Network scheduling method and device based on multi-network convergence and multi-network convergence access equipment

Abstract

The invention relates to a network scheduling method and device based on multi-network convergence and multi-network convergence access equipment. The method comprises the following steps: acquiring communication environment information corresponding to target equipment, standby network state information corresponding to a standby network link and cost information corresponding to a plurality of network links, and performing prediction processing based on equipment operation information, current network state information and a preset network prediction model to obtain network demand information; if the network demand information meets the preset parallel demand condition, performing network allocation processing based on the standby network state information, the current network state information, the network demand information, the cost information and a preset multi-target optimization network scheduling model to obtain target scheduling information; and updating the working states of the plurality of network links based on the plurality of target network types, so that the plurality of target network types are in the working state. According to the invention, the demand information of the user for the network can be predicted, the optimal network combination scheduling strategy is generated, and the stability and reliability of the network are improved.

Description

Technical Field

[0001] This disclosure relates to the field of network communication technology, and in particular to a network scheduling method, apparatus, and multi-network converged access device based on multi-network convergence. Background Technology

[0002] With the rapid evolution and widespread adoption of technologies such as mobile communication, wireless LAN, and low-Earth orbit satellite internet, modern smart terminal devices generally integrate multiple heterogeneous network interfaces, enabling them to simultaneously access 5G / 4G cellular networks, Wi-Fi, Ethernet, and even satellite communication networks. This provides the physical foundation for breaking through the limitations of a single network and achieving faster, more reliable, and more flexible connections.

[0003] Faced with complex multi-network converged environments, existing technologies mostly focus on intelligent switching of a single optimal network. Such solutions can largely guarantee network connectivity and avoid complete service interruptions. However, they are essentially still within the "single-link transmission" paradigm. When faced with sudden high-bandwidth or low-latency transmission demands such as high-definition video streaming, real-time interaction, and high-speed downloads of large files, the physical capacity limit and performance fluctuations of a single link become insurmountable bottlenecks. This fails to fully utilize the multi-network interface resources on the terminal side to match the ever-increasing real-time performance demands of users, easily leading to user experience degradation issues such as stuttering and excessively long waiting times. Some research focuses on multi-link parallel transmission and aggregation technologies, using bandwidth aggregation to improve overall throughput. However, most existing multi-network parallel solutions often adopt simple equal or fixed-ratio traffic allocation strategies. This extensive parallel approach easily leads to resource mismatch, resulting in ineffective waste of network resources and terminal power, failing to achieve a balance between user experience, system efficiency, and operational economy. Summary of the Invention

[0004] To address at least one of the aforementioned technical problems, this disclosure proposes a network scheduling method, apparatus, and multi-network converged access device based on multi-network convergence.

[0005] According to one aspect of this disclosure, a network scheduling method based on multi-network convergence is provided, applied to a multi-network converged access device connected to a target device via multiple network links, comprising: The communication environment information corresponding to the target device, the backup network status information corresponding to the backup network link, and the cost information corresponding to the multiple network links are obtained. The communication environment information includes device operation information and current network status information corresponding to the current working network link. The backup network is used to characterize the network links other than the current working network link among the multiple network links. Based on the device operation information, the current network status information, and the preset network prediction model, prediction processing is performed to obtain network demand information; If the network demand information meets the preset parallel demand conditions, network allocation processing is performed based on the backup network status information, the current network status information, the network demand information, the cost information, and the preset multi-objective optimized network scheduling model to obtain target scheduling information. The target scheduling information is used to characterize the scheduling schemes corresponding to multiple target network types. The working status of the multiple network links is updated based on the target scheduling information so that the network links corresponding to the multiple target network types are in a working state.

[0006] In some possible implementations, the method further includes: If the network demand information meets the preset single-line demand conditions, the target single-line network with the highest priority and in a connected state is determined based on the preset priority strategy. The working status of the multiple network links is updated based on the target single-line network so that the target single-line network is in a working state.

[0007] In some possible implementations, the backup network state information includes latency and packet loss rate, and the method further includes: Periodically send target detection packets to the target server; Receive the target response packet sent by the target server: The latency and packet loss rate are determined based on the target response packet.

[0008] In some possible implementations, the step of performing network allocation processing based on the backup network status information, the current network status information, the network demand information, the cost information, and a preset multi-objective optimized network scheduling model to obtain target scheduling information includes: Based on the backup network status information, the current network status information, the network demand information, and the cost information, information integration and normalization are performed to obtain a comprehensive input feature vector; The comprehensive input feature vector is input into the preset multi-objective optimization network scheduling model for network allocation processing to obtain target scheduling information.

[0009] In some possible implementations, the method further includes: Obtain the data to be sent and the link identifiers corresponding to the multiple target network types; The data to be sent is segmented based on the target scheduling information, and a segment identifier and a link identifier are added to each segment of data in the segmentation result to obtain multiple identified segment transmission data and a first identifier mapping table. Based on the network links corresponding to the multiple target network types, the multiple identifier fragments are sent along with the first identifier mapping table.

[0010] In some possible implementations, the method further includes: Based on the network links corresponding to the multiple target network types, obtain the received data of multiple identifier fragments sent by the target device and the second preset mapping table; Based on the segment identifier corresponding to each identified segment of received data and the second mapping table, the received data of the multiple identified segments are reassembled to obtain the target received data.

[0011] According to a second aspect of this disclosure, a network scheduling apparatus based on multi-network convergence is provided, applied to a multi-network converged access device connected to a target device via multiple network links, the apparatus comprising: The information acquisition module is used to acquire communication environment information corresponding to the target device, backup network status information corresponding to the backup network link, and cost information corresponding to the multiple network links. The communication environment information includes device operation information and current network status information corresponding to the current working network link. The backup network is used to characterize the network links other than the current working network link among the multiple network links. The network demand information determination module is used to perform prediction processing based on the device operation information, the current network status information and the preset network prediction model to obtain network demand information; The scheduling information determination module is used to perform network allocation processing based on the backup network status information, the current network status information, the network demand information, the cost information, and a preset multi-objective optimized network scheduling model if the network demand information meets the preset parallel demand conditions, in order to obtain target scheduling information. The target scheduling information is used to characterize the scheduling schemes corresponding to multiple target network types. The working status update module is used to update the working status of the multiple network links based on the target scheduling information, so that the network links corresponding to the multiple target network types are in a working state.

[0012] According to a third aspect of this disclosure, a multi-network converged access device is provided, including interfaces corresponding to multiple network links and a network scheduling device based on multi-network convergence as described in the second aspect.

[0013] According to a fourth aspect of this disclosure, an electronic device is provided, including at least one processor and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the at least one processor implements the network scheduling method based on multi-network convergence as described in any one of the first aspects by executing the instructions stored in the memory.

[0014] According to a fifth aspect of this disclosure, a computer-readable storage medium is provided, wherein at least one instruction or at least one program is stored therein, the at least one instruction or at least one program being loaded and executed by a processor to implement the network scheduling method based on multi-network convergence as described in any of the first aspects.

[0015] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure.

[0016] Implementing this disclosure will have the following beneficial effects: The system acquires communication environment information corresponding to the target device, backup network status information corresponding to the backup network link, and cost information corresponding to multiple network links. The communication environment information includes device operation information and current network status information corresponding to the currently working network link. The backup network represents network links other than the currently working network link. Based on the device operation information, current network status information, and a preset network prediction model, network demand information is obtained through prediction processing. Network transmission demand information is accurately predicted based on the device operation information and network status information to achieve proactive scheduling and meet users' high-quality and high-bandwidth network needs in real time. If the network demand information meets preset parallel demand conditions, network allocation processing is performed based on the backup network status information, current network status information, network demand information, cost information, and a preset multi-objective optimized network scheduling model to obtain target scheduling information. This target scheduling information represents the scheduling scheme corresponding to multiple target network types. When multiple networks need to operate in parallel, the optimal parallel scheduling strategy is generated by comprehensively considering demand, cost, and the status of each link to accurately respond to users' high network demands in real time. The working status of multiple network links is updated based on the target scheduling information to ensure that the network links corresponding to multiple target network types are in a working state. While minimizing costs, improve network stability and reliability to avoid network lag and stuttering issues.

[0017] Other features and aspects of this disclosure will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of this application, the accompanying drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0019] Figure 1A flowchart illustrating a network scheduling method based on multi-network convergence according to an embodiment of the present disclosure is shown. Figure 2 A flowchart illustrating a single-line network handover method according to an embodiment of the present disclosure is shown. Figure 3 A flowchart illustrating a network performance determination method according to an embodiment of the present disclosure is shown. Figure 4 A flowchart illustrating a method for determining target scheduling information according to an embodiment of the present disclosure is shown. Figure 5 A flowchart illustrating a parallel transmission method according to an embodiment of the present disclosure is shown; Figure 6 A flowchart illustrating a parallel receiving method according to an embodiment of the present disclosure is shown; Figure 7 This diagram illustrates the structure of a network scheduling device based on multi-network convergence according to an embodiment of the present disclosure. Figure 8 A block diagram of an electronic device according to an embodiment of the present disclosure is shown. Detailed Implementation

[0020] The technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0021] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0022] Various exemplary embodiments, features, and aspects of this disclosure will now be described in detail with reference to the accompanying drawings. The same reference numerals in the drawings denote elements that have the same or similar functions. Although various aspects of the embodiments are shown in the drawings, they are not necessarily drawn to scale unless specifically indicated otherwise.

[0023] The term “exemplary” as used herein means “serving as an example, embodiment, or illustration.” Any embodiment illustrated herein as “exemplary” is not necessarily to be construed as superior to or better than other embodiments.

[0024] In this document, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Furthermore, the term "at least one" in this document means any combination of at least two of any one or more elements. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.

[0025] Furthermore, to better illustrate this disclosure, numerous specific details are set forth in the following detailed description. Those skilled in the art will understand that this disclosure can be practiced without certain specific details. In some instances, methods, means, components, and circuits well known to those skilled in the art have not been described in detail in order to highlight the main points of this disclosure.

[0026] Figure 1 This diagram illustrates a flowchart of a network scheduling method based on multi-network convergence according to an embodiment of the present disclosure. The method is applied to a multi-network converged access device connected to a target device via multiple network links, such as... Figure 1 As shown, it includes: S101. Obtain the communication environment information corresponding to the target device, the backup network status information corresponding to the backup network link, and the cost information corresponding to multiple network links. The communication environment information includes the device operation information and the current network status information corresponding to the current working network link. The backup network is used to characterize the network links other than the current working network link among the multiple network links. Multi-network converged access devices are devices with interfaces corresponding to multiple network links. These network links are heterogeneous and have independent hardware interfaces. Each network interface can be configured with an independent IP address via DHCP or static allocation. If at least two network links need to transmit in parallel, a routing policy is configured based on a preset strategy so that outgoing traffic can select different interfaces and routing tables according to conditions such as source address, destination address, port, and type of service (ToS). Among the multiple network links, those in a working state are in an active state, while those in a non-working state are in a dormant state.

[0027] Multi-network converged access devices include, but are not limited to, routing devices and terminal devices. The implementing entity of this application is the central control module. The central control module can be built into the multi-network converged access device, or it can be deployed on an edge server, edge gateway, or cloud, depending on actual needs. Target devices include, but are not limited to, mobile phones, tablets, laptops, smart appliances, and head-mounted displays.

[0028] In some embodiments, the multiple network links include, but are not limited to, wireless network links, mobile network links, satellite network links, and fixed network links.

[0029] In some embodiments, communication environment information is used to characterize the current operating information of the target device. This information includes, but is not limited to, device operating information and current network status information. Device operating information includes time information, location information, battery level information, and application operation information. Application operation information includes, but is not limited to, user behavior data, foreground application information, application lifecycle status, background task queue, in-application status, and content metadata. User behavior data includes, but is not limited to, click events, such as opening a download page or clicking on video resolution while playing a video. Foreground application information includes videos, music, games, or app stores. Application lifecycle status includes whether the application is in the foreground, background, or suspended state. Background task queues include system updates, cloud synchronization, or email retrieval. In-application status includes live streaming or matchmaking games. Content metadata includes video bitrate adaptation and file size. Current network status information is used to characterize the performance information corresponding to the currently working network link, and backup network status information is used to characterize the performance information corresponding to the backup network link. Performance information includes, but is not limited to, signal strength, signal-to-noise ratio, bit error rate, throughput, latency, jitter, packet loss rate, and network connection status. Cost information includes, but is not limited to, data traffic fees and power consumption. Data traffic fees can be billed in the form of unlimited monthly data, pay-as-you-go, or data packages. Data packages include a certain amount of data, after which the speed will be reduced or pay-as-you-go will be charged. Power consumption can include the electricity consumption during operation.

[0030] S102. Based on equipment operation information, current network status information and preset network prediction model, perform prediction processing to obtain network demand information; The preset network prediction model is a model obtained by training an initial network model using a training dataset as input. The training dataset includes historical device operation information and corresponding historical network state information for the target device. The initial network model includes, but is not limited to, recurrent neural network models, temporal convolutional network models, and lightweight lifters. Network demand information is used to characterize the target device's future demand for network bandwidth, latency, and packet loss rate over a preset time period.

[0031] In some embodiments, network demand information includes bandwidth demand information, latency demand ceiling, and packet loss rate tolerance. Bandwidth demand information can be the network throughput corresponding to a preset future time period. For example, bandwidth demand information includes a time throughput sequence array [(t+1, BW1), (t+2, BW2), ..., (t+T, BWT)], where t is the current time and BW is the throughput. Latency demand ceiling includes maximum tolerable latency and latency jitter requirement, such as a latency demand ceiling of {"maximum tolerable latency": 50ms, "latency jitter requirement": <20ms}. Packet loss rate tolerance can be a packet loss rate less than or equal to a preset packet loss rate.

[0032] S103. If the network demand information meets the preset parallel demand conditions, network allocation processing is performed based on the backup network status information, the current network status information, the network demand information, the cost information, and the preset multi-objective optimized network scheduling model to obtain target scheduling information. The target scheduling information is used to characterize the scheduling schemes corresponding to multiple target network types. The preset parallel demand conditions can be defined as follows: the target device's bandwidth, latency, or packet loss rate requirements necessitate parallel processing by at least two network links, and the currently operating network link cannot meet the predicted network demand. Specifically, within a preset future time period, there must be a network throughput greater than a preset throughput threshold, a maximum tolerable latency less than a preset latency threshold, a latency jitter requirement less than a preset jitter threshold, or a packet loss rate tolerance less than a preset packet loss rate threshold. Furthermore, the target device's current bandwidth, latency, or packet loss rate requirements must exceed the overall throughput, overall latency, and overall packet loss rate of the currently operating network link. The currently operating network link must include at least one network link. If the network demand information meets the preset parallel demand conditions, it is determined that a single network link cannot meet the network demand within the preset future time period, and the currently operating network link also cannot meet the network demand within the preset future time period. Based on backup network status information, current network link status information, network demand information, cost information, and a preset multi-objective optimized network scheduling model, network optimization allocation processing is performed to obtain multiple target network types and optimized allocation scheduling schemes. If network demand information indicates that at least two network links need to process in parallel, and the currently working network link is capable of handling the demand, then the working state of the currently working network link and the non-working state of the backup network link will continue to be maintained.

[0033] The pre-defined multi-objective optimization network scheduling model can employ a multi-objective evolutionary algorithm, such as a multi-objective genetic algorithm, as the core optimization engine. This model can output Pareto-optimal network selection types and target scheduling information under multiple constraints, including latency, cost, and throughput as optimization objectives, and network quantity, budget, and latency limits. The target scheduling information characterizes the network scheduling scheme that processes tasks corresponding to target network requirements based on network links corresponding to multiple target network types.

[0034] In some embodiments, a preset network scheduling model can also be used to determine target scheduling information including multiple target network types based on backup network status information, current network status information, network demand information, cost information, and the preset network scheduling model. The preset network scheduling model is obtained by training an initial neural model with an optimized training set as input. The optimized training set includes the optimal multi-network parallel allocation scheme corresponding to different network demands, as well as network status information corresponding to multiple network links.

[0035] S104. Update the working status of multiple network links based on the target scheduling information so that the network links corresponding to multiple target network types are in working status.

[0036] The current working network link is deactivated, and the network links corresponding to multiple target network types are activated and switched to the current working network link.

[0037] In some embodiments, the network links corresponding to multiple target network types are physically activated, and the interfaces corresponding to multiple target network types are configured based on the Multiple Path TCP (MPTCP) protocol, adding independent MPTCP sub-streams.

[0038] The above technical solution accurately predicts network transmission demand based on equipment operation and network status information, enabling proactive scheduling and meeting users' high-quality and high-bandwidth network needs in real time. When multiple networks need to operate in parallel, it comprehensively considers demand, cost, and the status of each link to generate an optimal parallel scheduling strategy, responding accurately and in real time to users' high network demands. While minimizing costs, it improves network stability and reliability, preventing network lag and congestion caused by sudden surges in network demand.

[0039] Please see Figure 2 In some embodiments, the method further includes: S201. If the network demand information meets the preset single-line demand conditions, determine the target single-line network with the highest priority and in a connected state based on the preset priority strategy. S202. Update the working status of multiple network links based on the target single-line network so that the target single-line network is in a working state.

[0040] The preset single-link requirement conditions can be set so that the target device's bandwidth, latency, or packet loss rate requirements can be handled by only one network link. Specifically, this means that within a preset time period, the network throughput is less than or equal to a preset throughput threshold, the maximum tolerable latency is less than or equal to a preset latency threshold, the latency jitter requirement is less than or equal to a preset jitter threshold, or the packet loss rate tolerance is greater than or equal to a preset packet loss rate threshold. The preset priority policy can be configured by comprehensively considering speed, performance, cost, and convenience. If the network requirement information can be met by a single link, then the target single-link network with the highest priority and currently connected status will be periodically switched to the current working network link based on the preset priority policy.

[0041] In some embodiments, if the network demand information meets the preset single-row demand conditions, multiple network links are traversed according to a preset priority strategy at preset time intervals. When traversing a network link, the connectivity status of the currently traversed target link is detected. The connectivity status includes normal connectivity and abnormal connectivity. Abnormal connectivity status includes, but is not limited to, disconnection and channel congestion. If the connectivity status is normal connectivity and the target link is not the current working link of the access device, the current working link corresponding to the access device is switched to the currently traversed target link, and the traversal for the current period ends.

[0042] If the current network requirements can be met by a single-line network, the above technical solution maintains the current working network link as the optimal and connected network to ensure the best internet experience for users.

[0043] Please see Figure 3 In some embodiments, the backup network status information includes latency and packet loss rate, and the method further includes: S301. Periodically send target detection packets to the target server; S302. Receive the target response packet sent by the target server: S303. Determine latency and packet loss rate based on target response packets.

[0044] The backup network link is a network link in a deep sleep state. The backup network status information and the current working network status information include, but are not limited to, signal strength, signal-to-noise ratio, bit error rate, throughput, latency, jitter, packet loss rate, and network connection status. Among them, signal strength can be queried locally; for example, Wi-Fi can be read through the driver interface, and cellular networks can be queried through the command interface. Signal-to-noise ratio and bit error rate can be determined by probing physical layer parameters.

[0045] In some implementations, backup network links in deep sleep can be periodically and briefly woken up to send lightweight probes (target probe packets) to the target server. Through the target response packets, throughput, latency, latency jitter, packet loss rate, and network connection status can be determined.

[0046] The above technical solution accurately detects the network status information of backup network links through probe packets, providing accurate information for subsequent network scheduling and improving the accuracy of network allocation. Please see Figure 4 In some embodiments, network allocation processing is performed based on backup network status information, current network status information, network demand information, cost information, and a preset multi-objective optimized network scheduling model to obtain target scheduling information, including: S1031. Based on the backup network status information, current network status information, network demand information, and cost information, information integration and normalization are performed to obtain a comprehensive input feature vector; S1032. Input the comprehensive input feature vector into the preset multi-objective optimization network scheduling model for network allocation processing to obtain target scheduling information.

[0047] The pre-defined multi-objective optimization network scheduling model takes latency, cost, and throughput as optimization objectives and multiple constraints such as network quantity, budget, and latency limit as conditions, and outputs Pareto optimal network selection type and objective scheduling information.

[0048] In some embodiments, backup network status information, current network status information, network demand information, and cost information are integrated and normalized to obtain a sum of input feature vectors including network demand vectors and information vectors corresponding to each network link. Based on the comprehensive input feature vector, a preset multi-objective optimization network scheduling model is input to perform multi-objective optimization of network latency, cost, and throughput. Two or more different numbers of network links are set respectively, and the output includes an allocation scheme for multiple target network types with optimal performance.

[0049] The above technical solution outputs the optimal network allocation scheme by pre-setting a multi-objective optimized network scheduling model. It intelligently allocates the most suitable link combination for high traffic demand by taking into account cost and link status, thereby saving costs and improving the user's Internet experience.

[0050] Please see Figure 5 In some embodiments, the method further includes: S401. Obtain the data to be sent and the link identifiers corresponding to multiple target network types; S402. Based on the target scheduling information, the data to be sent is segmented, and a segment identifier and a link identifier are added to each segment of data in the segmentation result to obtain multiple identified segment transmission data and a first identifier mapping table. S403. Send multiple identifier fragments and a first identifier mapping table based on the network links corresponding to multiple target network types.

[0051] After the network links corresponding to multiple target network types are in working state, in response to the data request command of the target device, the data to be sent corresponding to the data request command is obtained. The data to be sent is fragmented according to the target scheduling information to obtain the fragmentation result. Each fragment of data in the fragmentation result is added with a fragment identifier and a link identifier, and the fragment identifier and link identifier are recorded in the identifier mapping table. Multiple identified fragments of data are sent in parallel based on the link identifier and the network links corresponding to multiple target network types. The identifier mapping table can be randomly sent through the network links corresponding to multiple target network types.

[0052] In some embodiments, after the data to be transmitted is fragmented based on the target scheduling information, error correction codes are calculated for each fragment of data in the fragmentation result to obtain multiple error correction codes; the multiple error correction codes are randomly allocated to network links corresponding to multiple target network types based on a preset allocation ratio, so that the target device can determine the lost identification fragments and transmit data based on the multiple error correction codes.

[0053] The above technical solution improves the overall network performance of data transmission by using target scheduling information to send data to be sent in parallel across multiple networks, thereby meeting the network demand for sudden increases in network load in real time and improving the user's internet experience.

[0054] Please see Figure 6 In some embodiments, the method further includes: S501. Obtain multiple identifier fragment received data and a second preset mapping table sent by the target device based on the network links corresponding to multiple target network types; S502. Based on the segment identifier and the second mapping table corresponding to each segment of received data, perform information recombination processing on multiple segments of received data to obtain the target received data.

[0055] Multiple identified data segments are generated by the target device by fragmenting and identifying the data it needs to send. The second preset mapping table is a mapping table of the relationship between segment identifiers and link identifiers recorded by the target device after fragmentation and identification. After receiving the multiple identified data segments and the second preset mapping table, the multi-network converged access device performs information reassembly processing on the multiple identified data segments based on the second mapping table to obtain the target received data.

[0056] The above technical solution rapidly receives fragmented data sent by the target device through network links corresponding to multiple target network types and combines them to obtain complete received data, thereby improving data transmission efficiency and ensuring the integrity of transmitted data.

[0057] Please see Figure 7 According to a second aspect of this disclosure, a network scheduling device based on multi-network convergence is provided, applied to a multi-network converged access device connected to a target device via multiple network links, the device comprising: Information acquisition module 10 is used to acquire communication environment information corresponding to the target device, backup network status information corresponding to the backup network link, and cost information corresponding to multiple network links. The communication environment information includes device operation information and current network status information corresponding to the current working network link. The backup network is used to characterize the network links other than the current working network link among the multiple network links. The network demand information determination module 20 is used to perform prediction processing based on device operation information, current network status information and preset network prediction model to obtain network demand information; The scheduling information determination module 30 is used to perform network allocation processing based on backup network status information, current network status information, network demand information, cost information and a preset multi-objective optimized network scheduling model if the network demand information meets the preset parallel demand conditions, so as to obtain target scheduling information. The target scheduling information is used to characterize the scheduling schemes corresponding to multiple target network types. The working status update module 40 is used to update the working status of multiple network links based on the target scheduling information, so that the network links corresponding to multiple target network types are in working status.

[0058] In some embodiments, the apparatus further includes: The target single-row network determination module is used to determine the target single-row network with the highest priority and in a connected state based on a preset priority strategy if the network requirement information meets the preset single-row requirement conditions. The network update module is used to update the working status of multiple network links based on the target single-line network, so that the target single-line network is in a working state.

[0059] In some embodiments, the backup network status information includes latency and packet loss rate, and the apparatus further includes: The probe packet sending module is used to periodically send target probe packets to the target server; The response packet receiving module is used to receive the target response packet sent by the target server. The performance determination module is used to determine latency and packet loss rate based on the target response packet.

[0060] In some embodiments, the scheduling information determination module 30 includes: The feature vector determination unit is used to integrate and normalize information based on backup network status information, current network status information, network demand information, and cost information to obtain a comprehensive input feature vector; The network allocation unit is used to input the comprehensive input feature vector into a preset multi-objective optimization network scheduling model for network allocation processing to obtain target scheduling information.

[0061] In some embodiments, the apparatus further includes: The data acquisition module is used to acquire the data to be sent and the link identifiers corresponding to multiple target network types; The fragmentation module is used to fragment the data to be sent based on the target scheduling information, and add a fragment identifier and a link identifier to each fragment of data in the fragmentation processing result to obtain multiple identified fragments of data to be sent and a first identifier mapping table. The sending module is used to send multiple identifier fragments of data and a first identifier mapping table based on the network links corresponding to multiple target network types.

[0062] In some embodiments, the apparatus further includes: The receiving module is used to obtain multiple identifier fragment received data and a second preset mapping table sent by the target device based on the network links corresponding to multiple target network types; The reassembly module is used to reassemble multiple identified segment received data based on the segment identifier corresponding to each identified segment and the second mapping table to obtain the target received data.

[0063] According to a third aspect of this disclosure, a multi-network converged access device is provided, including interfaces corresponding to multiple network links and a network scheduling device based on multi-network convergence as described above.

[0064] In some embodiments, the functions or modules of the apparatus provided in this disclosure can be used to perform the methods described in the above method embodiments. The specific implementation can be referred to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0065] This application provides a network scheduling device based on multi-network convergence. The device can be a terminal or a server. The network scheduling device based on multi-network convergence includes a processor and a memory. The memory stores at least one instruction or at least one program. The at least one instruction or at least one program is loaded and executed by the processor to implement the network scheduling method based on multi-network convergence as provided in the above method embodiments.

[0066] Memory is used to store software programs and modules. The processor executes these stored software programs and modules to perform various functional applications and data processing. Memory can primarily consist of a program storage area and a data storage area. The program storage area stores the operating system, application programs required for functionality, etc.; the data storage area stores data created based on device usage, etc. Furthermore, memory can include high-speed random access memory (RAM) and non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, memory can also include a memory controller to provide the processor with access to the memory.

[0067] The methods and embodiments provided in this application can be executed in electronic devices such as mobile terminals, computer terminals, servers, or similar computing devices. Figure 8 This is a hardware structure block diagram of an electronic device based on a network scheduling method for multi-network convergence, as provided in an embodiment of this application. Figure 8 As shown, the electronic device 900 can vary considerably due to differences in configuration or performance. It may include one or more Central Processing Units (CPUs) 910 (CPUs 910 may include, but are not limited to, microprocessors such as MCUs or programmable logic devices such as FPGAs), a memory 930 for storing data, and one or more storage media 920 (e.g., one or more mass storage devices) for storing application programs 923 or data 922. The memory 930 and storage media 920 may be temporary or persistent storage. The program stored in the storage media 920 may include one or more modules, each module may include a series of instruction operations on the electronic device. Furthermore, the CPU 910 may be configured to communicate with the storage media 920 and execute the series of instruction operations in the storage media 920 on the electronic device 900. Electronic device 900 may also include one or more power supplies 960, one or more wired or wireless network interfaces 950, one or more input / output interfaces 940, and / or one or more operating systems 921, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, etc.

[0068] The input / output interface 940 can be used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the electronic device 900. In one example, the input / output interface 940 includes a network interface controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the input / output interface 940 may be a radio frequency (RF) module used for wireless communication with the Internet.

[0069] Those skilled in the art will understand that Figure 8 The structure shown is for illustrative purposes only and does not limit the structure of the electronic device described above. For example, the electronic device 900 may also include... Figure 8 The more or fewer components shown, or having the same Figure 8 The different configurations shown.

[0070] Embodiments of this application also provide a computer-readable storage medium, which can be disposed in an electronic device to store at least one instruction or at least one program related to implementing a network scheduling method based on multi-network convergence in the method embodiment. The at least one instruction or the at least one program is loaded and executed by the processor to implement the network scheduling method based on multi-network convergence provided in the above method embodiment.

[0071] Optionally, in this embodiment, the storage medium may be located at at least one of the multiple network servers in a computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0072] According to one aspect of this application, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods provided in the various alternative implementations described above.

[0073] As can be seen from the embodiments of the network scheduling method, apparatus, device, terminal, server, storage medium, or computer program based on multi-network convergence provided in this application, when only one network link among multiple network links is in a working state, this application periodically acquires the communication environment information corresponding to the target device, the backup network status information corresponding to the backup network link, and the cost information corresponding to multiple network links. The communication environment information includes device operation information and the current network status information corresponding to the currently working network link. The backup network is used to characterize the network links other than the currently working network link among the multiple network links. Based on the device operation information, the current network status information, and the preset network prediction model, prediction processing is performed to obtain network demand information. Based on the device operation information and the network status information, the network transmission demand information is accurately predicted to achieve forward-looking scheduling and meet the user's high-quality and high-bandwidth network needs in real time. If network demand information meets preset parallel demand conditions, network allocation is performed based on backup network status information, current network status information, network demand information, cost information, and a preset multi-objective optimized network scheduling model to obtain target scheduling information. This target scheduling information characterizes the scheduling schemes corresponding to multiple target network types. When multiple networks need to operate in parallel, the optimal parallel scheduling strategy is generated by comprehensively considering demand, cost, and the status of each link, responding accurately and in real time to users' high network demands. The working status of multiple network links is updated based on the target scheduling information to ensure that network links corresponding to multiple target network types are in working condition. This improves network stability and reliability while minimizing costs, avoiding network lag and congestion issues.

[0074] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in a different order than that shown in the embodiments and still achieve the desired results. Additionally, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are also possible or may be advantageous.

[0075] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the device, equipment, and storage medium embodiments are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0076] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware, or by a program instructing the relevant hardware to implement them. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0077] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A network scheduling method based on multi-network convergence, characterized in that, The method is applied to a multi-network fusion access device connected with a target device through multiple network links, and the method comprises the following steps: Obtaining communication environment information corresponding to the target device, standby network state information corresponding to a standby network link, and cost information corresponding to the multiple network links, wherein the communication environment information comprises device running information and current network state information corresponding to a current working network link, and the standby network is used to represent network links other than the current working network link in the multiple network links; Performing prediction processing based on the device running information, the current network state information, and a preset network prediction model to obtain network demand information; If the network demand information meets a preset parallel demand condition, performing network allocation processing based on the standby network state information, the current network state information, the network demand information, the cost information, and a preset multi-target optimization network scheduling model to obtain target scheduling information, wherein the target scheduling information is used to represent scheduling schemes corresponding to multiple target network types; Updating the working states of the multiple network links based on the target scheduling information, so that the network links corresponding to the multiple target network types are in working states.

2. The method of claim 1, wherein, The method further comprises the following steps: If the network demand information meets a preset single-line demand condition, determining a target single-line network with the highest priority and in a connected state based on a preset priority strategy; Updating the working states of the multiple network links based on the target single-line network, so that the target single-line network is in a working state.

3. The method of claim 1, wherein, The standby network state information comprises a time delay and a packet loss rate, and the method further comprises the following steps: Periodically sending a target probe packet to a target server; Receiving a target response packet sent by the target server; Determining the time delay and the packet loss rate based on the target response packet.

4. The method of claim 1, wherein, The network allocation processing based on the standby network state information, the current network state information, the network demand information, the cost information, and the preset multi-target optimization network scheduling model to obtain the target scheduling information comprises the following steps: Performing information integration and normalization processing based on the standby network state information, the current network state information, the network demand information, and the cost information to obtain a comprehensive input feature vector; Inputting the comprehensive input feature vector into the preset multi-target optimization network scheduling model to perform network allocation processing and obtain the target scheduling information.

5. The method of claim 1, wherein, The method further comprises the following steps: Obtaining to-be-sent data and link identifiers corresponding to the multiple target network types; Performing fragmentation processing on the to-be-sent data based on the target scheduling information, adding a fragment identifier and a link identifier to each fragment data in the fragmentation processing result to obtain multiple identified fragment sending data and a first identifier mapping table; Sending the multiple identified fragment sending data and the first identifier mapping table based on the network links corresponding to the multiple target network types.

6. The method of claim 1, wherein, The method further comprises the following steps: Obtaining multiple identified fragment receiving data and a second preset mapping table sent by the target device based on the network links corresponding to the multiple target network types. The plurality of identification fragment receiving data are information reorganization processed based on a corresponding fragment identification of each identification fragment receiving data and the second mapping table to obtain target receiving data.

7. A network scheduling device based on multi-network fusion, characterized in that, The application is applied to a multi-network fusion access device connected with a target device through a plurality of network links, and the device comprises: An information acquisition module is configured to acquire communication environment information corresponding to the target device, standby network state information corresponding to a standby network link, and cost information corresponding to the plurality of network links, wherein the communication environment information comprises device running information and current network state information corresponding to a current working network link, and the standby network is used to represent network links other than the current working network link in the plurality of network links. A network demand information determination module is configured to perform prediction processing based on the device running information, the current network state information, and a preset network prediction model to obtain network demand information. A scheduling information determination module is configured to perform network allocation processing based on the standby network state information, the current network state information, the network demand information, the cost information, and a preset multi-target optimization network scheduling model to obtain target scheduling information if the network demand information satisfies a preset parallel demand condition, wherein the target scheduling information is used to represent a scheduling scheme corresponding to a plurality of target network types. A working state updating module is configured to update working states of the plurality of network links based on the target scheduling information so that network links corresponding to the plurality of target network types are in working states.

8. A multi-network convergence access device, characterized in that, The device comprises interfaces corresponding to the plurality of network links and the network scheduling device based on multi-network fusion according to claim 7.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by the processor to implement the network scheduling method based on multi-network fusion according to any one of claims 1-6.

10. An electronic device, comprising: The device comprises at least one processor and a memory connected with the at least one processor in communication, wherein the memory stores instructions executable by the at least one processor, and the at least one processor implements the network scheduling method based on multi-network fusion according to any one of claims 1-6 by executing the instructions stored in the memory.

Images