User behavior analysis customer service management system based on big data

Abstract

The invention relates to the technical field of customer service management, and discloses a user behavior analysis customer service management system based on big data. The system comprises a user data collection module, a merchant data collection module, a user behavior analysis module and customer service distribution management. According to the system, a user data collection module collects and calculates the credit rating of a user, the historical communication condition with a customer service and the historical credit conservation times and default times of the user, and after collection is completed, the user data collection module sends collected data to a user behavior analysis module; meanwhile, the merchant data collection module collects the merchant credit rating and history of the merchant who currently generates the appeal with the user and the service record of the user, and sends the collected data to the user behavior analysis module, and the user behavior analysis module receives the data transmitted by the user behavior analysis module and the user behavior analysis module; and whether the current appeal is a normal appeal or a malicious appeal is analyzed, and the weight indexes corresponding to different appeals are inconsistent, so that the working pressure of customer service staff is reduced.

Description

Technical Field

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

[0002] As an institution for communication between users and merchants, customer service plays an important role in helping merchants promote their own products and services, solve customer problems, and maintain old customers. The results of communication between customer service personnel or intelligent customer service and customers largely affect customers' impression of the entire merchant, and also indirectly affect customers' consumption of merchant products. The results of customer service's responses to customers can generally be reflected in the customer's satisfaction with the customer service. The existing intelligent customer service in most industries has the problem of being able to answer too few questions or too simple questions. Most customers can only find manual service to solve their problems. Manual service can be roughly divided into two types. One is that customer service personnel communicate with customers by typing text online. This method has the problem of slow customer service response and untimely reply. The other method is that customer service personnel communicate with customers by phone. Although this method is more intimate than the first method, the customer service personnel can answer questions quickly; Prior art CN 108197963 A discloses an intelligent customer service management system, which includes a client, a cloud database, a network module, an intelligent service module, a manual service module, and a call analysis module; the client is the user's operating end; the cloud database includes a recording module and a question bank; the intelligent service module includes a promotion module, a retrieval module, and an automatic reply module; the manual service module includes a text communication end and a call communication end; the call analysis module is used to time the call time in segments, analyze the changes in the customer's call speed and volume, and obtain data on the customer's emotional changes; the network module is respectively connected to the client, the intelligent service module, and the manual service module, and the cloud database is respectively connected to the intelligent service module, the manual service module, and the call analysis module. By testing the customer's emotional state during the call, the customer's satisfaction with the customer service can be obtained more objectively.

[0003] However, this technology only takes into account the customer satisfaction with the customer service. If some customers make malicious complaints, the customer service itself will face tremendous pressure. At the same time, it does not take into account the impact of malicious complaints on the performance salary of the customer service itself. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a customer service management system for user behavior analysis based on big data, which has the advantages of accurately identifying whether the user's demands are normal or malicious, and solves the above technical problems.

[0005] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a user behavior analysis customer service management system based on big data, comprising a user data collection module, a merchant data collection module, a user behavior analysis module and a customer service allocation management module; The user data collection module includes a user individual data collection unit, a user behavior collection unit and a user credit data collection unit. The user individual data collection unit is used to collect the user's individual data, including the user's credit rating. The user behavior collection unit is used to collect the user's communication process with the merchant before communicating with the customer service. The user credit data collection unit is used to collect the number of times the user has kept his or her promise and the number of times he or she has violated the contract in history. The user data collection module sends the collected data to the user behavior analysis module. The merchant data collection module is used to collect merchant data that the user currently has a demand for, including the merchant's credit rating and history and the user's service record, and send the collected data to the user behavior analysis module; The user behavior analysis module is used to evaluate the reliability of the user's current behavior, and analyze whether the current demand is a normal demand or a malicious demand, and send the calculation result to the customer service allocation management module for customer service allocation; The customer service allocation management module includes a customer service scheduling unit and a customer service performance calculation unit. The customer service scheduling unit is used to calculate the saturation level of the current customer service and allocate unsaturated customer service to the user's pending requests. The customer service performance calculation unit is used to calculate the performance of the customer service based on the situation of handling user requests.

[0006] As a preferred technical solution of the present invention, the specific process of collecting user credit ratings by the user individual data collection module is as follows: A1. Read user The credit rating of all platforms; A2. Calculate the comprehensive credit score based on the credit rating on different platforms .

[0007] As a preferred technical solution of the present invention, the step A2 calculates the user The expression of the comprehensive credit rating is as follows: ,in, Indicates user In the The scoring index function of the platform, Indicates to users Sum the score indicators of all platforms. Indicates user In the The rating level of each platform, Indicates user Comprehensive credit score, Indicates user The total number of accounts on different platforms.

[0008] As a preferred technical solution of the present invention, the user In the The scoring index function of each platform The expression is as follows: ,in, Indicates user In the The scoring indicator of the platform is high credit. Indicates user In the The rating indicator of the platform is medium credit. Indicates user In the The scoring indicator of the platform is low credit.

[0009] As a preferred technical solution of the present invention, the steps of merchant credit rating in the merchant data collection module are as follows: B1. Check whether the merchant has branches on other platforms. If so, execute step B2. If not, use the credit rating of the merchant on the platform where the current user and the merchant have a claim as the merchant's credit rating; B2. Calculate the average credit rating of merchants across the entire platform and derive the merchant credit rating.

[0010] As a preferred technical solution of the present invention, the specific steps of the user behavior analysis module to identify whether the current user's demand is a normal demand or a malicious demand are as follows: C1. Comparison of users The communication process with the merchant before communicating with customer service and the merchant’s communication with the user Is the content recorded in the service record consistent with that of the user? The content of the communication process with the merchant before communicating with customer service is less than that of the merchant to the user. If the content in the service record is malicious, the user The content of the communication with the merchant before communicating with customer service is equal to or more than the merchant's If the content in the service record is found, C2 is executed; C2. Calculate the user's demand index , and judge whether the appeal is normal or malicious based on the appeal index. The request will be deemed as a malicious request. Then the request will be deemed as a normal request.

[0011] As a preferred technical solution of the present invention, the user Demand Index The expression is as follows: ,in, Indicates user The appeal index, Indicates user The number of times the contract is observed, Indicates user The number of defaults, Indicates the credit rating of the merchant.

[0012] As a preferred technical solution of the present invention, the expression for calculating the saturation level of the current customer service by the customer service scheduling unit is as follows: ,in, represents the weight of malicious claims, Indicates processing user The time required, Indicates customer service The saturation level, Indicates working hours, Indicates the customer service overtime hours.

[0013] As a preferred technical solution of the present invention, the malicious appeal weight The expression is as follows: ,in, represents the weight of malicious claims, Indicates user For normal demands, Indicates user is a malicious request, and the weight is , Indicates customer service This is the Vth malicious claim handled today.

[0014] As a preferred technical solution of the present invention, the expression of the customer service performance calculation unit is as follows: ,in, Indicates customer service performance, Indicates customer service Basic performance in handling normal requests, Indicates customer service Performance in handling malicious claims, Indicates hourly wage.

[0015] Compared with the prior art, the present invention provides a customer service management system for user behavior analysis based on big data, which has the following beneficial effects: The present invention collects and calculates the user's credit rating, historical communication with customer service, and the number of times the user has kept his promise and violated his contract in history through a user data collection module. After the collection is completed, the user data collection module sends the collected data to the user behavior analysis module. At the same time, the merchant data collection module collects the merchant credit rating and historical service record of the merchant with which the user currently has a demand, and sends the collected data to the user behavior analysis module. After receiving the data transmitted by the two modules respectively, the user behavior analysis module analyzes whether the current demand is a normal demand or a malicious demand, and reduces the work pressure of the customer service by having different corresponding weight indexes for different demands. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 Schematic diagram of the system framework of the present invention. 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] See also Figure 1 , a user behavior analysis customer service management system based on big data, including a user data collection module, a merchant data collection module, a user behavior analysis module and a customer service allocation management module; The user data collection module includes a user individual data collection unit, a user behavior collection unit and a user credit data collection unit. The user individual data collection unit is used to collect the user's individual data, including the user's credit rating. The user behavior collection unit is used to collect the user's communication process with the merchant before communicating with the customer service. The user credit data collection unit is used to collect the number of times the user has kept his or her promise and the number of times he or she has defaulted on his or her promise in history. The user data collection module sends the collected data to the user behavior analysis module. The merchant data collection module is used to collect merchant data that the user currently has requests for, including the merchant's credit rating and history and the user's service record, and send the collected data to the user behavior analysis module; The user behavior analysis module is used to evaluate the reliability of the user's current behavior and analyze whether the current demand is normal or malicious, and send the calculation results to the customer service allocation management module for customer service allocation; The customer service allocation management module includes a customer service scheduling unit and a customer service performance calculation unit. The customer service scheduling unit is used to calculate the saturation level of the current customer service and allocate unsaturated customer service to the user's pending requests. The customer service performance calculation unit is used to calculate the performance of the customer service based on the situation of the customer service handling the user's request. The expression for calculating the saturation level of the current customer service by the customer service scheduling unit is as follows: ,in, Indicates processing user The time required, Indicates customer service The saturation level, Indicates working hours, Indicates the length of customer service overtime. When there are more malicious requests, customer service work is more likely to be saturated. This indicates that customer service work is saturated. Indicates the weight of malicious claims, The expression is as follows: ,in, represents the weight of malicious claims, Indicates user For normal demands, Indicates user is a malicious request, and the weight is , Indicates customer service This is the Vth malicious claim handled today.

[0019] The expression of the customer service performance calculation unit is as follows: ,in, Indicates customer service performance, Indicates customer service Basic performance in handling normal requests, Indicates customer service Performance in handling malicious claims, Indicates hourly wage.

[0020] The specific process of collecting user credit ratings by the user individual data collection module is as follows: A1. Read user The credit rating of all platforms; A2. Calculate the comprehensive credit score based on the credit rating on different platforms , calculate users The expression of the comprehensive credit rating is as follows: ,in, Indicates to users Sum the score indicators of all platforms. Indicates user In the The rating level of each platform, Indicates user Comprehensive credit score, Indicates user Total number of accounts on different platforms, Indicates user In the The scoring index function of the platform, user In the The scoring index function of each platform The expression is as follows: ,in, Indicates user In the The scoring indicator of the platform is high credit. Indicates user In the The rating indicator of the platform is medium credit. Indicates user In the The scoring indicator of the platform is low credit.

[0021] The merchant credit rating in the merchant data collection module first retrieves whether the merchant has branches on other platforms. If there are no branches, the credit rating of the merchant on the platform where the current user and the merchant have a dispute is used as the merchant credit rating. If there are branches, the average credit rating of the merchant on the entire platform is calculated to obtain the merchant credit rating.

[0022] The user behavior analysis module identifies the current user Is the appeal normal or malicious? First, compare the user The communication process with the merchant before communicating with customer service and the merchant’s communication with the user Is the content recorded in the service record consistent with that of the user? The content of the communication process with the merchant before communicating with customer service is less than that of the merchant to the user. If the content in the service record is malicious, the user The content of the communication with the merchant before communicating with customer service is equal to or more than the merchant's The content in the service record is used to calculate the user's demand index , and judge whether the appeal is normal or malicious based on the appeal index. The request will be deemed as a malicious request. Then the request will be deemed as a normal request.

[0023] in, Indicates user The appeal index, Indicates user The number of times the contract is observed, Indicates user The number of defaults, Indicates the credit rating of the merchant.

[0024] The specific workflow of the present invention is as follows: The user data collection module collects and calculates the user's credit rating, historical communication with customer service, and the number of times the user has kept his promises and breached his promises in history. After the collection is completed, the user data collection module sends the collected data to the user behavior analysis module. At the same time, the merchant data collection module collects the merchant credit rating and historical service record of the merchant with which the user currently has a request, and sends the collected data to the user behavior analysis module. After receiving the data transmitted by the two modules, the user behavior analysis module analyzes whether the current request is normal or malicious, and sends the calculation result to the customer service allocation management module for customer service allocation, giving priority to allocating users to unsaturated users.

[0025] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A customer service management system for user behavior analysis based on big data, characterized by: It includes user data collection module, merchant data collection module, user behavior analysis module and customer service allocation management module; The user data collection module includes a user individual data collection unit, a user behavior collection unit and a user credit data collection unit. The user individual data collection unit is used to collect the user's individual data, including the user's credit rating. The user behavior collection unit is used to collect the user's communication process with the merchant before communicating with the customer service. The user credit data collection unit is used to collect the number of times the user has kept his or her promise and the number of times he or she has violated the promise in history. The user data collection module sends the collected data to the user behavior analysis module. The merchant data collection module is used to collect merchant data that the user currently has a demand for, including the merchant's credit rating and history and the user's service record, and send the collected data to the user behavior analysis module; The user behavior analysis module is used to evaluate the reliability of the user's current behavior, and analyze whether the current demand is a normal demand or a malicious demand, and send the calculation result to the customer service allocation management module for customer service allocation; The customer service allocation management module includes a customer service scheduling unit and a customer service performance calculation unit. The customer service scheduling unit is used to calculate the saturation level of the current customer service and allocate unsaturated customer service to the user's pending requests. The customer service performance calculation unit is used to calculate the performance of the customer service based on the situation of handling user requests.

2. According to claim 1, a customer service management system for user behavior analysis based on big data is characterized by: The specific process of collecting user credit ratings by the user individual data collection module is as follows: A1. Read user The credit rating of all platforms; A2. Calculate the comprehensive credit score based on the credit rating on different platforms .

3. According to claim 2, a customer service management system for user behavior analysis based on big data is characterized by: In step A2, the user is calculated The expression of the comprehensive credit rating is as follows: ,in, Indicates user In the The scoring index function of each platform, Indicates to users Sum the score indicators of all platforms. Indicates user In the The rating level of each platform, Indicates user Comprehensive credit score, Indicates user The total number of accounts on different platforms.

4. According to claim 3, a customer service management system for user behavior analysis based on big data is characterized by: The user In the The scoring index function of each platform The expression is as follows: ,in, Indicates user In the The scoring indicator of the platform is high credit. Indicates user In the The rating indicator of the platform is medium credit. Indicates user In the The scoring indicator of the platform is low credit.

5. According to claim 3, a customer service management system for user behavior analysis based on big data is characterized by: The steps of merchant credit rating in the merchant data collection module are as follows: B1. Check whether the merchant has branches on other platforms. If so, execute step B2. If not, use the credit rating of the merchant on the platform where the current user and the merchant have a claim as the merchant's credit rating; B2. Calculate the average credit rating of merchants across the entire platform and derive the merchant credit rating.

6. A customer service management system for user behavior analysis based on big data according to claim 5, characterized in that: The specific steps of the user behavior analysis module to identify whether the current user's request is a normal request or a malicious request are as follows: C1. Comparison of users The communication process with the merchant before communicating with customer service and the merchant’s communication with the user Is the content recorded in the service record consistent with that of the user? The content of the communication process with the merchant before communicating with customer service is less than that of the merchant to the user. If the content in the service record is malicious, the user The content of the communication with the merchant before communicating with customer service is equal to or more than the merchant's If the content in the service record is found, C2 is executed; C2. Calculate the user's demand index , and judge whether the appeal is normal or malicious based on the appeal index. The request will be deemed as a malicious request. Then the request will be deemed as a normal request.

7. The user behavior analysis customer service management system based on big data according to claim 6, characterized in that: The user Demand Index The expression is as follows: ,in, Indicates user The appeal index, Indicates user The number of times the contract is observed, Indicates user The number of defaults, Indicates the credit rating of the merchant.

8. The user behavior analysis customer service management system based on big data according to claim 6, characterized in that: The expression used by the customer service scheduling unit to calculate the saturation level of the current customer service is as follows: ,in, represents the weight of malicious claims, Indicates processing user The time required, Customer Service The saturation level, Indicates working hours, Indicates the customer service overtime hours.

9. The user behavior analysis customer service management system based on big data according to claim 8, characterized in that: The weight of the malicious request The expression is as follows: ,in, represents the weight of malicious claims, Indicates user For normal demands, Indicates user is a malicious request, and the weight is , Customer Service This is the Vth malicious claim handled today.

10. The user behavior analysis customer service management system based on big data according to claim 8, characterized in that: The expression of the customer service performance calculation unit is as follows: ,in, Customer Service performance, Customer Service Basic performance in handling normal requests, Customer Service Performance in handling malicious claims, Indicates hourly wage.

Images