Intelligent cpe device management system based on visual recognition

Abstract

The application is suitable for the technical field of communication network equipment management, and particularly relates to an intelligent CPE equipment management system based on visual identification, which comprises a preprocessing module for collecting equipment image information and user image information; an equipment identification and authentication module for identifying the equipment image information and the user image information by using a small sample target identification algorithm, identifying the user and the equipment; and an intelligent equipment matching module for adjusting the network configuration strategy of each equipment according to the physical position of the equipment and the activity scene of the user, and providing higher bandwidth for the equipment with higher priority. The application uses a camera to capture the images of the equipment and the user, identifies the equipment type and the user identity through a visual model, automatically authenticates the known equipment, automatically adjusts the network configuration and the priority of the equipment by identifying the physical position of the equipment and the user activity, prevents unauthorized equipment from accessing the network, prompts the user to perform equipment authentication, and ensures network security.

Description

Technical Field

[0001] The present invention belongs to the technical field of communication network equipment management, and in particular relates to an intelligent CPE equipment management system based on visual recognition. Background Art

[0002] As the complexity of communication networks, home networks, and enterprise networks increases, the need to manage access devices is also growing. Existing CPE devices typically manage access devices through physical or logical methods, relying primarily on manual configuration or static authentication based on MAC addresses. Physical management determines which devices can access the network based on physical ports. This method typically requires manual configuration of the CPE device, using the CLI (Command Line Interface) or web management interface to specify that certain ports or interfaces can only connect to specific types of devices. Logical management, on the other hand, typically involves configuring VLANs, subnets, or other network policies to manage access devices. This process can be implemented through the configuration of network devices such as routers or switches. Both methods rely heavily on manual configuration by the administrator. Static authentication based on MAC addresses is also commonly used. This is a common device authentication method that uses MAC address filtering. In this method, the CPE device maintains a table of the MAC addresses of devices allowed to access the network. If a device's MAC address is not in the allowed list, it is denied network access. This method is called static authentication because the MAC address is manually configured or statically assigned and does not change dynamically after the device is connected to the network.

[0003] CPE devices typically manage access devices through physical or logical means. Current drawbacks include complex manual configuration, MAC address forgery, and a lack of dynamism. Manual configuration requires administrator intervention, which is labor-intensive and error-prone. MAC addresses can be forged, making static authentication based on MAC addresses a less secure method. Static authentication lacks dynamic adaptability, preventing dynamic adjustments to network access policies based on device characteristics and user behavior, and preventing effective network configuration optimization based on device usage. Summary of the Invention

[0004] The purpose of the present invention is to provide an intelligent CPE device management system based on visual recognition, aiming to solve the problems that static authentication methods lack dynamic adaptability, cannot dynamically adjust network access policies according to device characteristics and user behavior, and cannot perform better network configuration optimization based on device usage.

[0005] The present invention is implemented as follows: an intelligent CPE device management system based on visual recognition, the system comprising:

[0006] A pre-processing module is used to collect device image information and user image information;

[0007] A device identification and authentication module is configured to identify the device image information and the user image information by using a small sample target identification algorithm, and identify the user and the device.

[0008] An intelligent device matching module is configured to adjust the network configuration strategy of each device according to the physical location of the device and the activity scene of the user, and provide higher bandwidth for the device with higher priority.

[0009] Preferably, the pre-processing module stores user information and device information, one user can be bound to multiple devices, and one device can be bound to multiple users.

[0010] Preferably, the small sample target identification algorithm uses a lightweight convolutional neural network: the first layer is an input layer for inputting images; the second layer is a convolutional layer for extracting image features; the third layer is a pooling layer; the fourth layer is a convolutional layer using twice the convolutional kernel of the second layer, and the activation function uses a Hard Swish function; the fifth layer is a pooling layer using a max-pooling method for sampling; the sixth layer is a dropout layer for setting some neural node parameters to 0 according to a set probability; the seventh layer is a flattening layer for folding the input spatial dimension into a channel dimension to connect to a full connection layer; the eighth layer is a full connection layer, and the activation function uses a Hard Swish function; and the ninth layer is an output layer, and the activation function uses a SoftMax function.

[0011] Preferably, in the small sample target identification algorithm, the second layer is a convolutional layer, and the activation function uses a Hard Swish function.

[0012] Preferably, the third layer is a pooling layer using a max-pooling method for sampling, for reducing the dimension of data and compressing the characteristics of the image.

[0013] Preferably, the sixth layer is a dropout layer, and the set probability is 0.02, for reducing the probability of overfitting in the training process.

[0014] Preferably, the activity scene of the user includes at least home, company, shopping mall, bedroom, living room, office, conference room, and store.

[0015] Preferably, when the intelligent device matching module detects that the user is performing a specific activity in a specific activity scene, it provides higher network priority to the corresponding device used by the user, and reduces the occupation of network bandwidth by other devices with low network priority.

[0016] Preferably, when a user uses a device, traffic analysis, network protocol and visual recognition are used to determine the usage status of the device. During the traffic analysis, the process the device is running is determined based on the data packet size, transmission speed and transmission time.

[0017] Preferably, in the process of determining the device usage status based on the network protocol, when the WebRTC or Skype protocol used for video calls is detected, it is determined that the user is using the device for communication.

[0018] The present invention provides an intelligent CPE device management system based on visual recognition, which uses visual recognition technology to implement intelligent device management and user identification in CPE devices, uses a camera to capture device and user images, identifies device type and user identity through visual models, automatically authenticates known devices, and automatically adjusts the network configuration and priority of devices by identifying the physical location of the device and user activities; prevents unauthorized devices from accessing the network, prompts users to perform device authentication, and ensures network security. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A schematic diagram of the process of an intelligent CPE device management system based on visual recognition provided by an embodiment of the present invention;

[0020] Figure 2 This is an architecture diagram of a small sample target recognition algorithm provided by an embodiment of the present invention;

[0021] Figure 3 A schematic diagram of the overall process framework of the intelligent CPE device management system based on visual recognition provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0023] It is understood that the terms "first," "second," etc., used herein may be used to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script without departing from the scope of this application.

[0024] like Figure 1 、 Figure 2 and Figure 3As shown, an intelligent CPE device management system based on visual recognition provided by an embodiment of the present invention includes:

[0025] The preprocessing module is used to collect device image information and user image information.

[0026] This module initializes the CPE device management system before use, collecting the device type and user image information to be connected. A single user can be associated with multiple types of devices, and the same device can be associated with multiple users, allowing the device network to be configured based on the needs of each user. The preprocessing module generates a visual recognition model and stores device information, paving the way for subsequent use.

[0027] The device identification and authentication module is used to identify device image information and user image information using a small sample target recognition algorithm, and to identify users and devices.

[0028] In this module, the camera integrated in the CPE device is used to capture device and user image information in real time, and the visual recognition model is used to identify the device type and user identity. The system uses a small sample target recognition algorithm based on a lightweight convolutional neural network to process and analyze the captured images, identify different devices such as smartphones, tablets, smart TVs, and confirm the user's identity through facial recognition technology. The small sample target recognition algorithm based on a lightweight convolutional neural network can achieve good target recognition effects even when computing resources are limited and training samples are few by introducing a lightweight target recognition network structure. The core of this type of algorithm is to reduce the computational complexity and parameter amount of the network, while using various small sample learning strategies to deal with the problem of insufficient data, thereby achieving efficient and accurate target detection effects under limited conditions. Unlike traditional CNNs that usually use 3 or more convolution blocks with too many training parameters, the present invention proposes a small sample target recognition algorithm based on LWCNN, which has 2 convolution blocks and a small number of convolution kernels. Its network structure is as follows: Figure 3As shown, the first layer is the input layer, which inputs the image; the second layer is the convolution layer, and the activation function uses the Hard Swish function. This layer is used to extract image features; the third layer is the pooling layer, which uses the max-pooling method for sampling. This layer can reduce the dimension of the data and compress the characteristics of the image; the fourth layer is the convolution layer, which uses twice the convolution kernel of the second layer, and the activation function uses the Hard Swish function, which can further extract image features; the fifth layer is the pooling layer, which uses the max-pooling method for sampling, and this layer further compresses image features; the sixth layer is the dropout layer, which sets the parameters of some neural nodes to 0 according to the set probability. In the present invention, the probability is set to 0.02 to reduce overfitting during training; the seventh layer is the flat layer, which folds the input spatial dimension into the channel dimension so that it can be connected to the complete connection layer; the eighth layer is the fully connected layer (dense layer), and the activation function uses the Hard Swish function; the ninth layer is the output layer, and the activation function uses the SoftMax function. Finally, the user and the bound device are identified as the user image and device information collected and stored during initialization, and the network connection is made for their device.

[0029] Based on the information stored in the pre-processing module, the system automatically authenticates known devices, eliminating the tedious process of repeated identity verification. For unauthorized devices, the system automatically blocks access to the network and prompts the user to add a new device for authentication, ensuring network security. For added security, the system records the identification and authentication history of all devices for administrators to audit and monitor.

[0030] The intelligent device matching module is used to adjust the network configuration strategy of each device based on the physical location of the device and the user's activity scenario, providing higher bandwidth for higher-priority devices.

[0031] In this module, the system automatically adjusts the device's network configuration and priority based on its physical location and the user's activity scenario. This includes, but is not limited to, macro environments such as home, work, and shopping malls, as well as micro environments such as bedrooms, living rooms, offices, conference rooms, and shops. In a home environment, if the system detects that a user is watching an HD video streaming service in the bedroom, it automatically increases the network priority of the bedroom device to ensure smooth video playback and reduces bandwidth usage for other non-critical devices. Similarly, in a conference room at work or a shopping mall, if the system detects a video conference in progress, it similarly prioritizes network bandwidth for conference-related devices to ensure a smooth meeting. Applications requiring high bandwidth and low latency, such as real-time communications like video conferencing and online gaming, and HD streaming media, are given higher priority. Non-real-time, less bandwidth-intensive applications, such as web browsing and file downloads, are assigned lower priority. Specific priority settings can be customized based on the user's specific needs, aiming to improve network resource utilization and enhance the user experience.

[0032] Provide personalized network environment settings for different users, such as common bandwidth priorities and different needs. The system can sense users' different activity scenarios, such as home entertainment and office work, and automatically adjust the device's network configuration accordingly. CPE devices identify user device usage through traffic analysis, network protocols, and visual recognition. By analyzing traffic characteristics such as packet size, transmission speed, and transmission time, CPE devices can identify which devices are making HD video calls or running high-data-consuming software. They can also analyze network protocols to identify which devices are communicating using specific protocols, such as WebRTC and Skype for video calls, or high-data-consuming video streaming protocols. Visual recognition can also be used. While visual technology is primarily used for intelligent matching and location identification, in some cases it can also assist in identifying device usage. By capturing the video call interface on the device's screen through the camera, it can indirectly determine whether a device is currently in a video call. These identification mechanisms do not exist in isolation; they complement and work together. Therefore, when a user is making an HD video call and needs to ensure network connectivity, the system automatically allocates more bandwidth to the relevant device to ensure smooth call flow.

[0033] Compared to traditional CPE device management, this invention uses vision-based intelligent CPE management. It improves device management security through intelligent identification and authentication modules and intelligent device matching modules. It dynamically identifies access devices, blocks unauthorized devices from accessing the network, and prevents information leakage. Furthermore, it can automatically adjust the device's network configuration and priority by identifying the device's physical location, providing a better network experience. Furthermore, it uses a small-sample target recognition algorithm based on a lightweight neural network, achieving good target recognition results even with limited computing resources and a small number of training samples.

[0034] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An intelligent CPE device management system based on visual recognition, characterized in that: The system comprises: A pre-processing module is used to collect device image information and user image information; The device identification and authentication module is used to identify device image information and user image information using a small sample target recognition algorithm to identify the user and the device; The intelligent device matching module adjusts the network configuration policy of each device based on the physical location of the device and the user's activity scenario, providing higher bandwidth to higher-priority devices; The small sample target recognition algorithm adopts a lightweight convolutional neural network: the first layer is the input layer, which is used to input the image; the second layer is the convolution layer, which is used to extract image features; the third layer is the pooling layer; the fourth layer is the convolution layer, which uses twice the convolution kernel of the second layer and the activation function adopts the Hard Swish function; the fifth layer is the pooling layer, which uses the max-pooling method for sampling; the sixth layer is the dropout layer, which is used to set the parameters of some neural nodes to 0 according to the set probability; the seventh layer is the flattening layer, which is used to fold the spatial dimension of the input into the channel dimension to connect to the complete connection layer; the eighth layer is the fully connected layer, which uses the Hard Swish function as the activation function; the ninth layer is the output layer, which uses the SoftMax function as the activation function; In the small sample target recognition algorithm, the second layer is the convolution layer, and the activation function uses the Hard Swish function; The third layer is the pooling layer, which uses the max-pooling method for sampling to reduce the dimension of the data and compress the characteristics of the image; The sixth layer is the dropout layer, and the probability is set to 0.02 to reduce the probability of overfitting during training.

2. The intelligent CPE device management system based on visual recognition according to claim 1 is characterized in that: The pre-processing module stores user information and device information. One user can be bound to multiple devices, and one device can be bound to multiple users.

3. The intelligent CPE device management system based on visual recognition according to claim 1 is characterized in that: Users' activity scenarios include home, company and shopping malls.

4. The intelligent CPE device management system based on visual recognition according to claim 3 is characterized in that: Users' activity scenarios include bedrooms, living rooms, offices, conference rooms and shops.

5. The intelligent CPE device management system based on visual recognition according to claim 4 is characterized in that: When the smart device matching module detects that a user is performing a specific activity in a specific activity scenario, it provides a higher network priority for the corresponding device used by the user and reduces the network bandwidth occupied by other low-priority devices.

6. The intelligent CPE device management system based on visual recognition according to claim 5, characterized in that: When a user uses a device, traffic analysis, network protocols, and visual recognition are used to determine the device's usage status. During the traffic analysis process, the device's running process is determined based on the data packet size, transmission speed, and transmission time.

7. The intelligent CPE device management system based on visual recognition according to claim 6, characterized in that: In the process of determining the device usage status based on the network protocol, when the WebRTC or Skype protocol used for video calls is detected, it is determined that the user is using the device for communication.

Images