Operator-oriented intelligent customer hierarchical management system and method

Abstract

The invention discloses an operator-oriented intelligent customer hierarchical management system and method, and relates to the technical field of customer management, and the system comprises a customer relationship analysis module which is used for deploying fog nodes to collect customer data, and carrying out the modeling of a customer relationship through a GNN model; the hierarchical processing module is used for the fog node to calculate node energy consumption and judge available nodes based on the collected customer data, and performing hierarchical processing on the customer based on the available nodes and a GNN model; and the cloud storage module is used for the fog node to select an optimal transmission path through energy consumption to upload a client layering result to a cloud after the client layering processing is completed, and the cloud stores the client layering result and displays the client layering result to an operator. According to the method, the client data processing efficiency is effectively improved, the client data is subjected to hierarchical processing through the available fog nodes, and the optimal transmission path is selected to upload the hierarchical processing result to the cloud, so that the client hierarchical accuracy and security are greatly improved, and the transmission efficiency is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of customer management, and in particular to an intelligent customer hierarchical management system and method for operators. Background Art

[0002] With the continuous development of communication technology and big data applications, operators have an increasing demand for intelligent customer management. Traditional customer management and stratification technologies usually rely on single-dimensional data analysis, such as customer consumption behavior, service usage records, etc. However, these methods fail to fully utilize the interactive relationships and complex behavior patterns of customers in social networks, resulting in low accuracy of customer stratification, especially the inability to effectively identify high-value customer groups. In addition, the traditional centralized data processing model relies on cloud computing. Although it has strong computing power, it has large data transmission delays and bandwidth pressure. Especially in large-scale data processing scenarios, the efficiency of this model has dropped significantly. In recent years, fog computing has provided a new solution for distributed data processing. By sinking computing and storage resources to edge devices (such as gateways, routers, etc.) close to the data source, it can effectively alleviate data transmission delays and improve the real-time performance of data processing. However, the existing technology still has shortcomings. During the deployment and use of fog nodes, it is impossible to select available nodes for data analysis and processing based on energy consumption, and the transmission path selection cannot be fully optimized during data transmission, resulting in bandwidth resource waste and low transmission efficiency during data transmission. Summary of the invention

[0003] In view of the problems existing in the above-mentioned existing intelligent customer hierarchical management system and method for operators, the present invention is proposed.

[0004] Therefore, the problem to be solved by the present invention is that during the deployment and use of fog nodes, available nodes cannot be selected according to energy consumption for data analysis and processing, and the transmission path selection cannot be fully optimized during data transmission, resulting in the problem of bandwidth resource waste and low transmission efficiency during data transmission.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: an intelligent customer stratification management system for operators, comprising: a customer relationship analysis module, which is used to deploy fog nodes to collect customer data and model customer relationships through a GNN model; a stratification processing module, which is used for fog nodes to calculate node energy consumption based on the collected customer data to determine available nodes, and to perform stratification processing on customers based on the available nodes and the GNN model; a cloud storage module, which is used for the fog nodes to select the optimal transmission path based on energy consumption after completing the customer stratification processing, and upload the customer stratification results to the cloud, and the cloud stores the customer stratification results and displays them to the operator.

[0006] As a preferred solution of the operator-oriented intelligent customer stratification management system described in the present invention, the deployment of fog nodes to collect customer data refers to deploying edge devices to collect customer data, taking each edge device as a fog node, combining all fog nodes to form a fog node network, and pre-processing the collected customer data through the fog nodes.

[0007] As a preferred solution of the intelligent customer hierarchical management system for operators described in the present invention, wherein: the modeling of customer relationships through the GNN model refers to the fog node treating each customer as a separate node, extracting customer basic data as the customer's initial feature vector, inputting the customer's initial feature vector into the customer node, forming node edges to connect customer nodes through customer social relationship data, and using customer interaction frequency as the node edge weight to construct the GNN model;

[0008] The customer nodes are updated through graph convolution operations using the GNN model. In each convolution layer update, the neighbor nodes of the customer nodes are normalized and the customer nodes are updated synchronously. The weight matrix of the GNN model is optimized using the back propagation algorithm each time the customer node is updated. The cross entropy loss function is set as the objective function. When the cross entropy loss function value is lower than the set threshold, the customer node update is stopped, the customer relationship GNN model is obtained, and the customer relationship GNN model is deployed to all fog nodes.

[0009] As a preferred solution of the intelligent customer hierarchical management method for operators described in the present invention, wherein: the fog node calculates the node energy consumption based on the collected customer data to determine the available node. The fog node obtains the size of the collected customer data through the edge device, sets the processing density based on the customer data size, and calculates the computing requirements of the customer data according to the customer data size and the processing density:

[0010]

[0011] Where D i is the computing requirement of the i-th customer data, O i is the customer data size, To process density;

[0012] The fog node obtains the computing frequency f of edge device j through the edge device hardware interface j , and obtain the current load L of edge device j through the operating system interface j ;

[0013] Fog nodes calculate demand D through customer data i 、Edge device calculation frequency f j and the current load L of the edge device j Calculate the processing energy consumption E of edge devices ij :

[0014]

[0015] Where K is the capacitance switching constant;

[0016] Define the energy consumption threshold E of edge device j, if E ij ≤E, the node where edge device j is located is used as an available node to directly process customer data in layers. ij >E, then the fog node network is used to find available nodes, and the edge device j transmits the customer data hierarchical processing task to the available nodes for hierarchical processing.

[0017] As a preferred solution of the intelligent customer stratification management system for operators described in the present invention, wherein: the stratification processing of customers based on available nodes and GNN model refers to collecting historical customer data for preprocessing, building an ARIMA model based on available nodes, obtaining ARIMA model parameters through maximum gradient method training, and predicting future customer data y based on the collected customer data through the ARIMA model t ;

[0018] Extract the feature vector h from the customer node in the customer relationship GNN model v and predicting future customer data t Concatenate to form a joint feature vector x v ;

[0019] Use a three-layer neural network to build a multilayer perceptron, set the multilayer perceptron input as the joint feature vector, and the output as the customer stratification result, and use the cross entropy loss function and gradient descent to train the multilayer perceptron parameters;

[0020] The joint eigenvector x v Input into the multi-layer perceptron to obtain the customer stratification results.

[0021] As a preferred solution of the intelligent customer stratification management system for operators described in the present invention, wherein: after the fog node completes the customer stratification processing, it selects the optimal transmission path by energy consumption to upload the customer stratification result to the cloud, which means that the fog node obtains all data transmission path information between the edge device and the cloud, and randomly selects any transmission path as the initial transmission path group, and calculates the upload and download time of the initial transmission path group based on the transmission path information:

[0022]

[0023] Among them, zi Result data size for customer stratification, T uij and T dij is the upload time and download time of edge device j, Buijk and B dijk is the upload bandwidth and download bandwidth of the kth transmission path, P j Transmit power to edge devices, G jk is the channel gain of the kth transmission path, N jk is the noise of the kth transmission path, M is the number of transmission paths in the initial transmission path group;

[0024] Calculate the transmission energy consumption E of the initial transmission path group based on the upload and download time t :

[0025] E t =P j ×(T uij +T dij )+E ij ;

[0026] All data transmission paths between the edge device and the cloud are randomly combined, and the transmission energy consumption of each combined transmission path group is calculated. All combinations are traversed and the transmission path group with the lowest transmission energy consumption is selected as the final transmission path;

[0027] The edge device transmits the customer stratification results to the cloud through the final transmission path, and monitors the transmission energy consumption in real time during the transmission process. If the real-time transmission energy consumption is not higher than the calculated transmission energy consumption, the current transmission path is used to transmit all customer stratification results. If the real-time transmission energy consumption is higher than the calculated transmission energy consumption, the transmission path change operation is triggered and the remaining data volume of the customer stratification results is recorded. si ;

[0028] The edge node obtains the transmission path change time T from the qth transmission path group to the lth transmission path group through the TCP protocol and the network interface. wql , including the disconnection time of the original transmission path, the establishment time of the new transmission path, and the channel verification and handshake time, and the energy consumption E of the transmission path replacement is calculated based on the transmission power of the edge node wql ;

[0029] Based on the transmission path change time T wql The upload and download bandwidths of the lth transmission path group at current time t are calculated using a sliding average window at time t+T wql The upload and download bandwidth of the lth transmission path group is predicted based on the LSTM model at time t+T wql The channel gain of the lth transmission path group;

[0030] The amount of remaining data O according to customer stratification results si Calculate the remaining transmission energy consumption E of the lth transmission path group l and the remaining transmission energy consumption E of the qth transmission path groupq , and compare:

[0031] If E l +E wql ≤E q , the edge node changes the transmission path from the qth transmission path group to the lth transmission path group to transmit the remaining data of the customer layer. If E l +E wql >E q , the edge node still uses the transmission path in the qth transmission path group to transmit the remaining data of the customer layer.

[0032] As a preferred solution of the intelligent customer stratification management system for operators described in the present invention, wherein: the cloud stores the customer stratification processing results and displays them to the operator, which means that the cloud performs integrity verification after receiving the customer stratification results transmitted by the edge node, and stores the verified customer stratification results in the database, and simultaneously forms a visual chart of the customer stratification results to display to the operator.

[0033] Another object of the present invention is to provide an intelligent customer hierarchical management method for operators, which includes deploying edge devices and fog nodes to collect customer data and perform pre-processing;

[0034] Build a customer pipeline GNN model based on customer data and deploy the GNN model to fog nodes;

[0035] The energy consumption of computing fog nodes is judged and available nodes are processed by customer stratification;

[0036] Select the optimal transmission path and monitor the transmission energy consumption, and transmit the customer's layered processing results to the cloud through the transmission path for storage and display.

[0037] A computer device comprises: a memory and a processor; the memory stores a computer program, and the processor implements the steps of the above-mentioned intelligent customer stratification management system for operators when executing the computer program.

[0038] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned intelligent customer tiered management system for operators.

[0039] The beneficial effects of the present invention are as follows: the present invention collects customer data through fog nodes to establish a customer relationship GNN model, and determines node availability based on the calculation of node energy consumption based on customer data, thereby effectively improving the efficiency of customer data processing, performing layered processing on customer data through available fog nodes, and selecting the optimal transmission path to upload the layered processing results to the cloud, thereby greatly improving the accuracy and security of customer layering and ensuring transmission efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0041] Figure 1 The figure is a flowchart of an intelligent customer tiered management system for operators.

[0042] Figure 2 Schematic diagram of the structure of client stratification processing for calculating energy consumption and determining node availability.

[0043] Figure 3 A structural diagram of an intelligent customer tiered management method for operators. DETAILED DESCRIPTION

[0044] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings.

[0045] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0046] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0047] Example 1

[0048] Reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and which provides an intelligent customer stratification management system for operators. The intelligent customer stratification management system for operators includes:

[0049] S1, customer relationship analysis module, used to deploy fog nodes to collect customer data and model customer relationships through the GNN model;

[0050] Specifically, deploying fog nodes to collect customer data refers to deploying edge devices to collect customer data, taking each edge device as a fog node, combining all fog nodes to form a fog node network, and preprocessing the collected customer data through the fog nodes.

[0051] By deploying edge devices as fog nodes, the traditional way of collecting customer data is effectively expanded. By deploying multiple fog nodes close to the data source, real-time monitoring and collection of data such as customer behavior and consumption habits can be achieved. Compared with the traditional centralized data collection method that relies on the cloud, the deployment of fog nodes greatly reduces data transmission delays and improves the efficiency and real-time performance of data collection. This is of great help to operators in quickly responding to customer needs and providing personalized services. At the same time, the deployment of edge devices has good scalability. Operators can adjust or add fog nodes at any time according to business needs to adapt to the dynamic changes in data volume and processing power. Using each edge device as an independent fog node can not only utilize the existing computing and storage resources of the device, but also reduce the load on the central server through distributed processing. The independent operation of fog nodes enables each device to perform preliminary analysis and processing of data locally. , thereby reducing the dependence on the central cloud. Each fog node can intelligently process customer data according to its own resources and transmit the pre-processed data to the upper node or cloud for further analysis. This design not only improves the flexibility of the system, but also reduces operating costs, and helps to cope with complex network environments and data transmission requirements. The formation of a fog node network is a key step in achieving distributed processing and data synchronization. By combining various scattered fog nodes into a network, multiple nodes can work together to form an overall effect. The fog node network can automatically balance the load of each node to ensure that each node can evenly distribute data processing tasks during high traffic and avoid overloading of a single node. At the same time, the construction of the network structure also enhances the fault tolerance and stability of the system. When a fog node fails, other nodes can immediately take over the corresponding work to ensure the continuity and stability of the entire system.

[0052] Furthermore, modeling customer relationships through the GNN model means that the fog node treats each customer as a separate node, extracts the customer's basic data (age, gender, consumption history, hobbies, etc.) as the customer's initial feature vector, inputs the customer's initial feature vector into the customer node, forms node edges to connect customer nodes through customer social relationship data, and uses customer interaction frequency as the node edge weight to build the GNN model;

[0053] The customer nodes are updated through graph convolution operations using the GNN model. In each convolution layer update, the neighbor nodes of the customer nodes are normalized and the customer nodes are updated synchronously. The weight matrix of the GNN model is optimized using the back propagation algorithm each time the customer node is updated. The cross entropy loss function is set as the objective function. When the cross entropy loss function value is lower than the set threshold, the customer node update is stopped, the customer relationship GNN model is obtained, and the customer relationship GNN model is deployed to all fog nodes.

[0054] Modeling customer relationships through the GNN model is one of the core steps of the present invention. The fog node regards each customer as an independent node and forms an initial feature vector through the customer's basic data (such as age, gender, consumption history, hobbies, etc.). This method can fully reflect the personalized characteristics of each customer and provide a solid foundation for subsequent customer stratification. Compared with the traditional static data model, the present invention uses GNN to dynamically update the characteristics of customers when processing customer social relationships, which improves the flexibility and accuracy of the model. In addition, the use of GNN modeling can also automatically capture the complex social relationship patterns between customers, especially the implicit strong social interaction or the identification of potential high-value customers. In establishing customer When constructing a customer relationship graph, the interaction frequency between customers is set as the weight of the node edge, which greatly enhances the model's ability to represent customer social relationships. The interaction frequency not only reflects the interaction intensity between customers, but also directly affects the scope and effect of information dissemination in the graph convolution operation through weights. This method ensures that information dissemination is smoother between customers with frequent social interactions. The model can better capture the behavior patterns of these high-frequency interactive customers, thereby improving the recognition accuracy of high-value customers. The graph convolution operation is the core step in updating the features of customer nodes. In each layer of convolution operation, the features of the customer node are updated by normalizing the features of its neighbor nodes, thereby gradually integrating more levels of customers. Social relationship information, this mechanism ensures that each customer node not only relies on its own characteristics, but also can obtain information about other customer nodes through the social relationship network. The more layers of convolution operation, the more comprehensive the information obtained by the node. Compared with simple weighted average, the graph convolution operation in the present invention can perform complex multi-layer feature fusion while maintaining the social relationship structure, making customer relationship modeling more accurate. Each time a customer node is updated, the present invention uses a back propagation algorithm to optimize the weight matrix of the GNN model. The back propagation algorithm gradually adjusts the parameters of the model by minimizing the value of the cross entropy loss function, ensuring that the model can gradually improve the prediction accuracy when processing customer relationships. This weight The optimization strategy enables the GNN model to continuously improve its performance according to the actual data of customer relationships and achieve the best performance at the end of training. When the value of the cross entropy loss function is lower than the set threshold, the model will stop updating the customer node to ensure the convergence and stability of the model. By deploying the trained customer relationship GNN model to all fog nodes, the present invention achieves the goal of distributed customer relationship modeling and processing. Each fog node can independently run the customer relationship model and process customer data locally, reducing dependence on the central server. This distributed deployment not only improves the scalability of the system, but also significantly reduces the delay in data transmission and enhances the responsiveness to real-time customer stratification and precision marketing.

[0055] S2, hierarchical processing module, used for fog nodes to calculate node energy consumption based on collected customer data to determine available nodes, and hierarchical processing of customers based on available nodes and GNN model;

[0056] Specifically, the fog node calculates the node energy consumption based on the collected customer data. The available node refers to the fog node obtaining the size of the collected customer data through the edge device, and setting the processing density based on the size of the customer data. The computing requirements of the customer data are calculated based on the customer data size and processing density:

[0057] D i =O i ×O Pi ;

[0058] Where D i is the computing requirement of the i-th customer data, O i is the customer data size, O Pi To process density;

[0059] The fog node obtains the computing frequency f of edge device j through the edge device hardware interface j , and obtain the current load L of edge device j through the operating system interface j ;

[0060] Fog nodes calculate demand D through customer data i 、Edge device calculation frequency f j and the current load L of the edge device j Calculate the processing energy consumption E of edge devices ij :

[0061]

[0062] Where K is the capacitance switching constant;

[0063] Define the energy consumption threshold E of edge device j, if E ij ≤E, the node where edge device j is located is used as an available node to directly process customer data in layers. ij >E, then the fog node network is used to find available nodes, and the edge device j transmits the customer data hierarchical processing task to the available nodes for hierarchical processing.

[0064] The fog node obtains the size of customer data through the edge device and sets the processing density according to different types of data. The setting of processing density enables the system to flexibly respond to the computing requirements of different customer data. For example, the computing requirements for processing video data and text data are obviously different. The processing density of video data will be significantly higher than that of text data. Therefore, by combining data size and processing density, the system can dynamically calculate the computing requirements of each customer data to ensure the reasonable allocation of computing resources. This not only improves the efficiency of data processing, but also provides an accurate basis for subsequent energy consumption management and task allocation. The computing frequency and current load of the edge device directly affect the energy consumption. The higher the frequency and the heavier the load, the higher the energy consumption of the device. Through this energy consumption calculation, the system can monitor the working status of the device in real time to ensure that the actual use of the device is considered when calculating energy consumption, thereby optimizing resource allocation. This is especially important for systems that need to process customer data on a large scale, and can effectively reduce unnecessary energy waste. The introduction of energy consumption thresholds provides an efficient task management mechanism for the system. When the fog node calculates the processing energy consumption of the edge device After that, the system will compare it with the energy consumption threshold of the device. If the energy consumption of the device is lower than the preset energy consumption threshold, the node is considered available, and the system can complete the hierarchical processing of customer data directly on the device. However, if the energy consumption of the device exceeds the threshold, the system will find other available nodes through the fog node network and transfer the processing task to a device with higher energy efficiency. When the energy consumption of an edge device exceeds the set threshold, the system will transfer the task to other available nodes for processing through the fog node network. This design ensures that when faced with a large amount of customer data, the system can automatically switch tasks to avoid excessive load on a single device. The distributed characteristics of the fog node network make data transmission and processing more flexible and can quickly adapt to changes in task loads. It not only improves the accuracy and stability of data processing, but also enhances the fault tolerance of the system. Even if a node fails, the system can quickly transfer tasks to other nodes to ensure the continuity of data processing. Through optimized energy consumption management and task allocation strategies, the present invention can provide efficient and stable customer data processing services in a complex network environment.

[0065] Furthermore, stratifying customers based on available nodes and GNN models refers to collecting historical customer data for preprocessing, building an ARIMA model based on available nodes, obtaining ARIMA model parameters through maximum gradient training, and predicting future customer data y based on the collected customer data through the ARIMA model. t ;

[0066] Extract the feature vector h from the customer node in the customer relationship GNN model v and predicting future customer data t Concatenate to form a joint feature vector x v ;

[0067] Use a three-layer neural network to build a multilayer perceptron, set the multilayer perceptron input as the joint feature vector, and the output as the customer stratification result, and use the cross entropy loss function and gradient descent to train the multilayer perceptron parameters;

[0068] The joint eigenvector x v Input into the multi-layer perceptron to obtain the customer stratification results.

[0069] By building an ARIMA model on available nodes, the system can predict the future behavior trends of customers based on their past behavior data. This process effectively improves the accuracy and real-time performance of customer data processing. Compared with traditional static data analysis methods, the ARIMA model can capture the dynamic changes of customer behavior, especially when customer behavior fluctuates periodically or emergencies occur. The ARIMA model can generate more accurate customer behavior prediction results by analyzing the trends of historical data. This technology is particularly critical in customer stratification, because accurate future behavior predictions can help operators adjust strategies in a timely manner and provide personalized services to different customer groups. The feature vector of each customer node reflects the customer's influence in the social network and its interactive relationship with other customers. Extracting these feature vectors and splicing them with the future data predicted by the ARIMA model can generate a more comprehensive customer description. This feature vector not only contains the customer's historical behavior, but also combines the hidden features in its social relationships, which can more comprehensively reflect the customer's potential value. In this way, the system can achieve more accurate customer stratification, which helps to identify potential high-value customers or customer groups with special needs. By combining the customer's historical behavior characteristics with future prediction data, the system can generate a more comprehensive customer description. The MLP can perform in-depth analysis of customer behavior patterns by using the data as input. The three-layer MLP structure (input layer, hidden layer and output layer) can capture the complex relationship in the feature vector and generate accurate stratification results through multi-layer nonlinear calculations. Compared with the traditional simple linear classification method, the MLP can more accurately identify the subtle differences between customers and provide more refined customer stratification results. By taking the cross entropy as the objective function, the multi-layer perceptron can continuously adjust its internal parameters during the training process to gradually improve the prediction accuracy of the model. At the same time, the gradient descent algorithm is used to optimize the weights and bias terms of the MLP so that the model can quickly converge to the optimal solution. The gradient descent enables the MLP to effectively capture the relationship between customer characteristics and stratification results by gradually reducing the error of the model. By splicing the feature vectors in the customer relationship GNN model with the future customer data predicted by the ARIMA model, the present invention generates a joint feature vector containing historical and future behaviors. The joint feature vector not only integrates the customer's past behavior and future trends, but also combines the customer's status and relationship in the social network. This multi-dimensional feature representation can more accurately capture the comprehensive value of the customer and help operators make more informed decisions when stratifying customers.

[0070] S3, cloud storage module, is used to select the optimal transmission path based on energy consumption after the fog node completes the customer stratification process and upload the customer stratification results to the cloud. The cloud stores the customer stratification results and displays them to the operator;

[0071] Specifically, after the fog node completes the customer stratification processing, it selects the optimal transmission path by energy consumption and uploads the customer stratification result to the cloud. The fog node obtains all data transmission path information between the edge device and the cloud, and randomly selects any transmission path as the initial transmission path group. The upload and download time of the initial transmission path group is calculated based on the transmission path information:

[0072]

[0073] Among them, zi Result data size for customer stratification, T uij and T dij is the upload time and download time of edge device j, B uijk and B dijk is the upload bandwidth and download bandwidth of the kth transmission path, P j Transmit power to edge devices, G jk is the channel gain of the kth transmission path, N jk is the noise of the kth transmission path, M is the number of transmission paths in the initial transmission path group;

[0074] Calculate the transmission energy consumption E of the initial transmission path group based on the upload and download time t :

[0075] E t =P j ×(T uij +T dij )+E ij ;

[0076] All data transmission paths between the edge device and the cloud are randomly combined, and the transmission energy consumption of each combined transmission path group is calculated. All combinations are traversed and the transmission path group with the lowest transmission energy consumption is selected as the final transmission path;

[0077] The edge device transmits the customer stratification results to the cloud through the final transmission path, and monitors the transmission energy consumption in real time during the transmission process. If the real-time transmission energy consumption is not higher than the calculated transmission energy consumption, the current transmission path is used to transmit all customer stratification results. If the real-time transmission energy consumption is higher than the calculated transmission energy consumption, the transmission path change operation is triggered and the remaining data volume of the customer stratification results is recorded. si ;

[0078] The edge node obtains the transmission path change time T from the qth transmission path group to the lth transmission path group through the TCP protocol and the network interface. wql , including the disconnection time of the original transmission path, the establishment time of the new transmission path, and the channel verification and handshake time, and the energy consumption E of the transmission path replacement is calculated based on the transmission power of the edge node wql ;

[0079] Based on the transmission path change time T wql The upload and download bandwidths of the lth transmission path group at current time t are calculated using a sliding average window at time t+T wql The upload and download bandwidth of the lth transmission path group is predicted based on the LSTM model at time t+T wql The channel gain of the lth transmission path group;

[0080] The amount of remaining data O according to customer stratification results si Calculate the remaining transmission energy consumption E of the lth transmission path group l and the remaining transmission energy consumption E of the qth transmission path group q , and compare:

[0081] If E l +E wql ≤E q , the edge node changes the transmission path from the qth transmission path group to the lth transmission path group to transmit the remaining data of the customer layer. If E l +E wql >E q , the edge node still uses the transmission path in the qth transmission path group to transmit the remaining data of the customer layer.

[0082] The fog node obtains all the transmission path information between the edge device and the cloud, and randomly selects several transmission paths to form an initial transmission path group. This random selection method provides a variety of alternatives for subsequent path optimization, avoiding the problem of selecting the local optimal path. By calculating the upload and download time of these initial paths, the system can quickly screen out a more efficient transmission path group and improve the transmission efficiency. Through this step, the system can reduce the delay of data transmission and improve the utilization of transmission bandwidth to a certain extent. Especially when the customer hierarchical data is large, the optimization of the transmission path can significantly reduce the transmission time and reduce the system energy consumption. Based on the upload and download time of the initial transmission path group, the system further calculates the upload and download time of each transmission path. The transmission energy consumption of the path group is determined by traversing and randomly combining all transmission paths, and finally selecting the transmission path group with the lowest energy consumption as the final transmission path. This optimization process ensures that the transmission of customer stratification results is not only at a high speed, but also saves the system's energy consumption to the maximum extent. This energy consumption optimization mechanism can effectively extend the working time of edge devices, especially on battery-powered edge devices. Reducing transmission energy consumption is crucial to the stability and durability of the system. By selecting the optimal transmission path group, the system can reduce energy consumption while transmitting efficiently, providing a reliable foundation for uploading large-scale customer stratification data. During the transmission of customer stratification data, the fog node will monitor the energy consumption of the current transmission path in real time. If the actual energy consumption If the calculated transmission energy consumption is exceeded, the system will trigger a path replacement operation. This real-time monitoring mechanism ensures dynamic optimization of the transmission path and avoids low transmission efficiency or excessive energy consumption due to decreased path quality. The introduction of real-time monitoring and path replacement mechanisms enables the system to flexibly respond to changes in the network environment. By dynamically adjusting the transmission path, the system can switch to a better transmission path in time when the network is congested or the path performance is degraded, thereby ensuring the continuity and efficiency of data transmission. Especially in a complex network environment, this path optimization mechanism can greatly improve the reliability of the system. When the system decides to replace the transmission path, it needs to consider the energy consumption during the replacement process, including disconnecting the original path, establishing a new path, and channel verification and Energy consumption during the handshake process. By calculating the energy consumption of changing the transmission path based on the transmission power of the edge node, the system can evaluate the cost of the path change operation and ensure that the path change is energy-optimal overall. During the path change process, the system uses a sliding average window to calculate the new transmission path bandwidth and predicts the channel gain through the LSTM model. This combination of short-term smoothing and long-term trend prediction enables the system to more accurately grasp the state changes of the transmission path. Before changing the path, the system will calculate the remaining transmission energy consumption of the current path group and the target path group based on the remaining data volume of the customer stratification result. If the remaining energy consumption of the new path group is lower than that of the current path group, the system will perform path change, otherwise it will continue to use the current path group.This decision-making mechanism effectively prevents unnecessary path switching and ensures the maximum transmission efficiency. Through this energy consumption comparison and decision-making mechanism, the system can reduce unnecessary resource consumption while ensuring transmission efficiency, and improve the stability and durability of data transmission. Especially in the transmission process of large-scale customer data, energy consumption optimization has a significant effect on improving the overall performance of the system.

[0083] Furthermore, the cloud stores the customer stratification processing results and displays them to the operator, which means that after the cloud receives the customer stratification results transmitted by the edge node, it performs integrity verification, stores the verified customer stratification results in the database, and simultaneously forms a visual chart of the customer stratification results for display to the operator.

[0084] After the customer stratification results are transmitted from the edge node to the cloud, the cloud first verifies the integrity of the data. Through hash values, checksums or other commonly used integrity verification technologies, the system can quickly detect whether the data has been lost, tampered with or erroneous during transmission. This verification process is a key step to ensure data accuracy and security, especially when processing large-scale customer stratification data. Any data loss or error may affect the accuracy of subsequent analysis and decision-making. The customer stratification results that have passed integrity verification will be stored in the cloud database. The database is not only used for storage, but also can provide efficient query and analysis functions to support subsequent data mining and analysis. This storage process ensures the security and persistence of customer stratification data. Operators can call historical stratification data for analysis and comparison at any time as needed. In comparison, while storing the customer stratification results, the cloud will simultaneously display the results to the operator in the form of charts. This synchronous display mechanism enables operators to obtain customer stratification information in real time, which is convenient for quickly understanding the changes in the customer stratification structure. Through visualization technology, complex data can be converted into intuitive graphics and charts to help operators better understand the meaning behind the data. The display of customer stratification results is not only used for real-time monitoring, but also can serve as an important basis for subsequent business decisions. Through the customer stratification results stored in the cloud database, operators can conduct long-term trend analysis, customer behavior prediction and market strategy adjustment. Combined with data analysis tools, operators can further explore the commercial value behind the data, formulate accurate marketing strategies for different customer groups, and improve customer satisfaction and loyalty.

[0085] Example 2

[0086] Reference Figure 3 , which is the second embodiment of the present invention, and which is different from the previous embodiment, provides an intelligent customer hierarchical management method for operators, which includes:

[0087] Deploy edge devices and fog nodes to collect customer data and pre-process it;

[0088] Build a customer pipeline GNN model based on customer data and deploy the GNN model to fog nodes;

[0089] The energy consumption of computing fog nodes is judged and available nodes are processed by customer stratification;

[0090] Select the optimal transmission path and monitor the transmission energy consumption, and transmit the customer's layered processing results to the cloud through the transmission path for storage and display.

[0091] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0092] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0093] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0094] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0095] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An intelligent customer tiered management system for operators, characterized by: include, The customer relationship analysis module is used to deploy fog nodes to collect customer data and model customer relationships through the GNN model; The hierarchical processing module is used by fog nodes to calculate node energy consumption based on the collected customer data and determine available nodes, and to perform hierarchical processing on customers based on available nodes and the GNN model; The cloud storage module is used to upload the customer stratification results to the cloud by selecting the optimal transmission path based on energy consumption after the fog node completes the customer stratification processing. The cloud stores the customer stratification results and displays them to the operator.

2. The intelligent customer hierarchical management system for operators according to claim 1, characterized in that: The deployment of fog nodes to collect customer data refers to deploying edge devices to collect customer data, taking each edge device as a fog node, combining all fog nodes to form a fog node network, and preprocessing the collected customer data through the fog nodes.

3. The intelligent customer hierarchical management system for operators as claimed in claim 2, characterized in that: The customer relationship modeling by the GNN model refers to the fog node treating each customer as a separate node, extracting the customer's basic data as the customer's initial feature vector, inputting the customer's initial feature vector into the customer node, forming node edges to connect the customer nodes through the customer's social relationship data, and using the customer interaction frequency as the node edge weight to construct the GNN model; The customer nodes are updated through graph convolution operations using the GNN model. In each convolution layer update, the neighbor nodes of the customer nodes are normalized and the customer nodes are updated synchronously. The weight matrix of the GNN model is optimized using the back propagation algorithm each time the customer node is updated. The cross entropy loss function is set as the objective function. When the cross entropy loss function value is lower than the set threshold, the customer node update is stopped, the customer relationship GNN model is obtained, and the customer relationship GNN model is deployed to all fog nodes.

4. The intelligent customer hierarchical management system for operators as claimed in claim 3, characterized in that: The fog node calculates the node energy consumption based on the collected customer data to determine the available node. The fog node obtains the size of the collected customer data through the edge device, sets the processing density based on the customer data size, and calculates the computing requirements of the customer data based on the customer data size and the processing density: Where D i is the computing requirement of the i-th customer data, O i is the customer data size, To process density; The fog node obtains the computing frequency f of edge device j through the edge device hardware interface j , and obtain the current load L of edge device j through the operating system interface j ; Fog nodes calculate demand D through customer data i 、Edge device calculation frequency f j and the current load L of the edge device j Calculate the processing energy consumption E of edge devices ij : Where K is the capacitance switching constant; Define the energy consumption threshold E of edge device j, if E ij ≤E, the node where edge device j is located is used as an available node to directly process customer data in layers. ij >E, then the fog node network is used to find available nodes, and the edge device j transmits the customer data hierarchical processing task to the available nodes for hierarchical processing.

5. The intelligent customer hierarchical management system for operators as claimed in claim 4, characterized in that: The stratified processing of customers based on available nodes and GNN model refers to collecting historical customer data for preprocessing, building an ARIMA model based on available nodes, obtaining ARIMA model parameters through maximum gradient method training, and predicting future customer data y based on the collected customer data through the ARIMA model. t ; Extract the feature vector h from the customer node in the customer relationship GNN model v and predicting future customer data t Concatenate to form a joint feature vector x v ; Use a three-layer neural network to build a multilayer perceptron, set the multilayer perceptron input as the joint feature vector, and the output as the customer stratification result, and use the cross entropy loss function and gradient descent to train the multilayer perceptron parameters; The joint eigenvector x v Input into the multi-layer perceptron to obtain the customer stratification results.

6. The intelligent customer hierarchical management system for operators as claimed in claim 5, characterized in that: After the fog node completes the customer stratification processing, it selects the optimal transmission path by energy consumption and uploads the customer stratification result to the cloud. The fog node obtains all data transmission path information between the edge device and the cloud, and randomly selects any transmission path as the initial transmission path group, and calculates the upload and download time of the initial transmission path group based on the transmission path information: Among them, zi Result data size for customer stratification, T uij and T dij is the upload time and download time of edge device j, B uijk and B dijk is the upload bandwidth and download bandwidth of the kth transmission path, P j Transmit power to edge devices, G ik is the channel gain of the kth transmission path, N jk is the noise of the kth transmission path, M is the number of transmission paths in the initial transmission path group; Calculate the transmission energy consumption E of the initial transmission path group based on the upload and download time t : E t =P j ×(T uij +T dij )+E ij ; All data transmission paths between the edge device and the cloud are randomly combined, and the transmission energy consumption of each combined transmission path group is calculated. All combinations are traversed and the transmission path group with the lowest transmission energy consumption is selected as the final transmission path; The edge device transmits the customer stratification results to the cloud through the final transmission path, and monitors the transmission energy consumption in real time during the transmission process. If the real-time transmission energy consumption is not higher than the calculated transmission energy consumption, the current transmission path is used to transmit all customer stratification results. If the real-time transmission energy consumption is higher than the calculated transmission energy consumption, the transmission path change operation is triggered and the remaining data volume of the customer stratification results is recorded. si ; The edge node obtains the transmission path change time T from the qth transmission path group to the 1st transmission path group through the TCP protocol and the network interface. wgl , including the disconnection time of the original transmission path, the establishment time of the new transmission path, and the channel verification and handshake time, and the energy consumption E of the transmission path replacement is calculated based on the transmission power of the edge node wql ; Based on the transmission path change time T wql The upload and download bandwidth of the first transmission path group at current time t is calculated using a sliding average window at time t+T wql The upload and download bandwidth of the first transmission path group is predicted based on the LSTM model at time t+T wql The channel gain of the first transmission path group; The amount of remaining data O according to customer stratification results si Calculate the remaining transmission energy consumption E1 of the first transmission path group and the remaining transmission energy consumption E of the qth transmission path group q , and compare: If E1+E wql ≤E q , the edge node changes the transmission path from the qth transmission path group to the 1st transmission path group to transmit the remaining data of the customer layer. If E1+E wql >E q , the edge node still uses the transmission path in the qth transmission path group to transmit the remaining data of the customer layer.

7. The intelligent customer hierarchical management system for operators as claimed in claim 6, characterized in that: The cloud stores the customer stratification processing results and displays them to the operator, which means that the cloud performs integrity verification after receiving the customer stratification results transmitted by the edge node, stores the verified customer stratification results in the database, and simultaneously forms a visual chart of the customer stratification results to display to the operator.

8. An intelligent customer hierarchical management method for operators of the intelligent customer hierarchical management system for operators according to any one of claims 1 to 7, characterized in that: include, Deploy edge devices and fog nodes to collect customer data and pre-process it; Build a customer pipeline GNN model based on customer data and deploy the GNN model to fog nodes; The energy consumption of computing fog nodes is judged and available nodes are processed by customer stratification; Select the optimal transmission path and monitor the transmission energy consumption, and transmit the customer's layered processing results to the cloud through the transmission path for storage and display.

9. A computer device comprising: Memory and processor; The memory stores a computer program, characterized in that: when the processor executes the computer program, the steps of the intelligent customer stratification management system for operators described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the operator-oriented intelligent customer tiered management system according to any one of claims 1 to 7 are implemented.

Images