Multi-channel data transmission optimization method and device and electronic equipment

Abstract

The invention provides a multi-channel data transmission optimization method and device and electronic equipment, and relates to the technical field of communication technology and network flow scheduling, and the method comprises the steps: obtaining a dynamic performance index set of a plurality of transmission channels in real time; based on the dynamic performance index set, the comprehensive weight of each index is determined through an adaptive weight distribution model, and the real-time health degree score of each channel is calculated; inputting the historical performance data of each channel into a time sequence prediction model, and predicting a predicted health degree score of each channel at a future scheduling moment; based on the real-time health degree score and the predicted health degree score, performing joint decision through a multi-target decision function, and selecting a target transmission channel; and based on the actual transmission result of the target transmission channel, performing feedback optimization on the time sequence prediction model and the adaptive weight distribution model. According to the invention, multi-dimensional real-time sensing and adaptive weight allocation are realized, a predictive decision-making capability is provided, and a multi-channel data transmission optimization scheme of a self-optimization closed loop is formed.

Description

Technical Field

[0001] This invention relates to the fields of communication technology and network traffic scheduling technology, and in particular to a method, apparatus and electronic device for optimizing multi-channel data transmission. Background Technology

[0002] In communication services such as SMS gateways, IoT data pass-through, and large-scale application push, multi-channel parallel transmission is the basic architecture to ensure high availability and high concurrency processing capabilities. However, in actual operation, the performance of each transmission channel is not static, but is dynamically affected by a variety of complex factors such as network congestion, operator policy adjustments, and local infrastructure failures, which can lead to problems such as uneven load distribution and transmission quality fluctuations between channels.

[0003] In existing technologies, common multi-channel scheduling schemes often rely on static configuration or simple historical statistics. For example, while the round-robin method can achieve basic load balancing, it cannot detect the real-time congestion status of channels and is prone to continuously sending messages to overloaded channels. Fixed-priority scheduling strategies, although simple, lack flexibility and cannot adapt to dynamic changes in the network environment. On the other hand, some schemes based on historical average success rates, although considering certain quality factors, have serious lag and cannot respond to second- or minute-level channel performance fluctuations.

[0004] These solutions share several drawbacks: First, they rely on a single decision-making dimension, failing to comprehensively consider multiple indicators such as real-time load, transmission reliability, response speed, and stability of the channel. Second, they lack foresight, making decisions entirely based on current or historical conditions, making it impossible to predict and avoid impending channel performance degradation, which can easily trigger a "avalanche effect" (i.e., when one channel deteriorates, all traffic flows to another channel, causing it to quickly become overloaded). Third, the system parameters are fixed, and once key parameters such as weights are set, they are difficult to adjust adaptively, making it impossible to maintain optimal performance when business models or network characteristics change.

[0005] Therefore, a method, apparatus, and electronic device for optimizing multi-channel data transmission are proposed. Summary of the Invention

[0006] This specification provides a multi-channel data transmission optimization method, device, and electronic device that enables multi-dimensional real-time perception, adaptive weight allocation, predictive decision-making capabilities, and the formation of a self-optimizing closed loop for multi-channel data transmission optimization.

[0007] This specification provides a method for optimizing multi-channel data transmission, including: Real-time acquisition of dynamic performance metrics sets for multiple transmission channels; Based on the dynamic performance index set, the comprehensive weight of each index is determined by an adaptive weight allocation model, and the real-time health score of each channel is calculated. The historical performance data of each channel is input into the time series prediction model to predict the predicted health score of each channel at future scheduling times. Based on the real-time health score and the predicted health score, a joint decision is made through a multi-objective decision function to select a target transmission channel; Based on the actual transmission results of the target transmission channel, the time-series prediction model and the adaptive weight allocation model are optimized through feedback.

[0008] Optionally, the real-time acquisition of the dynamic performance metric set includes: Based on a dynamically adjustable sliding time window, the instantaneous throughput, transmission success rate, and average response latency of each channel are collected. The channel stability index is calculated based on the fluctuation of the transmission success rate or the average response delay within the sliding time window. The size of the sliding time window is adaptively adjusted in reverse according to the mutation rate of the network state.

[0009] Optionally, the dynamic performance index set includes at least indices reflecting channel load, transmission reliability, and response time.

[0010] Optionally, determining the comprehensive weight of each indicator through an adaptive weight allocation model includes: The information entropy weighting method is used to calculate the objective weight vector based on the data dispersion of each indicator across all channels; Based on the analytic hierarchy process (AHP), subjective weight vectors are determined according to pre-defined business rules. The fusion coefficient is dynamically calculated based on the signal-to-noise ratio of the historical dataset, and the objective weight vector and the subjective weight vector are weighted and fused based on the fusion coefficient to output the comprehensive weight.

[0011] Optionally, the time-series prediction model is a pre-trained long short-term memory network model; The prediction of the health score of each channel at future scheduling time includes: taking the health score sequence in the historical performance data and the original value of the dynamic performance index as input features, and performing multivariate time series prediction through the long short-term memory network model; For newly launched channels, the similarity between their fixed attributes and existing channels is calculated, and the predicted value of the most similar channel is used as its initial predicted health score.

[0012] Optionally, the step of selecting a target transmission channel based on the real-time health score and the predicted health score through a multi-objective decision function includes: Decision value = α * S c +β*S p -γ*C sel +δ*I stab Among them, S c For the real-time health score, S p For the predicted health score, C sel The overload protection factor is defined as the number of times the channel has been selected in the recent past. stab Let α, β, γ, and δ be the channel stability indices, and let α, β, γ, and δ be the balance parameters tuned using a multi-objective optimization algorithm.

[0013] Optionally, the step of performing feedback optimization on the time-series prediction model and the adaptive weight allocation model based on the actual transmission results of the target transmission channel includes: Establish a priority experience replay buffer to store transmission result samples, and assign higher sampling priority to samples that fail to make decisions or degrade in performance; High-priority samples are periodically extracted from the buffer to perform incremental learning and online fine-tuning on the time series prediction model; At fixed intervals, the adaptive weight allocation model is re-executed based on the recently collected set of dynamic performance indicators to update the comprehensive weights.

[0014] This specification provides a multi-channel data transmission optimization device, including: The acquisition module is used to acquire dynamic performance indicator sets of multiple transmission channels in real time. The calculation module is used to determine the comprehensive weight of each indicator based on the dynamic performance indicator set through an adaptive weight allocation model, and to calculate the real-time health score of each channel. The prediction module is used to input the historical performance data of each channel into the time series prediction model to predict the predicted health score of each channel at future scheduling times. The decision module is used to select a target transmission channel by making a joint decision based on the real-time health score and the predicted health score through a multi-objective decision function. The optimization module is used to perform feedback optimization on the time-series prediction model and the adaptive weight allocation model based on the actual transmission results of the target transmission channel.

[0015] Optionally, the acquisition module includes: Based on a dynamically adjustable sliding time window, the instantaneous throughput, transmission success rate, and average response latency of each channel are collected. The channel stability index is calculated based on the fluctuation of the transmission success rate or the average response delay within the sliding time window. The size of the sliding time window is adaptively adjusted in reverse according to the mutation rate of the network state.

[0016] Optionally, the dynamic performance index set includes at least indices reflecting channel load, transmission reliability, and response time.

[0017] Optionally, the computing module includes: The information entropy weighting method is used to calculate the objective weight vector based on the data dispersion of each indicator across all channels; Based on the analytic hierarchy process (AHP), subjective weight vectors are determined according to pre-defined business rules. The fusion coefficient is dynamically calculated based on the signal-to-noise ratio of the historical dataset, and the objective weight vector and the subjective weight vector are weighted and fused based on the fusion coefficient to output the comprehensive weight.

[0018] Optionally, the time-series prediction model is a pre-trained long short-term memory network model; The prediction of the health score of each channel at future scheduling time includes: taking the health score sequence in the historical performance data and the original value of the dynamic performance index as input features, and performing multivariate time series prediction through the long short-term memory network model; For newly launched channels, the similarity between their fixed attributes and existing channels is calculated, and the predicted value of the most similar channel is used as its initial predicted health score.

[0019] Optionally, the decision module includes: Decision value = α*S c +β*S p -γ*C sel +δ*I stab Among them, S c For the real-time health score, S p For the predicted health score, C sel The overload protection factor is defined as the number of times the channel has been selected in the recent past. stab Let α, β, γ, and δ be the channel stability indices, and let α, β, γ, and δ be the balance parameters tuned using a multi-objective optimization algorithm.

[0020] Optionally, the optimization module includes: Establish a priority experience replay buffer to store transmission result samples, and assign higher sampling priority to samples that fail to make decisions or degrade in performance; High-priority samples are periodically extracted from the buffer to perform incremental learning and online fine-tuning on the time series prediction model; At fixed intervals, the adaptive weight allocation model is re-executed based on the recently collected set of dynamic performance indicators to update the comprehensive weights.

[0021] This specification also provides an electronic device, wherein the electronic device includes: A processor; and a memory storing computer-executable instructions, which, when executed, cause the processor to perform any of the methods described above.

[0022] This specification also provides a computer-readable storage medium that stores one or more programs that, when executed by a processor, implement any of the methods described above.

[0023] This invention, by introducing real-time load metrics (such as instantaneous throughput) and combining them with adaptive weight calculation, proactively and intelligently guides data transmission requests to relatively idle channels, effectively avoiding congestion on a single channel and achieving dynamic load balancing among high-performance channels. This significantly improves the overall resource utilization and service throughput of the multi-channel system. By comprehensively evaluating transmission success rate, average response latency, and channel stability index, and assigning dynamic weights to these metrics in the decision-making process, the system can accurately select the channel with the highest transmission quality and most stable performance under the current network conditions. This effectively reduces message sending latency and packet loss rate, ensuring the quality of delivery for critical services. By using a time-series prediction model (such as LSTM) to predict the future health of the channels and incorporating the prediction results into the decision function, the system can proactively avoid potential performance bottlenecks. Simultaneously, the overload prevention factor (such as the number of recent selections) introduced into the decision function effectively smooths traffic, prevents scheduling oscillations, and greatly enhances the system's robustness in the face of sudden traffic surges. By constructing a feedback optimization closed loop based on actual transmission results and employing advanced machine learning techniques such as priority experience replay and online fine-tuning, this system is no longer a static scheduler, but an intelligent agent that can learn from historical decisions and continuously evolve with environmental changes, maintaining excellent scheduling performance over the long term. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1A schematic diagram illustrating the principle of a multi-channel data transmission optimization method provided in the embodiments of this specification; Figure 2 This is a schematic diagram of the structure of a multi-channel data transmission optimization device provided in the embodiments of this specification; Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this specification; Figure 4 This is a schematic diagram of a computer-readable medium provided for embodiments of this specification. Detailed Implementation

[0026] The following description is intended to disclose the present invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious variations will occur to those skilled in the art. The basic principles of the invention defined in the following description can be applied to other embodiments, modifications, improvements, equivalents, and other technical solutions that do not depart from the spirit and scope of the invention.

[0027] The following is in conjunction with the appendix Figure 1-4 Exemplary embodiments of the invention will be described more fully here. However, exemplary embodiments can be implemented in many forms and should not be construed as limiting the invention to the embodiments set forth herein. Rather, these exemplary embodiments are provided to make the invention more comprehensive and complete, and to facilitate a full communication of the inventive concept to those skilled in the art. The same reference numerals in the figures denote the same or similar elements, components, or parts, and therefore repeated descriptions of them are omitted.

[0028] Subject to the technical concept of this invention, the features, structures, characteristics or other details described in a particular embodiment may be combined in one or more other embodiments in a suitable manner.

[0029] In the description of specific embodiments, the features, structures, characteristics, or other details described in this invention are intended to enable those skilled in the art to fully understand the embodiments. However, it is not excluded that those skilled in the art can practice the technical solutions of this invention without one or more of the specific features, structures, characteristics, or other details.

[0030] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0031] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0032] The terms “and / or” or “and / or” include all combinations of any one or more of the listed items.

[0033] Figure 1 This is a schematic diagram illustrating the principle of a multi-channel data transmission optimization method provided in an embodiment of this specification. The method may include: S110: Real-time acquisition of dynamic performance metrics sets for multiple transmission channels; In the specific implementation of this specification, after initialization, the dynamic performance index set of all available channels (such as channels A, B, and C) is obtained in real time through the monitoring agent deployed on each channel. This set initially includes the number of successful and failed transmissions within the last 5 seconds.

[0034] Optionally, S110 includes: Based on a dynamically adjustable sliding time window, the instantaneous throughput, transmission success rate, and average response latency of each channel are collected. The channel stability index is calculated based on the fluctuation of the transmission success rate or the average response delay within the sliding time window. The size of the sliding time window is adaptively adjusted in reverse according to the mutation rate of the network state.

[0035] In the specific implementation of this specification, the initial size of the sliding time window is set to 30 seconds. The system continuously calculates the variance of the success rate within the window as a channel stability index. When the system detects that the success rate of a certain channel drops below a preset value within two consecutive sampling periods (e.g., 10 seconds) (i.e., the network state mutation rate is too high), it automatically and adaptively adjusts the window size of that channel to 10 seconds to capture its performance degradation more quickly. After the performance of that channel stabilizes for more than 2 minutes, the window size is gradually restored to 30 seconds to smooth out noise caused by instantaneous jitter.

[0036] Optionally, the dynamic performance index set includes at least indices reflecting channel load, transmission reliability, and response time.

[0037] In the specific implementation of this specification, three core metrics were explicitly selected when defining the dynamic performance metric set: instantaneous throughput (unit: lines / second) reflecting channel load, transmission success rate (percentage) reflecting transmission reliability, and average response latency (unit: milliseconds) reflecting response timeliness. These three metrics together constitute a comprehensive evaluation dimension for channel performance.

[0038] S120: Based on the dynamic performance index set, determine the comprehensive weight of each index through an adaptive weight allocation model, and calculate the real-time health score of each channel. In the specific implementation of this specification, the adaptive weight allocation model is triggered. This model is a calculation service with built-in entropy weight method and AHP method. It automatically calculates the weights based on the differences of each channel index and calculates the real-time health score of each channel (a value between 0 and 1).

[0039] Optionally, S120 includes: The information entropy weighting method is used to calculate the objective weight vector based on the data dispersion of each indicator across all channels; Based on the analytic hierarchy process (AHP), subjective weight vectors are determined according to pre-defined business rules. The fusion coefficient is dynamically calculated based on the signal-to-noise ratio of the historical dataset, and the objective weight vector and the subjective weight vector are weighted and fused based on the fusion coefficient to output the comprehensive weight.

[0040] In the specific implementation of this specification, when implementing the adaptive weight allocation model, firstly, the information entropy weighting method is used to process the indicator matrix of all channels to obtain an objective weight vector, for example, calculating [throughput weight = 0.5, success rate weight = 0.3, latency weight = 0.2]. Simultaneously, the operation and maintenance expert sets the subjective weight vector to [0.4, 0.4, 0.2] based on the analytic hierarchy process. The system then analyzes the signal-to-noise ratio of the indicator data over the past hour. If the signal-to-noise ratio is high (good data quality), the calculated fusion coefficient η is 0.7, and weighted fusion is performed: W final =0.7*[0.5, 0.3, 0.2]+0.3*[0.4, 0.4, 0.2]=[0.47, 0.33, 0.2], this vector is the final comprehensive weight used for calculation.

[0041] S130: Input the historical performance data of each channel into the time series prediction model to predict the predicted health score of each channel at future scheduling time; In the specific implementation of this specification, the time-series prediction model service (a trained LSTM network) predicts the predicted health score of each channel in the next minute based on the health sequence of the past hour.

[0042] Optionally, the time-series prediction model is a pre-trained long short-term memory network model; The prediction of the health score of each channel at future scheduling time includes: taking the health score sequence in the historical performance data and the original value of the dynamic performance index as input features, and performing multivariate time series prediction through the long short-term memory network model; For newly launched channels, the similarity between their fixed attributes and existing channels is calculated, and the predicted value of the most similar channel is used as its initial predicted health score.

[0043] In the specific implementation of this specification, the time-series prediction model uses the Keras framework in Python to build a pre-trained Long Short-Term Memory (LSTM) network model. During prediction, the model's input features include not only the health score sequence of the past 12 time points but also the raw values ​​of dynamic performance metrics (such as throughput and latency) for the same time period. For a newly launched channel, the system extracts its fixed attributes (such as the operator and bandwidth level), calculates cosine similarity with the existing channel set, finds the most similar channel (such as channel B), and then uses the predicted value of channel B as the initial predicted health score for the new channel, thereby solving the cold start problem.

[0044] S140: Based on the real-time health score and the predicted health score, a joint decision is made through a multi-objective decision function to select a target transmission channel; In the specific implementation of this specification, the decision engine selects the target transmission channel for this message transmission by executing a preset multi-objective decision function based on these two scores (for example, taking the channel with the highest weighted sum of the two).

[0045] Optionally, S140 includes: Decision value = α * S c +β*S p -γ*C sel +δ*I stab Among them, S c For the real-time health score, S p For the predicted health score, C sel The overload protection factor is defined as the number of times the channel has been selected in the recent past. stab Let α, β, γ, and δ be the channel stability indices, and let α, β, γ, and δ be the balance parameters tuned using a multi-objective optimization algorithm.

[0046] In the specific implementation of this specification, the multi-objective decision function takes the form: Decision value = 0.6 * S c +0.3*S p-0.08*C sel +0.02*I stab Among them, S c and S p These are the real-time and predicted scores for channel A, respectively, and C. sel It is the number of times channel A has been selected in the past minute (let's say 5 times), I stab This is its stability index (assumed to be 0.9). Substituting this into the calculation yields the decision value for channel A. The system will calculate this value for all available channels and select the channel with the highest decision value as the chosen target transmission channel. The balance parameters [α=0.6, β=0.3, γ=0.08, δ=0.02] are pre-optimized on historical datasets using a multi-objective optimization algorithm (such as NSGA-II).

[0047] S150: Based on the actual transmission results of the target transmission channel, perform feedback optimization on the time-series prediction model and the adaptive weight allocation model.

[0048] In the specific implementation of this specification, after the message is sent, the system will record the sample of this decision based on the actual transmission result (success or failure and delay time) returned by the channel, and trigger the feedback optimization process during the low-peak period in the early morning of each day to fine-tune and update the prediction model and weight allocation model.

[0049] Optionally, S150 includes: Establish a priority experience replay buffer to store transmission result samples, and assign higher sampling priority to samples that fail to make decisions or degrade in performance; High-priority samples are periodically extracted from the buffer to perform incremental learning and online fine-tuning on the time series prediction model; At fixed intervals, the adaptive weight allocation model is re-executed based on the recently collected set of dynamic performance indicators to update the comprehensive weights.

[0050] In the specific implementation of this specification, during the feedback optimization phase, the system establishes a priority experience replay buffer. When a decision results in message sending failure or timeout, the sample is marked as "decision failure" and assigned a higher sampling priority. Every night, the system periodically extracts a batch of high-priority samples from the buffer and mixes them with normal samples to perform incremental learning and online fine-tuning of the LSTM model. Simultaneously, every fixed period (e.g., every 24 hours), the system re-executes the weight allocation process described in claim 4 based on the dynamic performance index set collected over the past 24 hours to update the comprehensive weights for the next day, ensuring that the weight allocation remains consistent with the latest business data distribution.

[0051] In this invention, by introducing real-time load metrics (such as instantaneous throughput) and combining them with adaptive weight calculation, data transmission requests can be proactively and intelligently guided to relatively idle channels, effectively avoiding congestion on a single channel and achieving dynamic load balancing among high-performance channels. This significantly improves the overall resource utilization and service throughput of the multi-channel system. By comprehensively evaluating transmission success rate, average response latency, and channel stability index, and assigning dynamic weights to these metrics in the decision-making process, the system can accurately select the channels with the highest transmission quality and most stable performance under the current network conditions. This effectively reduces message sending latency and packet loss rate, ensuring the quality of delivery for critical services. By using a time-series prediction model (such as LSTM) to predict the future health of channels and incorporating the prediction results into the decision function, the system can proactively avoid potential performance bottlenecks. Simultaneously, the anti-overload factor (such as the number of recent selections) introduced into the decision function effectively smooths traffic, prevents scheduling oscillations, and greatly enhances the system's robustness in the face of sudden traffic surges. By constructing a feedback optimization closed loop based on actual transmission results and employing advanced machine learning techniques such as priority experience replay and online fine-tuning, this system is no longer a static scheduler, but an intelligent agent that can learn from historical decisions and continuously evolve with environmental changes, maintaining excellent scheduling performance over the long term.

[0052] Figure 2 This is a schematic diagram of a multi-channel data transmission optimization device provided in an embodiment of this specification. The device may include: The acquisition module 10 is used to acquire a set of dynamic performance indicators for multiple transmission channels in real time. The calculation module 20 is used to determine the comprehensive weight of each indicator based on the dynamic performance indicator set through an adaptive weight allocation model, and to calculate the real-time health score of each channel. Prediction module 30 is used to input the historical performance data of each channel into the time series prediction model to predict the predicted health score of each channel at a future scheduling time. Decision module 40 is used to select a target transmission channel by making a joint decision based on the real-time health score and the predicted health score through a multi-objective decision function. The optimization module 50 is used to perform feedback optimization on the time-series prediction model and the adaptive weight allocation model based on the actual transmission results of the target transmission channel.

[0053] Optionally, the acquisition module includes: Based on a dynamically adjustable sliding time window, the instantaneous throughput, transmission success rate, and average response latency of each channel are collected. The channel stability index is calculated based on the fluctuation of the transmission success rate or the average response delay within the sliding time window. The size of the sliding time window is adaptively adjusted in reverse according to the mutation rate of the network state.

[0054] Optionally, the dynamic performance index set includes at least indices reflecting channel load, transmission reliability, and response time.

[0055] Optionally, the computing module includes: The information entropy weighting method is used to calculate the objective weight vector based on the data dispersion of each indicator across all channels; Based on the analytic hierarchy process (AHP), subjective weight vectors are determined according to pre-defined business rules. The fusion coefficient is dynamically calculated based on the signal-to-noise ratio of the historical dataset, and the objective weight vector and the subjective weight vector are weighted and fused based on the fusion coefficient to output the comprehensive weight.

[0056] Optionally, the time-series prediction model is a pre-trained long short-term memory network model; The prediction of the health score of each channel at future scheduling time includes: taking the health score sequence in the historical performance data and the original value of the dynamic performance index as input features, and performing multivariate time series prediction through the long short-term memory network model; For newly launched channels, the similarity between their fixed attributes and existing channels is calculated, and the predicted value of the most similar channel is used as its initial predicted health score.

[0057] Optionally, the decision module includes: Decision value = α*S c +β*S p -γ*C sel +δ*I stab Among them, S c For the real-time health score, S p For the predicted health score, C sel The overload protection factor is defined as the number of times the channel has been selected in the recent past. stab Let α, β, γ, and δ be the channel stability indices, and let α, β, γ, and δ be the balance parameters tuned using a multi-objective optimization algorithm.

[0058] Optionally, the optimization module includes: Establish a priority experience replay buffer to store transmission result samples, and assign higher sampling priority to samples that fail to make decisions or degrade in performance; High-priority samples are periodically extracted from the buffer to perform incremental learning and online fine-tuning on the time series prediction model; At fixed intervals, the adaptive weight allocation model is re-executed based on the recently collected set of dynamic performance indicators to update the comprehensive weights.

[0059] The functions of the apparatus in this embodiment have been described in the above method embodiments. Therefore, for any parts not detailed in this embodiment, please refer to the relevant descriptions in the foregoing embodiments, which will not be repeated here.

[0060] Based on the same inventive concept, embodiments of this specification also provide an electronic device.

[0061] The following describes embodiments of the electronic device of the present invention, which can be considered as specific implementations of the methods and apparatus embodiments of the present invention described above. Details described in the embodiments of the electronic device of the present invention should be considered as supplements to the methods or apparatus embodiments described above; details not disclosed in the embodiments of the electronic device of the present invention can be implemented with reference to the methods or apparatus embodiments described above.

[0062] Figure 3 This is a schematic diagram of an electronic device provided as an embodiment of this specification. Refer to the following... Figure 3 The electronic device 300 according to this embodiment of the present invention will be described. Figure 3 The electronic device 300 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0063] like Figure 3 As shown, the electronic device 300 is presented in the form of a general-purpose computing device. The components of the electronic device 300 may include, but are not limited to: at least one processing unit 310, at least one storage unit 320, a bus 330 connecting different system components (including storage unit 320 and processing unit 310), a display unit 340, etc.

[0064] The storage unit stores program code that can be executed by the processing unit 310, causing the processing unit 310 to perform the steps described in the processing method section of this specification according to various exemplary embodiments of the present invention. For example, the processing unit 310 can perform, for example... Figure 1 The steps are shown.

[0065] The storage unit 320 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 3201 and / or a cache storage unit 3202, and may further include a read-only memory unit (ROM) 3203.

[0066] The storage unit 320 may also include a program / utility 3204 having a set (at least one) program module 3205, such program module 3205 including but not limited to: an operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0067] Bus 330 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0068] Electronic device 300 can also communicate with one or more external devices 400 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable viewers to interact with electronic device 300, and / or with any device that enables electronic device 300 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 350. Furthermore, electronic device 300 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 360. Network adapter 360 can communicate with other modules of electronic device 300 via bus 330. It should be understood that, although... Figure 3 As not shown, other hardware and / or software modules may be used in conjunction with electronic device 300, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0069] Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described in this invention can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this invention can be embodied in the form of a software product, which can be stored in a computer-readable storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, or network device, etc.) to execute the method described above according to this invention. When the computer program is executed by a data processing device, it enables the computer-readable medium to implement the method described above, i.e.: as... Figure 1 The method shown.

[0070] Figure 4 This is a schematic diagram of a computer-readable medium provided for embodiments of this specification.

[0071] accomplish Figure 1 The computer program of the method shown can be stored on one or more computer-readable media. A computer-readable medium can be a readable signal medium or a readable storage medium. A readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0072] The computer-readable storage medium may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The readable storage medium may also be any readable medium other than a readable storage medium, capable of transmitting, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0073] Program code for performing the operations of this invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the audience's computing device, partially on the audience's device, as a standalone software package, partially on the audience's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the audience's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0074] In summary, the present invention can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that in practice, general-purpose data processing devices such as microprocessors or digital signal processors (DSPs) can be used to implement some or all of the functions of some or all of the components according to the embodiments of the present invention. The present invention can also be implemented as a device or apparatus program (e.g., a computer program and computer program product) for performing part or all of the methods described herein. Such programs implementing the present invention can be stored on a computer-readable medium or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0075] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the present invention is not inherently related to any specific computer, virtual device, or electronic device, and various general-purpose devices can also implement the present invention. The above descriptions are merely specific embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

[0076] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0077] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for optimizing multi-channel data transmission, characterized in that, include: Real-time acquisition of dynamic performance metrics sets for multiple transmission channels; Based on the dynamic performance index set, the comprehensive weight of each index is determined by an adaptive weight allocation model, and the real-time health score of each channel is calculated. The historical performance data of each channel is input into the time series prediction model to predict the predicted health score of each channel at future scheduling times. Based on the real-time health score and the predicted health score, a joint decision is made through a multi-objective decision function to select a target transmission channel; Based on the actual transmission results of the target transmission channel, the time-series prediction model and the adaptive weight allocation model are optimized through feedback.

2. The multi-channel data transmission optimization method as described in claim 1, characterized in that, The real-time acquisition of dynamic performance metric set includes: Based on a dynamically adjustable sliding time window, the instantaneous throughput, transmission success rate, and average response latency of each channel are collected. The channel stability index is calculated based on the fluctuation of the transmission success rate or the average response delay within the sliding time window. The size of the sliding time window is adaptively adjusted in reverse according to the mutation rate of the network state.

3. The multi-channel data transmission optimization method as described in claim 1, characterized in that, The dynamic performance index set includes at least the indices reflecting channel load, transmission reliability, and response time.

4. The multi-channel data transmission optimization method as described in claim 1, characterized in that, The determination of the comprehensive weights of each indicator through an adaptive weight allocation model includes: The information entropy weighting method is used to calculate the objective weight vector based on the data dispersion of each indicator across all channels; Based on the analytic hierarchy process (AHP), subjective weight vectors are determined according to pre-defined business rules. The fusion coefficient is dynamically calculated based on the signal-to-noise ratio of the historical dataset, and the objective weight vector and the subjective weight vector are weighted and fused based on the fusion coefficient to output the comprehensive weight.

5. The multi-channel data transmission optimization method as described in claim 1, characterized in that, The time-series prediction model is a pre-trained long short-term memory network model; The prediction of the health score of each channel at future scheduling time includes: taking the health score sequence in the historical performance data and the original value of the dynamic performance index as input features, and performing multivariate time series prediction through the long short-term memory network model; For newly launched channels, the similarity between their fixed attributes and existing channels is calculated, and the predicted value of the most similar channel is used as its initial predicted health score.

6. The multi-channel data transmission optimization method as described in claim 1, characterized in that, The step of selecting a target transmission channel based on the real-time health score and the predicted health score through a multi-objective decision function includes: Decision value = α * S c + β * S p - γ * C sel + δ * I stab Among them, S c For the real-time health score, S p For the predicted health score, C sel The overload protection factor is defined as the number of times the channel has been selected in the recent past. stab Let α, β, γ, and δ be the channel stability indices, and let α, β, γ, and δ be the balance parameters tuned using a multi-objective optimization algorithm.

7. The multi-channel data transmission optimization method as described in claim 1, characterized in that, The step of optimizing the time-series prediction model and the adaptive weight allocation model based on the actual transmission results of the target transmission channel includes: Establish a priority experience replay buffer to store transmission result samples, and assign higher sampling priority to samples that fail to make decisions or degrade in performance; High-priority samples are periodically extracted from the buffer to perform incremental learning and online fine-tuning on the time series prediction model; At fixed intervals, the adaptive weight allocation model is re-executed based on the recently collected set of dynamic performance indicators to update the comprehensive weights.

8. A multi-channel data transmission optimization device, characterized in that, include: The acquisition module is used to acquire dynamic performance indicator sets of multiple transmission channels in real time. The calculation module is used to determine the comprehensive weight of each indicator based on the dynamic performance indicator set through an adaptive weight allocation model, and to calculate the real-time health score of each channel. The prediction module is used to input the historical performance data of each channel into the time series prediction model to predict the predicted health score of each channel at future scheduling times. The decision module is used to select a target transmission channel by making a joint decision based on the real-time health score and the predicted health score through a multi-objective decision function. The optimization module is used to perform feedback optimization on the time-series prediction model and the adaptive weight allocation model based on the actual transmission results of the target transmission channel.

9. An electronic device, wherein, The electronic device includes: A processor; and a memory storing computer-executable instructions, which, when executed, cause the processor to perform the method as described in any one of claims 1-7.

10. A computer-readable storage medium, wherein, The computer-readable storage medium stores one or more programs that, when executed by a processor, implement the method of any one of claims 1-7.

Images