Customer relationship management system based on big data

Abstract

The invention provides a customer relationship management system based on big data, and relates to the technical field of information, and the system comprises a customer division module which is used for dividing customers into different customer types according to the industry characteristics, market positioning and business targets of an enterprise; the customer maintenance analysis module is used for acquiring maintenance related information of the customer and analyzing the maintenance related information to obtain a customer analysis result; and the return visit personnel configuration module is used for receiving the client analysis result, performing personnel configuration processing to obtain a corresponding return visit personnel, and sending a corresponding client maintenance list to an intelligent terminal of the return visit personnel. According to the invention, customer information is comprehensively collected by using a big data technology, customer types are accurately divided through a complex algorithm, expected customers and potential customers are accurately identified, a targeted marketing strategy basis is provided for enterprises, the market expansion efficiency is effectively improved, and the competitiveness of the enterprises in the market is enhanced.

Description

Technical Field

[0001] The present invention relates to the field of information technology, and in particular to a customer relationship management system based on big data. Background Art

[0002] In today's digital age, with the rapid development of information technology and the widespread popularity of the Internet, companies have accumulated massive amounts of customer data through various channels in their daily operations. These data cover customer behavior, preferences, consumption history and other aspects of information, and their scale and complexity are growing exponentially. On the one hand, the number of touchpoints for customers to interact with companies is increasing, including but not limited to corporate official websites, mobile applications, social media platforms, online customer service systems, and offline sales terminals. Every browsing, searching, consulting, purchasing or complaining behavior will leave a digital trace, forming a huge and complex data set.

[0003] Traditional customer relationship management methods often rely on manual experience and simple data statistical analysis, which makes it difficult to cope with complex needs in a big data environment. The traditional model is inefficient when processing massive amounts of data and cannot capture customers' dynamically changing needs and behavior patterns in a timely manner. Its customer classification method is relatively extensive, lacks accuracy and foresight, and makes it difficult to identify potential high-value customers. The analysis of customer maintenance needs is not in-depth and comprehensive enough to provide personalized service recommendations. In terms of the allocation of return personnel, there is a lack of scientific and reasonable basis, which can easily lead to a waste of human resources or uneven customer service quality. Therefore, it is necessary to provide a customer relationship management system based on big data to solve the above technical problems. Summary of the invention

[0004] The present invention provides a customer relationship management system based on big data, which solves the problems raised by the above-mentioned background technology.

[0005] In order to solve the above technical problems, the present invention provides a customer relationship management system based on big data, comprising: The data collection module initiates data collection instructions to each data source according to a preset cycle to obtain customer-related data fed back by the data source; The data storage module uses a distributed storage architecture to store customer-related data; The customer segmentation module is used to segment customers into different types according to the enterprise's industry characteristics, market positioning, and business goals; customer types include expected customers, existing customers, and potential customers; The customer maintenance analysis module is used to obtain the customer's maintenance-related information and analyze it to obtain the customer analysis results; the customer analysis results include the customer's contact interval, communication times, purchase frequency, purchase gold shadow value, customer maintenance value, regular maintenance strategy, customer push strategy, close customer maintenance list, and customer maintenance list to be activated; The return visit personnel configuration module is used to receive customer analysis results and perform personnel configuration processing to obtain corresponding return visit personnel, and send the corresponding customer maintenance list to the return visit personnel's smart terminal; after the return visit personnel receives the corresponding customer maintenance list through the smart terminal, they will return the corresponding customer maintenance list.

[0006] As a preferred method, customers are divided into different customer types according to the enterprise's industry characteristics, market positioning, and business goals. The logic of dividing the expected customers is as follows: Build an industry key intention vocabulary library, including several industry key intention vocabulary; obtain the customer's consultation text and search keyword list; Identify customer intended words from customer consultation texts and search keyword lists; Calculate the cosine similarity between the customer intention word and any industry key intention word in the industry key intention word library to obtain the matching similarity with the corresponding industry key intention word; set a minimum similarity threshold, and mark the customer intention word corresponding to the matching similarity greater than the minimum similarity threshold as a similar word; Identify the query time of the customer corresponding to the similar words, and calculate the time difference between the query time and the current time to obtain the similar word query time difference value; Identify the source channels of the consulting text or search keyword list corresponding to similar words, and assign source channel weights to different source channels; The word usage value is obtained by weighting the matching similarity of similar words, the time difference of similar word search and the weight of the source channel; Set a customer monitoring time zone, number similar words in the customer monitoring time zone, calculate the mean and standard deviation of the matching similarity of similar words in the customer monitoring time zone according to the number to obtain the similarity mean and similarity fluctuation value; record the number of similar words in the customer monitoring time zone and mark it as the similar word quantity; perform weighted calculation on the word usage values ​​of all similar words in the customer monitoring time zone to obtain the word comprehensive value; The similarity mean, similarity fluctuation value, similarity word quantity and word comprehensive value are weightedly calculated to obtain the key word score; a word score threshold is set, and if the key word score is greater than its word score threshold, the customer is marked as a desired customer.

[0007] As a preferred method, customers are divided into different customer types according to the enterprise's industry characteristics, market positioning, and business goals. The specific logic of dividing potential customers is as follows: Obtain search engine search history and count the number of searches that match industry keywords related to the enterprise within a set search cycle; Obtain the number of pages viewed, browsing time, and average page dwelling time of any customer search on the company's official website; The number of pages viewed, browsing time, and average page dwell time are weighted to obtain the search impact value; the search impact value of each search within the set search cycle is weighted to obtain the search score; a search score threshold is set, and if the search score is greater than the search score threshold, the customer is marked as a potential customer.

[0008] Preferably, the customer's maintenance related information is obtained and analyzed to obtain a customer analysis result, specifically: Obtain maintenance-related information for any customer type, including interaction history data, business transaction data, and external related data: The time interval between the last contact between the customer and the enterprise is recorded as the contact interval; Get the number of communications between customers and enterprises; Set products or services associated with the enterprise; set a purchase monitoring time zone, identify the number of purchases of products or services associated with the enterprise within the purchase monitoring time zone, and calculate the purchase frequency of products or services within the purchase monitoring time zone; obtain the purchase amount of any product or service, and calculate the statistical indicators of the product or service, including the total purchase amount, the maximum and minimum purchase amount, the average purchase amount, and the purchase amount fluctuation value; Perform weighted calculation on any of the statistical indicators of the product or service to obtain the purchase price shadow value; The customer maintenance value is obtained by weighted calculation of the contact interval, communication times, purchase frequency, and purchase gold shadow value; a maintenance threshold is set. If the customer maintenance value is greater than the maintenance threshold, the customer is marked as a close customer and a regular maintenance strategy is generated; the regular maintenance strategy is used to regularly maintain close customers, including regular return visits, priority push of new product information or exclusive promotions, and provision of value-added service experience; If the customer maintenance value is less than or equal to its maintenance threshold, the customer is marked as a customer to be activated, the customer's preset maintenance cycle is dynamically adjusted according to the customer maintenance value, and a customer push strategy is generated; Sort the customer maintenance values ​​of close customers by size to generate a close customer maintenance list; Sort the customer maintenance values ​​of the customers to be activated by size to generate a customer maintenance list to be activated; The customer's contact interval, number of communications, purchase frequency, purchase value, customer maintenance value, regular maintenance strategy, customer push strategy, close customer maintenance list, and customer maintenance list to be activated are marked as customer analysis results.

[0009] As a preferred method, receiving the customer analysis results and performing personnel allocation processing to obtain corresponding return visit personnel are specifically as follows: Divide the close customer maintenance list and the customer maintenance list to be activated, set the number of return visits to the sub-lists, and start from the head of the close customer maintenance list and the customer maintenance list to be activated, and divide the customers with the number of return visits in the sub-lists into the sub-customer maintenance lists corresponding to the close customer maintenance list and the customer maintenance list to be activated; then select customers from the remaining customers in the close customer maintenance list and the customer maintenance list to be activated according to the number of return visits in the sub-lists, and repeat the cycle until the customers in the close customer maintenance list and the customer maintenance list to be activated are divided, and a certain number of sub-close customer maintenance lists and sub-customer maintenance lists to be activated are obtained; Obtain the return visit personnel of the enterprise; feedback the information acquisition instruction to the intelligent terminal of the return visit personnel to obtain the personnel parameters of the return visit personnel, and process the personnel parameters to obtain the return visit value of the return visit personnel; Identify the return visit values ​​of all return visit personnel in the enterprise, and sort them in descending order according to the return visit values ​​to generate a return visit personnel list; The first sub-close customer maintenance list and customer maintenance list to be activated are assigned to the return visit personnel with the largest return visit value in the return visit personnel list; then the return visit personnel with the second highest return visit value are assigned to the next sub-close customer maintenance list and customer maintenance list to be activated, and so on until all sub-close customer maintenance lists and customer maintenance lists to be activated are assigned.

[0010] Preferably, the customer-related data includes behavioral data, interaction data and source data; wherein the behavioral data includes browsing records, dwell time on each page, search keywords, and usage frequency; the interaction data includes customer consultation content, complaint records, and purchase records; and the source data includes the keywords that the customer first encounters from the search engine and the corresponding search engine identifier.

[0011] Preferably, the personnel parameters are processed to obtain the return visit value of the return visit personnel, specifically: Obtain the personnel parameters of the return visit personnel, including years of service and past service performance data; among which, past service performance data includes customer satisfaction score, problem solving efficiency, and return visit success rate; The return visit value is obtained by weighting the working years of the return visit personnel and all the parameters in the past service performance data.

[0012] Preferably, when information acquisition instructions are fed back to the intelligent terminal of the return visit personnel, if there is no timely response within the set time, the instructions are resent according to the set time interval, and the number of times the instructions are resent is counted; a threshold for the number of times the instructions are resent is set, and if the number of times the instructions are resent is greater than the threshold, the return visit personnel is marked as abnormal, and the customer maintenance list allocation is temporarily adjusted, and the customer maintenance list allocated to the return visit personnel is reallocated to the return visit personnel with the next highest return value.

[0013] Compared with the related art, the customer relationship management system based on big data provided by the present invention has the following beneficial effects: 1. The present invention uses big data technology to comprehensively collect customer information, accurately divides customer types through complex algorithms, accurately identifies expected customers and potential customers, provides companies with a basis for targeted marketing strategies, effectively improves market expansion efficiency, and enhances the competitiveness of companies in the market.

[0014] 2. The present invention can scientifically configure the return visit tasks according to the ability characteristics of the return visit personnel through the return visit personnel configuration module, ensuring that the customer is connected with the most suitable return visit personnel. This not only improves the return visit efficiency and reduces the waste of human resources, but also enhances the customer communication experience, further consolidates customer relationships, and creates greater value for the enterprise. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A principle block diagram of a customer relationship management system based on big data provided by the present invention. DETAILED DESCRIPTION

[0016] 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.

[0017] The terms used in this disclosure are for the purpose of describing specific embodiments only and are not intended to limit the disclosure. The singular forms of "group", "class" and "the" used in this disclosure and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0018] It should be understood that although the terms first, second, third, etc. may be used in the present disclosure to describe various information, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present disclosure, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0019] Please refer to Figure 1 A customer relationship management system based on big data, comprising: The data collection module initiates data collection instructions to each data source according to a preset period to obtain customer-related data fed back by the data source; the preset period can be set as needed, such as hourly / daily, etc.; The data storage module uses a distributed storage architecture to store customer-related data; The customer segmentation module is used to segment customers into different types according to the enterprise's industry characteristics, market positioning, and business objectives. Customer types include expected customers, existing customers, and potential customers. Existing customers refer to customers with whom the enterprise has established cooperation. The customer maintenance analysis module is used to obtain the customer's maintenance-related information and analyze it to obtain the customer analysis results; the customer analysis results include the customer's contact interval, communication times, purchase frequency, purchase gold shadow value, customer maintenance value, regular maintenance strategy, customer push strategy, close customer maintenance list, and customer maintenance list to be activated; The return visit personnel configuration module is used to receive customer analysis results and perform personnel configuration processing to obtain corresponding return visit personnel, and send the corresponding customer maintenance list to the return visit personnel's smart terminal; after the return visit personnel receives the corresponding customer maintenance list through the smart terminal, they will return the corresponding customer maintenance list.

[0020] Customers are divided into different types according to the company's industry characteristics, market positioning, and business goals. The logic of dividing expected customers is as follows: Build an industry key intention vocabulary library, including several industry key intention vocabulary; obtain the customer's consultation text and search keyword list; Identify customer intended words from customer consultation texts and search keyword lists; Calculate the cosine similarity between the customer intention word and any industry key intention word in the industry key intention word library to obtain the matching similarity with the corresponding industry key intention word; set a minimum similarity threshold, and mark the customer intention word corresponding to the matching similarity greater than the minimum similarity threshold as a similar word; Identify the query time of the customer corresponding to the similar words, and calculate the time difference between the query time and the current time to obtain the similar word query time difference value; Identify the source channels of the consulting text or search keyword list corresponding to similar words, and assign source channel weights to different source channels; The word usage value is obtained by weighting the matching similarity of similar words, the time difference of similar word search and the weight of the source channel; Set a customer monitoring time zone, number similar words in the customer monitoring time zone, calculate the mean and standard deviation of the matching similarity of similar words in the customer monitoring time zone according to the number to obtain the similarity mean and similarity fluctuation value; record the number of similar words in the customer monitoring time zone and mark it as the similar word quantity; perform weighted calculation on the word usage values ​​of all similar words in the customer monitoring time zone to obtain the word comprehensive value; The similarity mean, similarity fluctuation value, similarity word quantity and word comprehensive value are weightedly calculated to obtain the key word score; a word score threshold is set, and if the key word score is greater than its word score threshold, the customer is marked as a desired customer.

[0021] Customers are divided into different types according to the company's industry characteristics, market positioning, and business goals. The logic of dividing potential customers is as follows: Obtain search engine search history and count the number of searches that match industry keywords related to the enterprise within a set search cycle; Obtain the number of pages viewed, browsing time, and average page dwelling time of any customer search on the company's official website; The number of pages viewed, browsing time, and average page dwell time are weighted to obtain the search impact value; the search impact value of each search within the set search cycle is weighted to obtain the search score; a search score threshold is set, and if the search score is greater than the search score threshold, the customer is marked as a potential customer.

[0022] Obtain the customer's maintenance related information and analyze it to obtain the customer analysis results, specifically: Obtain maintenance-related information for any customer type, including interaction history data, business transaction data, and external related data: The time interval between the last contact between the customer and the enterprise is recorded as the contact interval; Get the number of communications between customers and enterprises; Set products or services associated with the enterprise; set a purchase monitoring time zone, identify the number of purchases of products or services associated with the enterprise within the purchase monitoring time zone, and calculate the purchase frequency of products or services within the purchase monitoring time zone; obtain the purchase amount of any product or service, and calculate statistical indicators of the product or service, including the total purchase amount, the maximum and minimum purchase amount, the average purchase amount, and the purchase amount fluctuation value, which is obtained by calculating the standard deviation of the purchase amount within the purchase monitoring time zone; Perform weighted calculation on any of the statistical indicators of the product or service to obtain the purchase price shadow value; The customer maintenance value is obtained by weighted calculation of the contact interval, communication times, purchase frequency, and purchase shadow value; a maintenance threshold is set. If the customer maintenance value is greater than the maintenance threshold, it means that there has been no recent contact, the number of communications is small, the purchase frequency is high, and the purchase shadow value is large, indicating that the customer has great potential. The customer is then marked as a close customer and a regular maintenance strategy is generated. The regular maintenance strategy is used to regularly maintain close customers, including regular return visits, priority push of new product information or exclusive promotions, and provision of value-added service experience; If the customer maintenance value is less than or equal to its maintenance threshold, the customer is marked as a customer to be activated, the customer's preset maintenance cycle is dynamically adjusted according to the customer maintenance value, and a customer push strategy is generated; Sort the customer maintenance values ​​of close customers by size to generate a close customer maintenance list; Sort the customer maintenance values ​​of the customers to be activated by size to generate a customer maintenance list to be activated; The customer's contact interval, number of communications, purchase frequency, purchase value, customer maintenance value, regular maintenance strategy, customer push strategy, close customer maintenance list, and customer maintenance list to be activated are marked as customer analysis results.

[0023] Receive customer analysis results and perform staffing processing to obtain corresponding return visit personnel, specifically: Divide the close customer maintenance list and the customer maintenance list to be activated, set the number of return visits to the sub-lists, and start from the head of the close customer maintenance list and the customer maintenance list to be activated, and divide the customers with the number of return visits in the sub-lists into the sub-customer maintenance lists corresponding to the close customer maintenance list and the customer maintenance list to be activated; then select customers from the remaining customers in the close customer maintenance list and the customer maintenance list to be activated according to the number of return visits in the sub-lists, and repeat the cycle until the customers in the close customer maintenance list and the customer maintenance list to be activated are divided, and a certain number of sub-close customer maintenance lists and sub-customer maintenance lists to be activated are obtained; Obtain the return visit personnel of the enterprise; feedback the information acquisition instruction to the intelligent terminal of the return visit personnel to obtain the personnel parameters of the return visit personnel, and process the personnel parameters to obtain the return visit value of the return visit personnel; Identify the return visit values ​​of all return visit personnel in the enterprise, and sort them in descending order according to the return visit values ​​to generate a return visit personnel list; The first sub-close customer maintenance list and customer maintenance list to be activated are assigned to the return visit personnel with the largest return visit value in the return visit personnel list; then the return visit personnel with the second highest return visit value are assigned to the next sub-close customer maintenance list and customer maintenance list to be activated, and so on until all sub-close customer maintenance lists and customer maintenance lists to be activated are assigned.

[0024] Customer-related data includes behavioral data, interaction data and source data; among them, behavioral data includes browsing records, dwell time on each page, search keywords, and usage frequency; interaction data includes customer consultation content, complaint records, and purchase records; source data includes the keywords that the customer first encounters from the search engine and the corresponding search engine identifier.

[0025] The personnel parameters are processed to obtain the return visit value of the return visit personnel, specifically: Obtain the personnel parameters of the return visit personnel, including years of work experience and past service performance data; among which, the past service performance data includes customer satisfaction score, problem solving efficiency, and return visit success rate; it should be noted that, among them, the customer satisfaction score is the average score calculated by equally dividing the return visits of all customers to the return visit personnel in history; the problem solving efficiency is measured by the average time spent on solving a single customer problem; the return visit success rate is the behavior of customers purchasing the company's products or upgrading services, renewing contracts, etc. within a set time after the return visit, which is marked as a successful return visit, and the proportion of successful return visits to the total number of return visits is the return visit success rate.

[0026] The return visit value is obtained by weighting the working years of the return visit personnel and all the parameters in the past service performance data.

[0027] When feeding back information to the intelligent terminal of the return visit personnel to obtain instructions, if there is no timely response within the set time, the instructions will be resent at the set time interval, and the number of resent instructions will be counted; a threshold for the number of resent instructions will be set. If the number of resent instructions is greater than the threshold, the return visit personnel will be marked as abnormal, and the customer maintenance list allocation will be temporarily adjusted. The customer maintenance list allocated to the return visit personnel will be reallocated to the return visit personnel with the next highest return visit value. Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed in this disclosure. The specification and examples are to be considered exemplary only, and the true scope and spirit of the present invention are indicated by the following claims.

[0028] It should be understood that the present invention is not limited to the exact construction that has been described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A customer relationship management system based on big data, characterized in that: include: The data collection module initiates data collection instructions to each data source according to a preset cycle to obtain customer-related data fed back by the data source; The data storage module uses a distributed storage architecture to store customer-related data; The customer segmentation module is used to segment customers into different types according to the enterprise's industry characteristics, market positioning, and business goals; customer types include expected customers, existing customers, and potential customers; The customer maintenance analysis module is used to obtain the customer's maintenance-related information and analyze it to obtain the customer analysis results; the customer analysis results include the customer's contact interval, communication times, purchase frequency, purchase gold shadow value, customer maintenance value, regular maintenance strategy, customer push strategy, close customer maintenance list, and customer maintenance list to be activated; The return visit personnel configuration module is used to receive customer analysis results and perform personnel configuration processing to obtain corresponding return visit personnel, and send the corresponding customer maintenance list to the return visit personnel's smart terminal; after the return visit personnel receives the corresponding customer maintenance list through the smart terminal, they will return the corresponding customer maintenance list.

2. A customer relationship management system based on big data according to claim 1, characterized in that: Customers are divided into different types according to the company's industry characteristics, market positioning, and business goals. The logic of dividing expected customers is as follows: Build an industry key intention vocabulary library, including several industry key intention vocabulary; obtain the customer's consultation text and search keyword list; Identify customer intended words from customer consultation texts and search keyword lists; Calculate the cosine similarity between the customer intention word and any industry key intention word in the industry key intention word library to obtain the matching similarity with the corresponding industry key intention word; set a minimum similarity threshold, and mark the customer intention word corresponding to the matching similarity greater than the minimum similarity threshold as a similar word; Identify the query time of the customer corresponding to the similar words, and calculate the time difference between the query time and the current time to obtain the similar word query time difference value; Identify the source channels of the consulting text or search keyword list corresponding to similar words, and assign source channel weights to different source channels; The word usage value is obtained by weighting the matching similarity of similar words, the time difference of similar word search and the weight of the source channel; Set a customer monitoring time zone, number similar words in the customer monitoring time zone, calculate the mean and standard deviation of the matching similarity of similar words in the customer monitoring time zone according to the number to obtain the similarity mean and similarity fluctuation value; record the number of similar words in the customer monitoring time zone and mark it as the similar word quantity; perform weighted calculation on the word usage values ​​of all similar words in the customer monitoring time zone to obtain the word comprehensive value; The similarity mean, similarity fluctuation value, similarity word quantity and word comprehensive value are weightedly calculated to obtain the key word score; a word score threshold is set, and if the key word score is greater than its word score threshold, the customer is marked as a desired customer.

3. A customer relationship management system based on big data according to claim 1, characterized in that: Customers are divided into different types according to the company's industry characteristics, market positioning, and business goals. The logic of dividing potential customers is as follows: Obtain search engine search history and count the number of searches that match industry keywords related to the enterprise within a set search cycle; Obtain the number of pages viewed, browsing time, and average page dwelling time of any customer search on the company's official website; The number of pages viewed, browsing time, and average page dwell time are weighted to obtain the search impact value; the search impact value of each search within the set search cycle is weighted to obtain the search score; a search score threshold is set, and if the search score is greater than the search score threshold, the customer is marked as a potential customer.

4. A customer relationship management system based on big data according to claim 1, characterized in that: Obtain the customer's maintenance related information and analyze it to obtain the customer analysis results, specifically: Obtain maintenance-related information for any customer type, including interaction history data, business transaction data, and external related data: The time interval between the last contact between the customer and the enterprise is recorded as the contact interval; Get the number of communications between customers and enterprises; Set products or services associated with the enterprise; set a purchase monitoring time zone, identify the number of purchases of products or services associated with the enterprise within the purchase monitoring time zone, and calculate the purchase frequency of products or services within the purchase monitoring time zone; obtain the purchase amount of any product or service, and calculate the statistical indicators of the product or service, including the total purchase amount, the maximum and minimum purchase amount, the average purchase amount, and the purchase amount fluctuation value; Perform weighted calculation on any of the statistical indicators of the product or service to obtain the purchase price shadow value; The customer maintenance value is obtained by weighted calculation of the contact interval, communication times, purchase frequency, and purchase gold shadow value; a maintenance threshold is set. If the customer maintenance value is greater than the maintenance threshold, the customer is marked as a close customer and a regular maintenance strategy is generated; the regular maintenance strategy is used to regularly maintain close customers, including regular return visits, priority push of new product information or exclusive promotions, and provision of value-added service experience; If the customer maintenance value is less than or equal to its maintenance threshold, the customer is marked as a customer to be activated, the customer's preset maintenance cycle is dynamically adjusted according to the customer maintenance value, and a customer push strategy is generated; Sort the customer maintenance values ​​of close customers by size to generate a close customer maintenance list; Sort the customer maintenance values ​​of the customers to be activated by size to generate a customer maintenance list to be activated; The customer's contact interval, number of communications, purchase frequency, purchase value, customer maintenance value, regular maintenance strategy, customer push strategy, close customer maintenance list, and customer maintenance list to be activated are marked as customer analysis results.

5. A customer relationship management system based on big data according to claim 1, characterized in that: Receive customer analysis results and perform staffing processing to obtain corresponding return visit personnel, specifically: Divide the close customer maintenance list and the customer maintenance list to be activated, set the number of return visits to the sub-lists, and start from the head of the close customer maintenance list and the customer maintenance list to be activated, and divide the customers with the number of return visits in the sub-lists into the sub-customer maintenance lists corresponding to the close customer maintenance list and the customer maintenance list to be activated; then select customers from the remaining customers in the close customer maintenance list and the customer maintenance list to be activated according to the number of return visits in the sub-lists, and repeat the cycle until the customers in the close customer maintenance list and the customer maintenance list to be activated are divided, and a certain number of sub-close customer maintenance lists and sub-customer maintenance lists to be activated are obtained; Obtain the return visit personnel of the enterprise; feedback the information acquisition instruction to the intelligent terminal of the return visit personnel to obtain the personnel parameters of the return visit personnel, and process the personnel parameters to obtain the return visit value of the return visit personnel; Identify the return visit values ​​of all return visit personnel in the enterprise, and sort them in descending order according to the return visit values ​​to generate a return visit personnel list; The first sub-close customer maintenance list and customer maintenance list to be activated are assigned to the return visit personnel with the largest return visit value in the return visit personnel list; then the return visit personnel with the second highest return visit value are assigned to the next sub-close customer maintenance list and customer maintenance list to be activated, and so on until all sub-close customer maintenance lists and customer maintenance lists to be activated are assigned.

6. A customer relationship management system based on big data according to claim 1, characterized in that: The customer-related data includes behavioral data, interaction data and source data; among them, behavioral data includes browsing records, dwell time on each page, search keywords, and usage frequency; interaction data includes customer consultation content, complaint records, and purchase records; source data includes the keywords that the customer first encounters from the search engine and the corresponding search engine identifier.

7. A customer relationship management system based on big data according to claim 5, characterized in that: The personnel parameters are processed to obtain the return visit value of the return visit personnel, specifically: Obtain the personnel parameters of the return visit personnel, including years of service and past service performance data; among which, past service performance data includes customer satisfaction score, problem solving efficiency, and return visit success rate; The return visit value is obtained by weighting the working years of the return visit personnel and all the parameters in the past service performance data.

8. The customer relationship management system based on big data according to claim 1, characterized in that: When feeding back information acquisition instructions to the intelligent terminal of the return visitor, if there is no timely response within the set time, the instruction will be resent according to the set time interval, and the number of resent instructions will be counted; Set a threshold for the number of resending instructions. If the number of resending instructions is greater than the threshold, the return visitor will be marked as abnormal, and the customer maintenance list allocation will be temporarily adjusted. The customer maintenance list allocated to the return visitor will be reallocated to the return visitor with the next highest return visit value.

Images