversion time acquisition module is used to obtain the customer conversion time with long-term periodicity; The first recommendation acquisition module is used to acquire high seas customers that meet historical short-term periodic purchase data; The second recommendation acquisition module is used to acquire customers among long-term periodic customers who have the ability to be contacted by sales staff in advance; The third recommendation acquisition module is used to select customers with a correlation greater than a preset threshold between the private sea customers and the high seas customers of the target salesperson; The fourth recommendation acquisition module is used to obtain qualified customers replaced by each salesperson according to the replacement time and adjustment parameters; Recommendation module, which makes recommendations to users based on all recommendation modules.

Images