Customer service real-time follow-up method, system, equipment and medium

Abstract

The invention discloses a customer service real-time follow-up method, system and device and a medium. The method comprises the steps that a call center API or a customer service system API interface is called based on an HTTP / HTTPS request to collect customer interaction data in real time; constructing a deep learning model based on a TensorFlow framework, and analyzing complex behavior characteristics and demands of clients; data interfaces are uniformly managed through API Gateway, so that real-time communication between the client and the cloud assistant system and the background system can be realized; and pushing a questionnaire link through the client or the cloud assistant, and collecting feedback information of the client. A layered architecture mode is adopted, the system is divided into a plurality of layers through the layered architecture mode, and the layered architecture mode is mainly divided into a data acquisition and processing layer, a data analysis and model construction layer, a real-time decision and communication layer, a system integration and management layer and a customer feedback and visualization layer. Each level is responsible for a specific function module. The layers communicate with one another through well-defined interfaces, so that the modularization, expandability and maintainability of the system are improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, system, device and medium for real-time follow-up of customer service. Background Art

[0002] In the current wave of digital transformation, customer service, as an important part of the interaction between enterprises and customers, faces the challenge of how to improve service quality and optimize customer experience. Traditional customer service methods usually rely on manual follow-up, which is inefficient and has limited personalized service capabilities. With the rapid development of artificial intelligence, big data and real-time communication technologies, enterprises have the opportunity to achieve intelligent and real-time customer service through data-driven methods.

[0003] In view of the current situation of telephone reports and customer complaints, companies are more likely to have untimely manual communication or service follow-up, which will result in sales staff being unable to receive customer needs first-hand and unable to solve customers' current problems in a timely manner, resulting in a decrease in customer satisfaction. In order to improve customer service quality, building a customer service real-time follow-up system based on data analysis is a current key research issue. However, there is currently a lack of a real-time customer service follow-up method. Summary of the invention

[0004] The present application provides a customer service real-time follow-up method, system, device and medium to solve the above-mentioned problems.

[0005] In one aspect, the present application provides a method for real-time follow-up of customer service, the method comprising the following steps:

[0006] Step S1: Call the call center API or customer service system API interface based on HTTP / HTTPS request to collect customer interaction data in real time;

[0007] Step S2: Build a deep learning model based on the TensorFlow framework to analyze customers’ complex behavioral characteristics and needs;

[0008] Step S3: The data interface is managed uniformly through API Gateway, so that the client and cloud assistant system can communicate with the backend system in real time;

[0009] Step S4: Push the questionnaire link through the client or cloud assistant to collect customer feedback information.

[0010] In one implementation of the present application, step S1 specifically includes:

[0011] Use Python's Scikit-learn library to preprocess data, use Imputer to handle missing values, remove duplicate values ​​and outliers, use MinMaxScaler or StandardScaler to standardize data, and extract customer call duration, service request frequency, and historical satisfaction score features;

[0012] The collected data is sent to the Topic of Kafka, and the downstream system consumes the data from the Topic to ensure the real-time transmission and processing of data;

[0013] The collected data is stored in a data warehouse or temporary storage for fast query and real-time decision-making; CDC technology is used to capture database changes, and Kafka is combined to achieve real-time synchronization of the database.

[0014] In one implementation of the present application, the step S2 specifically includes:

[0015] Through multi-layer neural network, features are extracted to capture nonlinear relationships. In the data preprocessing stage, key features that can reflect customer behaviors and needs are extracted through feature selection and feature combination to improve the prediction accuracy of the model.

[0016] Customers are classified based on the K-means algorithm and divided into different groups according to their needs and behavior patterns. Based on the collaborative filtering algorithm, similar customer cases are matched to provide personalized service recommendations.

[0017] In one implementation of the present application, step S3 specifically includes:

[0018] Use WebSocket or RESTful API to push real-time messages, so that sales staff can receive customer demand information in a timely manner; WebSocket technology provides two-way communication capabilities, which can reduce communication delays;

[0019] Build a real-time decision-making engine that combines customer classification and behavior prediction results to generate personalized service recommendations in real time and push them to sales staff through message queues.

[0020] In one implementation of the present application, in step S3, the introduction of API Gateway simplifies the system integration process and improves the scalability and security of the system. API Gateway adopts a microservice architecture design to split the system into multiple independent services, each of which is responsible for a specific function.

[0021] In one implementation of the present application, in step S4, customer feedback information is collected through questionnaire design, and the questionnaire design adopts a multi-dimensional scoring mechanism to ensure that customer satisfaction can be fully reflected. Tableau or Power BI is used to perform visual analysis on the questionnaire data to generate a customer satisfaction report.

[0022] In a second aspect, the present application also provides a real-time customer service follow-up system, the system comprising:

[0023] The collection module is used to call the call center API or customer service system API interface based on HTTP / HTTPS requests to collect customer interaction data in real time;

[0024] The analysis module is used to build a deep learning model based on the TensorFlow framework to analyze customers' complex behavioral characteristics and needs;

[0025] The interface module is used to uniformly manage data interfaces through API Gateway, so that the client and cloud assistant system can communicate with the backend system in real time;

[0026] The feedback module is used to push questionnaire links through the client or cloud assistant to collect customer feedback information.

[0027] In a third aspect, the present application further provides a customer service real-time follow-up device, the device comprising:

[0028] at least one processor; and,

[0029] a memory communicatively connected to the at least one processor; wherein,

[0030] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can complete the aforementioned real-time customer service follow-up method.

[0031] In a fourth aspect, the present application also provides a non-volatile computer storage medium for real-time follow-up of customer service, storing computer executable instructions, characterized in that the computer executable instructions are executed by a processor to implement the aforementioned real-time follow-up method for customer service.

[0032] This application provides a real-time follow-up method, system, device and medium for customer service, which accurately classifies customers and lays the foundation for personalized services. Through collaborative filtering algorithms, we provide customers with personalized service cases and suggestions based on the preferences of similar customers, and achieve accurate matching of services. These personalized suggestions are promptly conveyed to sales staff and customers through real-time communication and push technology, ensuring the timeliness and pertinence of the service. Finally, by collecting customer feedback and using data visualization tools for analysis, we have achieved real-time monitoring and continuous improvement of service results, thereby providing customers with a better quality and personalized service experience. The entire process, from data collection to real-time feedback, forms a closed loop to continuously optimize and improve service quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0034] Figure 1 A flowchart of a customer service real-time follow-up method provided in an embodiment of the present application;

[0035] Figure 2 A diagram showing the composition of a customer service real-time follow-up system provided in an embodiment of the present application;

[0036] Figure 3 A schematic diagram of a customer service real-time follow-up device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0037] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0038] The embodiments of the present application provide a method, system, device and medium for real-time follow-up of customer service. The technical solution proposed in the embodiments of the present application is described in detail below with reference to the accompanying drawings.

[0039] Figure 1 A flowchart of a customer service real-time follow-up method provided in an embodiment of the present application. Figure 1 As shown, the method mainly includes the following steps:

[0040] Step S1: Call the call center API or customer service system API interface based on HTTP / HTTPS request to collect customer interaction data in real time.

[0041] In an embodiment of the present application, Python's Scikit-learn library is used for data preprocessing, Imputer is used to process missing values ​​(such as filling with mean values), duplicate values ​​and outliers are removed, MinMaxScaler or StandardScaler is used to standardize the data, and features such as customer call duration, service request frequency, and historical satisfaction scores are extracted. The collected data is sent to the Topic of Kafka, and the downstream system consumes data from the Topic to ensure real-time transmission and processing of the data. The collected data is stored in a data warehouse (such as AWS Redshift, Google BigQuery) or temporary storage (Redis) for fast query and real-time decision-making. CDC technology is used to capture changes in the database, and Kafka is combined to achieve real-time synchronization of the database. The introduction of CDC technology can avoid the high latency problem of traditional polling methods and ensure the real-time and consistency of data.

[0042] Step S2: Build a deep learning model based on the TensorFlow framework to analyze customers’ complex behavioral characteristics and needs.

[0043] In the embodiment of the present application, the model extracts features through a multi-layer neural network and can effectively capture nonlinear relationships. In the data preprocessing stage, through feature selection and feature combination, key features that can reflect customer behavior and needs are extracted to improve the prediction accuracy of the model. The K-means algorithm is used to classify customers and divide customers into different groups according to their needs and behavior patterns. The advantages of the K-means algorithm are high computational efficiency and the ability to effectively process large-scale data. Based on the collaborative filtering algorithm, similar customer cases are matched to provide personalized service recommendations. The collaborative filtering algorithm analyzes customer historical behavior, identifies similar customers, and recommends similar service cases.

[0044] Step S3: The data interface is uniformly managed through API Gateway, so that the client and cloud assistant system can communicate with the backend system in real time.

[0045] In the embodiment of the present application, API Gateway provides a unified entrance to simplify the system integration process. Use WebSocket or RESTful API to implement real-time message push to ensure that sales staff can receive customer demand information in a timely manner. WebSocket technology provides two-way communication capabilities, which can significantly reduce communication delays. Build a real-time decision engine, combine customer classification and behavior prediction results, generate personalized service recommendations in real time, and push them to sales staff through message queues.

[0046] In addition, API Gateway is used as the center of system integration to uniformly manage data interfaces and ensure data consistency among clients, cloud assistants, and backend systems. The introduction of API Gateway simplifies the system integration process and improves the scalability and security of the system. Microservice architecture design is adopted to split the system into multiple independent services, each responsible for a specific function. The advantage of microservice architecture is modular design, which facilitates system expansion and maintenance. Use distributed databases (such as Cassandra or MongoDB) to store real-time data to ensure data persistence and efficient query.

[0047] Step S4: Push the questionnaire link through the client or cloud assistant to collect customer feedback information.

[0048] In the embodiment of the present application, the questionnaire design adopts a multi-dimensional scoring mechanism to ensure that customer satisfaction can be fully reflected. Tableau or Power BI is used to visualize the questionnaire data and generate a customer satisfaction report.

[0049] In the embodiments of the present application, Python and Java are mainly used as the main development languages. Python is mainly used for core functions such as data processing, model building, API interface calling, WebSocket push, and questionnaire link generation. Java language and Scala are used for the underlying implementation of CDC technology and Kafka. JavaScript is used to implement the WebSocket client to ensure real-time communication.

[0050] The logical process starts with data collection. By calling API interfaces and database monitoring technology, we can capture customer call records and service request data in real time, and realize the comprehensive collection of customer behavior data. Then, we use Kafka message queues for data transmission and synchronization to ensure the real-time and efficient transmission of data. After cleaning and preprocessing, the data is stored in the data warehouse and Redis cache, providing a neat and usable data set for subsequent analysis. Furthermore, through data preprocessing and feature extraction, we extracted key customer features, laying the foundation for model training. The deep learning model built with TensorFlow is used to predict and analyze customer behavior, achieving in-depth insights into customer behavior. Subsequently, with the help of K-means clustering algorithm, we accurately classified customers, laying the foundation for personalized services. Through collaborative filtering algorithms, we provide customers with personalized service cases and suggestions based on the preferences of similar customers, achieving accurate matching of services. These personalized suggestions are promptly conveyed to sales staff and customers through real-time communication and push technology, ensuring the timeliness and pertinence of services. Finally, by collecting customer feedback and using data visualization tools for analysis, we have achieved real-time monitoring and continuous improvement of service effects, thereby providing customers with a better and more personalized service experience. The entire process, from data collection to real-time feedback, forms a closed loop, continuously optimizing and improving service quality.

[0051] The above is a customer service real-time follow-up method provided by the embodiment of the present application. Based on the same inventive concept, the embodiment of the present application also provides a customer service real-time follow-up system. Figure 2 A diagram of a real-time customer service follow-up system provided in an embodiment of the present application, such as Figure 2 As shown, the system mainly includes:

[0052] The collection module 201 is used to call the call center API or the customer service system API interface based on HTTP / HTTPS requests to collect customer interaction data in real time;

[0053] An analysis module 202 is used to build a deep learning model based on the TensorFlow framework to analyze the complex behavioral characteristics and needs of customers;

[0054] Interface module 203, used to uniformly manage data interfaces through API Gateway, so that the client and cloud assistant system can communicate with the backend system in real time;

[0055] The feedback module 204 is used to push the questionnaire link through the client or the cloud assistant to collect customer feedback information.

[0056] The above is a customer service real-time follow-up system provided by the embodiment of the present application. Based on the same inventive concept, the embodiment of the present application also provides a customer service real-time follow-up device. Figure 3 A schematic diagram of a real-time follow-up device for customer service provided in an embodiment of the present application, such as Figure 3 As shown, the device mainly includes: at least one processor 301; and a memory 302 communicatively connected to the at least one processor; wherein the memory 302 stores instructions that can be executed by the at least one processor 301, and the instructions are executed by the at least one processor 301 so that the at least one processor 301 can complete the aforementioned real-time follow-up method for customer service.

[0057] In addition, an embodiment of the present application further provides a non-volatile computer storage medium for real-time follow-up of customer service, which stores computer executable instructions, and the computer executable instructions are executed by a processor to implement the aforementioned real-time follow-up method for customer service.

[0058] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0059] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0060] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0061] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0062] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0063] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0064] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A customer service real-time follow-up method, characterized in that: The method comprises the following steps: Step S1: Call the call center API or customer service system API interface based on HTTP / HTTPS request to collect customer interaction data in real time; Step S2: Build a deep learning model based on the TensorFlow framework to analyze customers’ complex behavioral characteristics and needs; Step S3: The data interface is managed uniformly through API Gateway, so that the client and cloud assistant system can communicate with the backend system in real time; Step S4: Push the questionnaire link through the client or cloud assistant to collect customer feedback information.

2. A customer service real-time follow-up method according to claim 1, characterized in that: The step S1 specifically includes: Use Python's Scikit-learn library to preprocess data, use Imputer to handle missing values, remove duplicate values ​​and outliers, use MinMaxScaler or StandardScaler to standardize data, and extract customer call duration, service request frequency, and historical satisfaction score features; The collected data is sent to the Topic of Kafka, and the downstream system consumes the data from the Topic to ensure the real-time transmission and processing of data; The collected data is stored in a data warehouse or temporary storage for fast query and real-time decision-making; CDC technology is used to capture database changes, and Kafka is combined to achieve real-time synchronization of the database.

3. A customer service real-time follow-up method according to claim 1, characterized in that: in, The step S2 specifically includes: Through multi-layer neural network, features are extracted to capture nonlinear relationships. In the data preprocessing stage, key features that can reflect customer behaviors and needs are extracted through feature selection and feature combination to improve the prediction accuracy of the model. Customers are classified based on the K-means algorithm and divided into different groups according to their needs and behavior patterns. Based on the collaborative filtering algorithm, similar customer cases are matched to provide personalized service recommendations.

4. A customer service real-time follow-up method according to claim 1, characterized in that: The step S3 specifically includes: Use WebSocket or RESTful API to push real-time messages, so that sales staff can receive customer demand information in a timely manner; WebSocket technology provides two-way communication capabilities, which can reduce communication delays; Build a real-time decision-making engine that combines customer classification and behavior prediction results to generate personalized service recommendations in real time and push them to sales staff through message queues.

5. A customer service real-time follow-up method according to claim 1, characterized in that: In step S3, the introduction of API Gateway simplifies the system integration process and improves the scalability and security of the system. API Gateway adopts a microservice architecture design to split the system into multiple independent services, each of which is responsible for a specific function.

6. A customer service real-time follow-up method according to claim 1, characterized in that: In step S4, customer feedback information is collected through questionnaire design. The questionnaire design adopts a multi-dimensional scoring mechanism to ensure that customer satisfaction can be fully reflected. Tableau or Power BI is used to perform visual analysis on the questionnaire data to generate a customer satisfaction report.

7. A real-time customer service follow-up system, characterized in that: The system comprises: The collection module is used to call the call center API or customer service system API interface based on HTTP / HTTPS requests to collect customer interaction data in real time; The analysis module is used to build a deep learning model based on the TensorFlow framework to analyze customers' complex behavioral characteristics and needs; The interface module is used to uniformly manage data interfaces through API Gateway, so that the client and cloud assistant system can communicate with the backend system in real time; The feedback module is used to push questionnaire links through the client or cloud assistant to collect customer feedback information.

8. A customer service real-time follow-up device, characterized in that: The device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can complete the real-time follow-up method for customer service as described in any one of claims 1-6.

9. A non-volatile computer storage medium for real-time follow-up of customer service, storing computer executable instructions, characterized in that: The computer executable instructions are executed by a processor to implement a real-time customer service follow-up method as described in any one of claims 1-6.

Images