Network transmission path determination method and device, storage medium and electronic equipment

Abstract

The invention discloses a network transmission path determination method and device, a storage medium and electronic equipment, and relates to the field of artificial intelligence. The method comprises the steps that under the condition that an ith data transmission node in a network is not a target node, the fair sharing rate of a data link in the network at the moment t is determined, i is an integer larger than or equal to 1, the target node is the data transmission node through which flow in the network flows finally, and the moment t is any moment; initializing an ant colony according to a state transition rule; updating pheromones according to the fair sharing rate at the t moment and the length of the path passed by the ant colony; and determining a target transmission path from the ith data transmission node to the target node at the t moment according to the updated pheromone. According to the method and the device, the technical problem that the selection accuracy of the network transmission path is reduced due to incomplete reference elements when the network transmission path is selected by adopting a dynamic routing strategy in the prior art is solved.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence, and more specifically, to a method, apparatus, storage medium, and electronic device for determining a network transmission path. Background Technology

[0002] In the internet environment, data transmission generally needs to meet two conditions: first, to avoid the risk of eavesdropping and interference by attackers, thus protecting the security of information transmission; and second, to achieve efficient data transmission by adaptively adjusting latency network strategies based on the real-time network environment, load, and traffic rate to reduce traffic completion time. In recent years, low-latency network control strategies have become a hot topic of attention and development in the industry.

[0003] In ensuring efficient data transmission, typical data transmission technologies, such as congestion control, control the transmission rate of traffic and distribute idle buffers evenly among traffic processes, thus facilitating multi-threaded and multi-channel data transmission. While existing dynamic routing technologies can adapt to changes in the network environment and intelligently select transmission paths to some extent, their selection mechanisms largely rely on link bandwidth, latency, and the current network load. However, relying on such limited reference factors can easily lead to inaccurate path selection, resulting in low data transmission efficiency.

[0004] There is currently no effective solution to the above problems. Summary of the Invention

[0005] The main objective of this application is to provide a method, apparatus, storage medium, and electronic device for determining network transmission paths, so as to at least solve the technical problem in the prior art where the accuracy of network transmission path selection is reduced due to incomplete reference factors when using dynamic routing strategies to select network transmission paths.

[0006] To achieve the above objectives, according to one aspect of this application, a method for determining a network transmission path is provided, comprising: determining the fair sharing rate of the data link in the network at time t when the i-th data transmission node in the network is not the target node, wherein i is an integer greater than or equal to 1, the target node is the last data transmission node through which the traffic in the network flows, and time t is any time; initializing an ant colony according to a state transition rule, wherein the ant colony represents the search process of the network transmission path, and the state transition rule is used to dynamically update the selection of the network transmission path based on pheromone and path distance; updating the pheromone according to the fair sharing rate at time t and the path length already traversed by the ant colony; and determining the target transmission path from the i-th data transmission node to the target node at time t based on the updated pheromone.

[0007] Optionally, if the i-th data transmission node in the network is not the target node, the fair sharing rate of the data link in the network at time t is determined, including: detecting the capacity of the data link, where capacity represents the maximum transmission rate of the data link; detecting the average utilization of data packets entering the data link at time t, where average utilization represents the ratio of the total bandwidth to the capacity when all data packets enter the data link; detecting the average round-trip time of traffic traversing the data link at time t; detecting the average queue size of the data link at time t, where the average queue size represents the amount of data waiting to be sent in the data link; and determining the fair sharing rate of the data link in the network at time t based on the capacity, average utilization, average round-trip time, and average queue size.

[0008] Optionally, the fair sharing rate of the data link in the network at time t is determined based on capacity, average utilization, average round-trip time, and average queue size, including: detecting the fair sharing rate of the data link at time tT, where T is a preset fair sharing rate update period for the data link; and determining the fair sharing rate of the data link at time t based on capacity, average utilization, average round-trip time, average queue size, and the fair sharing rate of the data link at time tT.

[0009] Optionally, the process of determining the state transition rule includes: obtaining the pheromone concentration on the path from the first node to the second node in the network, wherein the pheromone concentration is proportional to the frequency of use of the path from the first node to the second node, and the first node and the second node are two different data transmission nodes in the network; using the reciprocal of the path distance from the first node to the second node as a heuristic value; determining the probability that the ant colony will choose to move from the first node to the second node based on the heuristic value and the pheromone concentration; and determining the state transition rule based on the probability that the ant colony will choose to move from the first node to the second node.

[0010] Optionally, determining the probability of the ant colony choosing to move from the first node to the second node based on the heuristic value and pheromone concentration includes: obtaining a first parameter, wherein the first parameter is used to balance the dependence of the heuristic value and pheromone concentration on the selection of network transmission paths; detecting the set of data transmission nodes that the ant colony can choose to move from the first node to the second node; and determining the probability of the ant colony choosing to move from the first node to the second node based on the first parameter, the set, the heuristic value, and the pheromone concentration.

[0011] Optionally, the pheromone is updated based on the fair sharing rate at time t and the path length already traversed by the ant colony, including: upon detecting that the ant colony has traversed the path from the first node to the second node, determining the incremental update value corresponding to the pheromone concentration based on the fair sharing rate at time t and the path length already traversed by the ant colony; wherein the first node and the second node are two different data transmission nodes in the network; and the pheromone is updated based on the incremental update value, the number of ants, and the pheromone decay factor, wherein the pheromone decay factor is used to simulate the rate at which the pheromone disappears over time.

[0012] Optionally, the method for determining the network transmission path further includes: if the ant colony does not pass through the path from the first node to the second node, determining the incremental update value corresponding to the pheromone concentration to be 0.

[0013] Optionally, determining the target transmission path from the i-th data transmission node to the target node at time t based on the updated pheromone includes: determining the target transmission path from the i-th data transmission node to the target node at time t based on the path distance function and the updated pheromone, wherein the path distance function is used to select the network transmission path between different data transmission nodes based on the time window and the load of the data link.

[0014] Optionally, before determining the target transmission path from the i-th data transmission node to the target node at time t based on the path distance function and the updated pheromone, the method further includes: detecting the file fragment size, where the file fragment size is the size of the data packets transmitted in the network; detecting the time window, where the time window represents the time range for data packets to arrive at the target node; detecting the load parameter, where the load parameter represents the load of the data link when the ant colony passes through the i-th data transmission node at time t; detecting the time parameter, where the time parameter represents the degree of matching between the time of data packets arriving at the target node according to the path selected by the ant colony and the time window when the ant colony passes through the i-th data transmission node at time t; and determining the path distance function based on the file fragment size, time window, load parameter, and time parameter.

[0015] Optionally, the target transmission path from the i-th data transmission node to the target node at time t is determined based on the path distance function and the updated pheromone. This includes: determining the target transmission path from the i-th data transmission node to the target node at time t based on random values, preset constant parameters, target random variables, updated pheromone, and the path distance function. Here, the random values ​​are values ​​randomly determined from the data range of 0 to 1, the preset constant parameters are constants greater than or equal to 0 and less than or equal to 1, and the target random variables are variables randomly selected according to the state transition rules.

[0016] Optionally, the data packets transmitted in the network include at least one of the following elements: the packet header; the next-hop routing information corresponding to the data packet; the message type corresponding to the data packet; the public key of the recipient of the data packet; the public key of the sender of the data packet; the identifier of the switch that processes the data packet; the length of the data queue in which the data packet is located; the temporary credential corresponding to the data packet; the sending time corresponding to the data packet; and the physical address corresponding to the data packet.

[0017] Optionally, the method further includes: after a data packet passes through the i-th data transmission node in the network, generating a header information in hash form corresponding to the data packet based on the content information of the data packet's structure and the public key of the i-th data transmission node.

[0018] Optionally, before updating the pheromone based on the fair sharing rate at time t and the path length already traversed by the ant colony, the method further includes: determining the instantaneous flow rate of the data link at each time step based on the data link capacity and the initial average flow rate of the data link.

[0019] To achieve the above objectives, according to another aspect of this application, a network transmission path determination apparatus is also provided, comprising: a first determining unit, which determines the fair sharing rate of the data link in the network at time t when the i-th data transmission node in the network is not the target node, wherein i is an integer greater than or equal to 1, the target node is the last data transmission node through which the traffic in the network flows, and time t is any time; a first processing unit, which initializes an ant colony according to a state transition rule, wherein the ant colony represents the search process of the network transmission path, and the state transition rule is used to dynamically update the selection of the network transmission path based on pheromone and path distance; a first updating unit, which updates the pheromone according to the fair sharing rate at time t and the path length already traversed by the ant colony; and a second determining unit, which determines the target transmission path from the i-th data transmission node to the target node at time t based on the updated pheromone.

[0020] According to another aspect of this application, a computer-readable storage medium is also provided, which includes a stored executable program, wherein, when the executable program is running, it controls the device where the computer-readable storage medium is located to execute the above-described method for determining the network transmission path.

[0021] According to another aspect of this application, an electronic device is also provided, comprising: a memory storing an executable program; and a processor for running the program, wherein the program executes the aforementioned method for determining a network transmission path during runtime.

[0022] According to another aspect of this application, a computer program product is also provided, including computer instructions that, when executed by a processor, implement the steps of the above-described method for determining a network transmission path.

[0023] In this application, firstly, when the i-th data transmission node in the network is not the target node, the fair sharing rate of the data link in the network at time t is determined, where i is an integer greater than or equal to 1, the target node is the last data transmission node through which the traffic in the network flows, and time t is any time. Then, the ant colony is initialized according to the state transition rule, where the ant colony represents the search process of the network transmission path. The state transition rule is used to dynamically update the selection of the network transmission path based on pheromone and path distance. Then, the pheromone is updated according to the fair sharing rate at time t and the path length already traversed by the ant colony. Finally, the target transmission path from the i-th data transmission node to the target node at time t is determined based on the updated pheromone. That is, by dynamically monitoring and optimizing the pheromone, the goal of quickly and accurately selecting a low-latency network transmission path is achieved under the condition of real-time network changes. This achieves the technical effect of efficient and real-time optimized low-latency data transmission, thereby solving the technical problem in the prior art where the accuracy of network transmission path selection is reduced due to incomplete reference factors when using dynamic routing strategies to select network transmission paths. Attached Figure Description

[0024] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0025] Figure 1 This is a flowchart of an optional method for determining a network transmission path according to an embodiment of this application;

[0026] Figure 2 This is a schematic diagram of an optional low-latency communication network according to an embodiment of this application;

[0027] Figure 3 This is a schematic diagram of an optional data transmission module according to an embodiment of this application;

[0028] Figure 4 This is a schematic diagram of an optional message management module according to an embodiment of this application;

[0029] Figure 5 This is a flowchart of an optional load-optimized low-latency network control strategy algorithm according to an embodiment of this application;

[0030] Figure 6 This is a schematic diagram of an optional network transmission path determination device according to an embodiment of this application. Detailed Implementation

[0031] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0032] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application 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 this application 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 apparatus 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 apparatus.

[0033] It should be noted that the information collected in this application (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) are information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of this data all comply with relevant laws, regulations, and standards, necessary confidentiality measures have been taken, and they do not violate public order and good morals. Corresponding access points are provided for users to choose to authorize or refuse. For example, interfaces are set up between this system and relevant users or organizations, providing users with corresponding access points to choose to agree to or refuse automated decision-making results; if the user chooses to refuse, the process proceeds to the expert decision-making stage.

[0034] It should be noted that an intelligent processing system can serve as the execution subject of the network transmission path determination method in the embodiments of this application. It is understood that the network transmission path determination method provided in the embodiments of this application can also be executed by other systems or devices, and the embodiments of this application do not specifically limit this.

[0035] According to an embodiment of this application, a method embodiment for determining a network transmission path is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0036] Figure 1 This is a flowchart of an optional network transmission path determination method according to an embodiment of this application, such as... Figure 1 As shown, the method includes the following steps:

[0037] Step S101: If the i-th data transmission node in the network is not the target node, determine the fair sharing rate of the data link in the network at time t.

[0038] In step S101, i is an integer greater than or equal to 1, the target node is the last data transmission node through which the traffic in the network flows, and time t is any time.

[0039] Optionally, the target node is the last data transmission node through which traffic in the network flows, i.e., the destination or end point of data transmission.

[0040] Optionally, fair shared rate is a key output of the RCP (Rate Control Protocol) algorithm, used to dynamically adjust the transmission rate of links to ensure that traffic in the network can be fairly and efficiently distributed to different links, avoiding overload and congestion.

[0041] It should be noted that the core of the RCP algorithm is to calculate the fair shared rate for each link. It dynamically adjusts the transmission rate of the link based on the average utilization of the link, the queue size, and the average round-trip time to achieve fair resource allocation and improve transmission efficiency.

[0042] Optionally, when the transmitting node is not the target node, the intelligent processing system determines the fair sharing rate of the data links in the network at time t.

[0043] Step S102: Initialize the ant colony according to the state transition rules.

[0044] In step S102, the ant colony represents the search process for network transmission paths, and the state transition rule is used to dynamically update the selection of network transmission paths based on pheromones and path distance.

[0045] Optionally, in Ant Colony Optimization (ACO), the state transition rule is a rule used to calculate the probability of each "ant" (i.e., the routing process) moving from one node to another. The state transition rule comprehensively considers pheromone concentration and distance heuristics, as well as a parameter to determine the next movement direction.

[0046] Optionally, the intelligent processing system sets the initial position and behavioral rules for each "ant" before the algorithm executes. The ant colony here represents the process of searching for network transmission paths, i.e., multiple independent path-choice entities simulated by the algorithm. The initialization of the ant colony is the first step in starting the algorithm, ensuring that each process has a fair opportunity to explore the network and find the optimal path.

[0047] Step S103: Update the pheromone based on the fair sharing rate at time t and the path length already traversed by the ant colony.

[0048] Optionally, the path length traversed by the ant colony refers to the path length or distance traversed by the ant colony from the source node to the current node during the search process.

[0049] Optionally, the intelligent processing system updates the pheromone concentration on the corresponding path based on the fair sharing rate of the link at time t and the path length already traversed by the ant colony. The pheromone update mechanism is the core of the ant colony algorithm; it simulates the process of ants leaving pheromones while searching for food in nature, guiding subsequent "ants" to choose better paths. The specific pheromone update rules consider the natural decay of pheromones and the update increment, ensuring the dynamics and adaptability of path selection.

[0050] Step S104: Determine the target transmission path from the i-th data transmission node to the target node at time t based on the updated pheromone.

[0051] Optionally, after the pheromone update described above, the pheromone concentration on each path reflects the historical usage and current transmission efficiency of that path. A higher pheromone concentration indicates a more popular path and potentially higher transmission efficiency.

[0052] Optionally, the intelligent processing system determines the optimal path (target transmission path) from the i-th data transmission node to the target node at time t based on the updated pheromone.

[0053] Optionally, Figure 2 This is a schematic diagram of an optional low-latency communication network according to an embodiment of this application, such as... Figure 2As shown in the diagram, the schematic includes: data transmission node 1, data transmission node 2, data transmission node 3, and user client 4. Data transmission node 1, data transmission node 2, and data transmission node 3 are all nodes participating in low-latency data transmission. These nodes may be located inside or outside the network address translation node (NAT), and are responsible for establishing secure channels with other nodes for secure data transmission. Data transmission node 1, data transmission node 2, and data transmission node 3 in this schematic are connected to form a low-latency data transmission network. Data transmission node 2 acts as the source node for data transmission, transmitting data to data transmission node 3 with low latency. Data transmission node 3 acts as the destination node for data transmission, receiving data from data transmission source node 2. User client 4 is responsible for sending and receiving transaction requests from users to access data transmission nodes, forwarding the transaction requests to the corresponding low-latency data transmission nodes, and simultaneously receiving low-latency data from the low-latency data transmission nodes and returning it to the user.

[0054] As can be seen from steps S101 to S104, in this application, firstly, when the i-th data transmission node in the network is not the target node, the fair sharing rate of the data link in the network at time t is determined, where i is an integer greater than or equal to 1, the target node is the last data transmission node through which the traffic in the network flows, and time t is any time. Then, the ant colony is initialized according to the state transition rule, where the ant colony represents the search process of the network transmission path, and the state transition rule is used to dynamically update the selection of the network transmission path based on pheromone and path distance. Then, the pheromone is updated according to the fair sharing rate at time t and the path length already traversed by the ant colony. Finally, the target transmission path from the i-th data transmission node to the target node at time t is determined based on the updated pheromone. That is, by dynamically monitoring and optimizing the pheromone, the goal of quickly and accurately selecting a low-latency network transmission path is achieved under the condition of real-time network changes, thereby realizing the technical effect of efficient and real-time optimized low-latency data transmission. This solves the technical problem in the prior art where the accuracy of network transmission path selection is reduced due to incomplete reference factors when using dynamic routing strategies to select network transmission paths.

[0055] In one optional embodiment, the intelligent processing system first detects the capacity of the data link, where capacity represents the maximum transmission rate of the data link. Next, it detects the average utilization of data packets entering the data link at time t, where average utilization represents the ratio of the total bandwidth to the capacity when all data packets enter the data link. Then, it detects the average round-trip time of traffic traversing the data link at time t. Afterward, it detects the average queue size of the data link at time t, where the average queue size represents the amount of data waiting to be sent in the data link. Finally, based on the capacity, average utilization, average round-trip time, and average queue size, it determines the fair sharing rate of the data link in the network at time t.

[0056] Optionally, the intelligent processing system first performs capacity detection on the data links in the network. Here, capacity specifically refers to the maximum transmission rate of the data link, which is a fundamental parameter for evaluating link performance and bandwidth allocation. Next, the system needs to detect the average utilization rate of data packets entering the data link at any time t. This measures the ratio of the total bandwidth to the link capacity at time t, reflecting the link's busyness. Then, the system also detects the average round-trip time of traffic traversing the data link at time t. This not only reflects the time it takes for data packets to travel from the sender to the receiver and back to the sender, but also indirectly reveals the health status of the link and the real-time performance of data transmission. After that, the system continues to detect the average queue size of the data link at time t. The average queue size is a quantitative indicator used to characterize the number of data packets waiting to be sent in the data link, which directly reflects the link's congestion status. Finally, the intelligent processing system integrates the above detection results, including link capacity, average data packet utilization rate at time t, average round-trip time of traffic, and average queue size of the link, to calculate and determine the fair sharing rate of the data links in the network at time t.

[0057] As described above, the intelligent processing system continuously monitors and analyzes the real-time performance parameters of the links, enabling it to dynamically adjust the fair sharing rate of the links and ensure the rational allocation of link resources. This mechanism not only considers the physical limitations of the links but also fully evaluates the instantaneous usage status of the links, including real-time changes in data traffic, congestion levels, and latency performance. This achieves intelligent optimization of the network transmission path, reducing data transmission latency and improving transmission efficiency and network response speed.

[0058] In one optional embodiment, the intelligent processing system first detects the fair sharing rate of the data link at time tT, where T is a preset fair sharing rate update period for the data link, and then determines the fair sharing rate of the data link at time t based on capacity, average utilization, average round-trip time, average queue size, and the fair sharing rate of the data link at time tT.

[0059] Optionally, the intelligent processing system detects the fair sharing rate of the data link at time tT, where T is a preset fair sharing rate update period for the data link, which is usually a fixed and configurable time interval. Then, based on the link capacity, the average utilization of data packets entering the link at time t, the average round-trip time of traffic traversing the link, the average queue size of the link, and the previously calculated fair sharing rate R(tT) at time tT, the system comprehensively determines the fair sharing rate R(t) of the data link at the current time t.

[0060] Optionally, the fair sharing rate R(tT) is calculated as shown in formula (1):

[0061]

[0062] Where t represents the current time, T is the preset fair sharing rate update period for the data link, C is the capacity, y(t) is the average data packet utilization at time t, d is the average round-trip time of traffic, q(t) is the average queue size of the link, and γ and δ are configurable parameters (used to adjust the influence of y(t) and q(t) on the fair sharing rate R(t). They are configurable weight parameters in the RCP algorithm, and the values ​​of γ and δ determine the relative importance of average utilization and queue size when calculating the new R(t).

[0063] As can be seen from the above, the intelligent processing system realizes dynamic monitoring of data link performance and continuous updates of fair sharing rate. By periodically detecting the historical performance of the link and combining it with real-time link status parameters, the system can intelligently adjust the transmission rate of the link at the current moment, ensuring fair and efficient use of link resources, thereby reducing data transmission latency and improving the overall transmission efficiency and response speed of the network.

[0064] In one optional embodiment, the intelligent processing system obtains the pheromone concentration along the path from a first node to a second node in the network, wherein the pheromone concentration is proportional to the frequency of use of the path from the first node to the second node, and the first node and the second node are two different data transmission nodes in the network. Then, the reciprocal of the path distance from the first node to the second node is used as a heuristic value. After that, the probability of the ant colony choosing to move from the first node to the second node is determined based on the heuristic value and the pheromone concentration. Finally, the state transition rule is determined based on the probability of the ant colony choosing to move from the first node to the second node.

[0065] Optionally, the intelligent processing system first obtains the pheromone concentration along the path from the first node to the second node in the network. Then, the system uses the path distance from the first node to the second node as the basis for calculating the heuristic value, specifically the reciprocal of the path distance. Next, based on the heuristic value and the pheromone concentration, the system determines the probability that the ant colony will choose to move from the first node to the second node. Finally, based on the probability that the ant colony will choose to move from the first node to the second node, the system determines the state transition rule.

[0066] As described above, the intelligent processing system achieves dynamic adaptability in path selection through the combined use of pheromone concentration and heuristic values. Pheromone concentration reflects the historical usage frequency of a path, helping to guide data flow to select paths that have been proven to be efficient and stable. Heuristic values, on the other hand, encourage the selection of shorter, theoretically lower-latency paths based on path distance. The integrated application of these two mechanisms ensures that, in a dynamically changing network environment, the system can quickly and accurately select the most suitable transmission path, significantly reducing data transmission latency and improving network transmission efficiency.

[0067] In one alternative embodiment, the intelligent processing system first obtains a first parameter, which is used to balance the dependence of the heuristic value and pheromone concentration when selecting a network transmission path. Then, it detects the set of data transmission nodes that the ant colony can choose to move from the first node to the second node. Finally, based on the first parameter, the set, the heuristic value, and the pheromone concentration, it determines the probability that the ant colony will choose to move from the first node to the second node.

[0068] Optionally, the intelligent processing system first obtains the first parameter, then detects the set of next-hop data transmission nodes that the ant colony can choose when moving from the current first node to the second node. This set includes all data transmission nodes that can theoretically reach the second node from the first node, providing the ant colony with a candidate range for path selection. Finally, the system determines the probability that the ant colony will choose to move from the first node to the second node based on the first parameter, the candidate node set, the heuristic value, and the pheromone concentration.

[0069] Optionally, the above probability p k The calculation method for (a,b) is shown in formula (2):

[0070]

[0071] Among them, J k(r) is the set of data transmission nodes (candidate node set) that ant colony k (from a to b) can choose from. β is the first parameter, τ is the pheromone concentration, τ(a,b) represents the pheromone concentration on the path from a to b, μ(a,b) represents the heuristic value of the path from a to b (μ = 1 / δ(a,b) represents the reciprocal of the path distance δ(a,b) between a and b), and a and b represent the first node and the second node, respectively. Usually, β>0. The variable s represents the next node that ant colony k may choose from the current node a. This represents the weighted sum of pheromone heuristic values ​​from node a to all possible next nodes b.

[0072] Optionally, set J k (r) contains all candidate nodes that ant colony k can move from node a in the current iteration. In the ant colony algorithm, each ant colony can only choose from its current set of candidate nodes when selecting the next node. Therefore, the conditional statement (if s∈J) k The purpose of (r) is to ensure that only nodes in the candidate node set have their probabilities calculated; that is, only the probability value of a valid next-hop node is calculated. If s does exist in the set, it means that node b is a valid choice for ant colony k to start from node a, then the probability p k (a,b) will be calculated according to the formula. If s is not in the set, it means that node b is not a valid choice for ant colony k to start from node a. Therefore, the probability value of node b will be set to 0, that is, ant colony k will not choose to move to node b.

[0073] As can be seen from the above, the intelligent processing system determines the probability of the ant colony choosing to move from the first node to the second node by comprehensively considering the first parameter, the candidate node set, the heuristic value, and the pheromone concentration. This achieves intelligent and adaptive path selection, effectively reduces data transmission latency, and improves network transmission efficiency.

[0074] In one optional embodiment, when the intelligent processing system detects that the ant colony has traversed the path from the first node to the second node, it determines the incremental update value corresponding to the pheromone concentration based on the fair sharing rate at time t and the length of the path already traversed by the ant colony. Here, the first node and the second node are two different data transmission nodes in the network. Then, the pheromone is updated based on the incremental update value, the number of ants, and the pheromone decay factor, where the pheromone decay factor is used to simulate the rate at which the pheromone disappears over time.

[0075] Optionally, the intelligent processing system first monitors the dynamics of data transmission in the network, especially detecting whether the ant colony has traversed the path from the first node to the second node. Based on the fair sharing rate at time t and the length of the path already traversed by the ant colony, the system determines the incremental update value corresponding to the pheromone concentration. Subsequently, the system updates the path pheromone concentration based on the calculated incremental update value, the total number of ant colonies in the current network, and the pheromone decay factor.

[0076] Optionally, the incremental update value Δτ corresponding to the pheromone concentration k The calculation method for (a,b) is shown in formula (3):

[0077]

[0078] Where R(t) is the fair sharing rate, L k Let be the length of the path traversed by ant colony k.

[0079] Optionally, the above formula (3) means that if (a,b)∈Routes for every k holds true, that is, the ant colony k has indeed traversed the path from node a to node b in the current search process, then Δτ k (a, b) will be set to Otherwise, Δτ k (a,b) will be set to 0.

[0080] Optionally, the pheromone update rule τ(a,b) is as shown in formula (4):

[0081]

[0082] Where 0<α<1 represents the pheromone decay factor, and m represents the ant colony size.

[0083] Optionally, Equation (4) implies that the update of pheromone concentration includes both the decay of pheromones (achieved through ((1-α).τ(a,b)) and the incremental update of pheromone concentration for all ant colonies k that have traversed the path, based on their path selection (through (Partially implemented). The dynamic adjustment of pheromone concentration allows more efficient paths to have higher pheromone concentrations, thus being prioritized in future path selection and contributing to efficient data transmission in the network.

[0084] As can be seen from the above, the intelligent processing system dynamically updates the pheromone concentration of the already traversed path, thereby achieving adaptive optimization of the network transmission path.

[0085] In one alternative embodiment, the intelligent processing system determines that the incremental update value corresponding to the pheromone concentration is 0 when it detects that the ant colony has not traversed the path from the first node to the second node.

[0086] Alternatively, as shown in formula (3), if the condition if(a,b)∈Routes for every k does not hold, i.e., ant colony k has not used the path from node a to node b, then Δτ k (a,b) will be set to 0.

[0087] As described above, the intelligent processing system sets the incremental update value of pheromone concentration on network paths not used by the ant colony to 0, thus achieving precise guidance and optimization of network transmission paths. This mechanism ensures that the algorithm can dynamically adjust the pheromone concentration based on actual network traffic and path usage, guiding data flows to select paths that have been verified to be efficient and low-latency, without being misled by paths that are not actually used. Therefore, the intelligent processing system can more accurately reflect the real-time state of the network, improve the intelligence and adaptability of path selection, effectively reduce data transmission latency, and improve network transmission efficiency.

[0088] In one alternative embodiment, the intelligent processing system determines the target transmission path from the i-th data transmission node to the target node at time t based on the path distance function and the updated pheromone, wherein the path distance function is used to select the network transmission path between different data transmission nodes based on the time window and the load of the data link.

[0089] Optionally, the intelligent processing system comprehensively utilizes the path distance function and the updated pheromone concentration to determine the target transmission path from the i-th data transmission node to the target node at time t. The core of this mechanism lies in the fact that it not only considers historical path selection preferences (pheromone concentration) but also combines the real-time characteristics of the current network environment (link load and time window) to achieve more intelligent and dynamic path selection.

[0090] As described above, the intelligent processing system effectively optimizes the efficiency and real-time performance of network data transmission by combining the path distance function and the updated pheromone concentration to determine the target transmission path. The introduction of the path distance function allows the algorithm to dynamically adjust the selection of the data transmission path based on the time window and the actual load of the data link, avoiding transmission delays caused by link overload or time window mismatch. Simultaneously, the pheromone concentration update mechanism ensures that the path selection reflects historical path selection preferences, guiding data to paths that have been verified as efficient and low-latency. This comprehensive mechanism significantly improves the accuracy and low-latency characteristics of data transmission.

[0091] In one optional embodiment, the intelligent processing system detects the file fragment size, where the file fragment size is the size of the data packets transmitted in the network; detects the time window, where the time window represents the time range for data packets to arrive at the target node; detects the load parameter, where the load parameter represents the load of the data link when the ant colony passes through the i-th data transmission node at time t; and detects the time parameter, where the time parameter represents the degree of matching between the time of data packets arriving at the target node according to the path selected by the ant colony and the time window when the ant colony passes through the i-th data transmission node at time t. Finally, the path distance function is determined based on the file fragment size, time window, load parameter, and time parameter.

[0092] Optionally, the intelligent processing system first detects the file fragment size (referring to the size of data packets transmitted in the network), then detects the time window, which defines the earliest and latest time for data packets to arrive at the target node. Next, it detects the load parameter, which is the link load when ant colony k passes through the j-th data transmission node at time t. Then, it detects the time parameter, which reflects the degree of matching between the time when ant colony k passes through the j-th data transmission node at time t and the time window. Finally, based on the file fragment size, time window, load parameter, and time parameter, the system determines the path distance function.

[0093] Optionally, the load parameter quantifies the link load when ant colony k traverses path j at time t. The value of the load parameter is typically related to metrics such as the current utilization of the link and the packet queue length, and it is used to evaluate the transmission efficiency and congestion level of the path. The time parameter reflects the degree of conformity between the path selection and the time window when ant colony k traverses path j at time t. Its calculation may be based on a comparison between the path transmission time and the time window. If the path transmission time is close to or within the center value of the time window, its value is higher; otherwise, it is lower, indicating a time mismatch.

[0094] Optionally, the path distance function As shown in formula (5):

[0095]

[0096] Where size represents the file slice size, w represents the time window, and δ j (k,t) represents the load parameters, ε j (k,t) represents the time parameter.

[0097] As can be seen from the above, the intelligent processing system can more accurately determine the path distance function and guide the selection of data transmission paths by monitoring and analyzing key parameters transmitted in the network (file fragment size, time window, load parameters, and time parameters).

[0098] In an optional embodiment, the intelligent processing system determines the target transmission path from the i-th data transmission node to the target node at time t according to a random value, a preset constant parameter, a target random variable, the updated pheromone, and a path distance function. The random value is a value randomly determined from the data interval of 0 to 1, the preset constant parameter is a constant greater than or equal to 0 and less than or equal to 1, and the target random variable is a variable randomly selected following a state transition rule.

[0099] Optionally, the intelligent processing system adopts a mechanism for determining the data transmission path based on a random value, a preset constant parameter, a target random variable, the updated pheromone concentration, and an optimized path distance function.

[0100] Optionally, the calculation method of the optimal path (target transmission path) s is shown in formula (6):

[0101]

[0102] where q is a random value distributed in [0...1], q0 (0 ≤ q0 ≤ 1) is a constant parameter (preset constant parameter), S is a randomly selected variable (target random variable) following a state transition rule, and τ(a,u) is the updated pheromone.

[0103] Optionally, in formula (6) it is to find all possible next nodes b from node a to the node set J k (a), and which node has the highest comprehensive evaluation value. The comprehensive evaluation value consists of two parts: the pheromone concentration (τ(a,u)) and the β power of the path heuristic value (μ(a,u)). The pheromone concentration reflects the frequency of past data packets or ant colonies using this path, and the heuristic value is usually related to the reciprocal of the path distance, indicating the relative attractiveness of the path. β is a parameter controlling the relative importance of the pheromone and the heuristic value. When β is larger, the heuristic value plays a more important role; when β is smaller, the influence of the pheromone concentration is more significant. If the random number q is less than the preset threshold q0, then the ant colony k will select the node b with the highest comprehensive evaluation value as the next node to move to. If the condition (q < q0) is not satisfied, that is, q is greater than or equal to q0, then the ant colony k will randomly select a node from all possible next nodes (J k (a)) as the target node S.

[0104] As described above, the intelligent processing system determines the target transmission path by comprehensively utilizing random numerical values, preset constant parameters, target random variables, updated pheromone concentrations, and optimized path distance functions, significantly improving the efficiency and real-time performance of network data transmission. This mechanism ensures the flexibility and intelligence of path selection, dynamically adjusting the path according to real-time changes in the network environment and reducing data transmission latency.

[0105] In one optional embodiment, the data packet transmitted in the network includes at least one of the following elements: the packet header; the next-hop routing information corresponding to the data packet; the message type corresponding to the data packet; the public key of the recipient of the data packet; the public key of the sender of the data packet; the identifier of the switch processing the data packet; the length of the data queue in which the data packet is located; the temporary credential corresponding to the data packet; the sending time corresponding to the data packet; and the physical address corresponding to the data packet.

[0106] Optionally, data packets transmitted in the network include at least one of the following elements: Packet header: The packet header is the front part of the data packet and contains key information for packet identification and routing. It ensures that the data packet is correctly transmitted to the target node in the network; Next-hop routing information: Information indicating the next node to which the data packet should be sent after the current node. This information helps the data packet to be transmitted efficiently along the optimal path, reducing network transmission latency; Message type: Defines the nature and purpose of the data packet. The message type ensures that the receiving end can correctly parse and process the data packet; Receiver's public key: The data packet contains the receiver's public key, which is the identity identifier of the receiver in encrypted communication. It is used for decrypting the data packet and verifying the receiver's identity, ensuring the security of data transmission; Sender's public key: Similarly, the data packet also carries the sender's public key, which plays a key role in the encryption process of the data packet and verifies the sender's identity, strengthening the trustworthiness of data transmission; Identification of the switch processing the data packet: Identifies the switch processing the data packet, which helps in tracking... The system manages the transmission path of data packets in the network, ensuring the transparency and reliability of data transmission; the length of the data queue containing the data packet: provides information on the length of the current node's processing queue, reflecting the degree of congestion in the network, helping the intelligent processing system dynamically adjust transmission strategies and optimize network performance; the temporary credential corresponding to the data packet: used for one-time verification of the data packet, ensuring the uniqueness and security of each data packet during transmission and preventing replay attacks; the sending time corresponding to the data packet: records the sending time of the data packet, which is crucial for monitoring network latency and adjusting routing strategies, helping the intelligent processing system to perform real-time analysis and optimization of network status; the physical address corresponding to the data packet: identifies the specific physical address information of the data packet in the network layer, used for the correct transmission and routing selection of the data packet in the network layer, ensuring that the data packet arrives at its destination accurately.

[0107] Optionally, Table 1 is an example of an optional message format according to an embodiment of this application. As shown in Table 1, the IP header represents the data packet header, Next hop represents the next-hop routing information; type represents the message type, TYPE=0x1 represents a sent message, TYPE=0x2 represents a received message, etc.; reserved represents the receiver's public key; sender represents the sender's public key; SwitchID represents the switch ID; QueueSize represents the queue length; ephemeral represents a temporary credential; timestamp represents the sending timestamp; mac1 represents physical address 1; mac2 represents physical address 2; static represents static information. In this table, bytes refers to the basic unit of data storage or transmission, i.e., bytes. For example, in the given table, mac1 (16 bytes) and mac2 (16 bytes) represent the physical address (MAC address) field, and each MAC address occupies 16 bytes of storage space.

[0108] Table 1

[0109]

[0110] As described above, data packets are designed as comprehensive information carriers containing multiple key elements, aiming to support secure and efficient data transmission under low-latency network control strategies. Through a carefully designed data packet structure, the intelligent processing system can monitor network status in real time and dynamically adjust transmission strategies to ensure that data packets are transmitted quickly to the target node along the optimal path.

[0111] In one optional embodiment, after a data packet passes through the i-th data transmission node in the network, the intelligent processing system generates a header information in hash form corresponding to the data packet based on the content information of the data packet's structure and the public key of the i-th data transmission node.

[0112] Optionally, to ensure the integrity and security of data packets during network transmission, the intelligent processing system employs a mechanism for generating hash-format header information. The intelligent processing system first parses the structure content information of the data packet, including all key fields. Then, it obtains the public key of the i-th data transmission node. This public key serves as the identity identifier of the data transmission node and is used for encryption and verification in the subsequent hash header information generation process. Finally, using the parsed data packet structure content information and the obtained public key of the i-th data transmission node, the intelligent processing system generates the hash-format header information corresponding to the data packet through a hash algorithm.

[0113] Alternatively, the hash-form header information can be generated as shown in formula (7):

[0114] H i=Hash(Hash(Construct)||PK(i)) (7)

[0115] Where Hash represents the SHA-256 hash algorithm (Secure Hash Algorithm 256-bit), Construct represents the content information of the structure, PK(i) represents the public key of data transmission node i, and || represents the byte sequence concatenation operator.

[0116] Optionally, Figure 3 This is a schematic diagram of an optional data transmission module according to an embodiment of this application, such as... Figure 3 As shown, the system includes: a communication module 31, a traffic acquisition module 32, a secure computing module 33, a message processing module 34, and a routing management module 35. Specifically, the communication module 31 serves as the entry point for the data transmission node, enabling the sending and receiving of data messages for the recommendation system; the traffic acquisition module 32 is responsible for collecting traffic data for the data transmission node, managing network traffic, and tracking, collecting, and recording data transmission traffic; the secure computing module 33 is responsible for encrypting and decrypting the generated data messages using cryptographic algorithms; the message processing module 34 is responsible for parsing and splitting user data, forming data vectors, and assembling user data messages, with the message format shown in Table 1; and the routing management module 35 is responsible for managing the routing of data transmission messages, including saving, deleting, and adding routing information. The execution process includes two phases: initialization and dynamic pheromone updating.

[0117] Optionally, Figure 4 This is a schematic diagram of an optional message management module according to an embodiment of this application, such as... Figure 4 As shown in the diagram, the schematic includes: a communication module 41, a security processing module 42, a message assembly module 43, and a key storage module 44. The communication module 41 is responsible for data transmission and interaction, completing general data transmission and reception, including broadcast message information, message transmission and reception control, and network status information collection. The security processing module 42 is responsible for encrypting and decrypting the data messages sent and received by the communication module 41. The message assembly module 43 is responsible for assembling messages based on the collected network status information, generating uniquely identified data messages, and assembling them into transaction messages using parameters, as shown in Table 1. The key storage module 44 is responsible for storing the key jointly generated by the data transmission nodes in a trusted space.

[0118] As can be seen from the above, after the data packet passes through the i-th data transmission node, the intelligent processing system generates a hash-format header based on the data packet's structure content information and the node's public key, significantly enhancing the security and integrity verification capabilities of the data packet in the network.

[0119] In one alternative embodiment, the intelligent processing system determines the instantaneous flow rate of the data link at each moment based on the data link capacity and the initial average flow rate of the data link.

[0120] Optionally, the intelligent processing system first obtains the capacity of the data link, which is usually the maximum transmission rate of the link, reflecting the upper limit of the physical transmission capacity of the link. Then, it obtains the initial average flow rate of the data link, which reflects the average transmission rate of the link during the algorithm initialization phase. Obtaining the initial average flow rate helps the system understand the initial state of the link and provides a reference point for dynamically adjusting the flow rate. Finally, it obtains the instantaneous flow rate of the data link at each moment.

[0121] Optionally, the instantaneous flow velocity d i The calculation form of (t) is shown in formula (8):

[0122]

[0123] Where, d i (t) represents the instantaneous flow rate of link i at time t, d0 represents the average flow rate (average transmission rate, i.e. the initial average flow rate mentioned above), and C represents the capacity of the data link.

[0124] Optionally, the intelligent processing system incorporates a load-optimized low-latency network control strategy algorithm that combines rate control protocols and ant colony optimization. This algorithm aims to dynamically adjust data transmission paths within the network to achieve low latency and load balancing, while considering time window constraints to ensure efficient and timely data transmission. The core steps of the algorithm are as follows:

[0125] Phase 1: Initialization

[0126] Step 1: Assume there are m concurrent processes, and divide the n data packets of the data asset into m equal parts;

[0127] Step 2: Let the value of the pheromone τ(a,b) be a constant c, and initialize it as τ(a,b)=c, where a and b represent the source node and the destination node, respectively;

[0128] Step 3: Initialize the pheromone gain Δτ(a,b) k =0.

[0129] Step 4: Initialize C as the link capacity, α, β, γ and δ as constants, and d0 (representing the average flow rate), calculated as shown in formula (8);

[0130] Phase Two: Low-Latency Network Control Routing Strategy Algorithm

[0131] Input: Number of concurrent processes M, number of data asset partitions N;

[0132] Output: Shortest low-latency network control routing policy;

[0133] The algorithm steps are as follows:

[0134] Step 1: Collect traffic data. The traffic collection module periodically collects information such as switch ID, queue size, link utilization, and average shared link rate, calculates d0, and updates the corresponding variables in local memory. For example, (PUSH[SwitchID]; PUSH[QueueSize]; PUSH[LinkUtilization]; PUSH[Average Shared Rate]).

[0135] Step 2: Initialize the dynamic update routing algorithm parameters. Construct the 1-MTSP parameter set, initialize the pheromone matrix PM, and initialize the solution s. k Let Shortest be the optimal path in each iteration;

[0136] Step 3: Initialize ant colony routing information and calculate heuristic information for each node;

[0137] Step 4: If the number of iterations is less than N max Then the following loop processing will be performed:

[0138] Step 4: For each process k≤m, perform the following steps:

[0139] Step 4.1: For each node i≤n, perform the following steps:

[0140] Step 4.1.1: Perform the following calculation steps of the flow rate control protocol to calculate the fair shared rate for each link (as in formula (1));

[0141] Step 4.1.2: Execute the following state transition function to calculate the pheromone from the ant colony to each node (as shown in formula (2));

[0142] Step 4.1.2.1: Update pheromone τ(a,b). The pheromone parameters are updated iteratively. The basic idea is that the concentration of pheromone is proportional to the fair sharing rate. The specific method for updating pheromone is as follows: Based on the path distance μ and the fair sharing rate R(t) of the link, calculate the pheromone concentration and continuously update the pheromone τ. The pheromone update rules are as shown in formulas (3)-(4).

[0143] Step 4.1.2.2: If a node satisfies the constraints, add that node to the solution s. k ;

[0144] Step 4.1.2.3: Obtain the file fragment size (size) (assuming all file fragment sizes are the same), and the time window w, where w is a time range [e i ,l i ], e i Indicates the earliest arrival time, l i This represents the latest arrival time (stay time is negligible). The path distance function μ for optimizing the pheromone transfer matrix is ​​then adjusted as follows: Formally represented as formula (5);

[0145] Step 4.1.3: If a node does not meet the constraints, start searching for the next node;

[0146] Step 5: For each process k≤m, perform the following steps:

[0147] Step 5.1: Calculate the length of each path and update the shortest path (shortest);

[0148] Step 5.1.1: For each node i≤n, perform the following steps to update the pheromone function:

[0149] Step 5.1.1.2: Update the pheromone matrix PM;

[0150] Step 5.1.1.3: Set the unupdated paths to the worst-case scenario;

[0151] Step 6: Output the best routing information. The optimal route selection is to select the best path s based on the pheromone concentration, as shown in formula (6).

[0152] As described above, the intelligent processing system dynamically adjusts the instantaneous flow rate of the data link at each moment based on the data link capacity and the initial average flow rate. This mechanism effectively optimizes network traffic allocation and scheduling, reduces data transmission latency, and improves data transmission efficiency and network throughput.

[0153] In one alternative embodiment, Figure 5 This is a flowchart of an optional load-optimized low-latency network control strategy algorithm according to an embodiment of this application, such as... Figure 5 As shown, step S501: Initialize security parameters, ant colony parameters, generate public and private keys, such as the initialization parameters of the elliptic curve algorithm X25519 used in this example; execute the GenKey() function, for each data transmission node i (i∈[1,n]), iteratively generate the public key pk(i) and private key sk(i) of data transmission node i, and at the same time, upload pk(i) to the blockchain for evidence storage; in form as shown in formula (9):

[0154] (pk(i),sk(i))=genkey(1k (9)

[0155] Among them, 1 k It represents a k-bit binary number where all bits are 1.

[0156] Step S502: For each process or ant colony k (k∈[1,n]), perform the following processing in a loop;

[0157] Step S503: For all nodes i (i∈[1,n]), if i is not the target node, execute the following loop;

[0158] Step S504: Perform the following calculation steps of the flow rate control protocol to calculate the fair shared rate R(t) for each link (Formula (1));

[0159] Step S505: Initialize the path search process (ant colony), calculate the state transition rules, and define the state transition rules as shown in formula (2);

[0160] Step S506: Update the pheromone τ(a,b) according to the instantaneous flow velocity, and cyclically update the pheromone parameters. The specific method for updating the pheromone is as follows: calculate the pheromone concentration based on the path distance μ and the fair sharing rate R(t) of the link, and continuously update the pheromone τ. The pheromone update rules are shown in formulas (3)-(4).

[0161] Step S507: If the currently accessed node does not exist in the set of accessed nodes, then perform the following steps;

[0162] Step S508: Add the currently visited node I to the set of visited nodes;

[0163] Step S509: Update pheromone parameters and other information based on the time window and load conditions. Obtain the file fragment size (size) (assuming all file fragment sizes are the same), and the time window w, where w is a time range [e i ,l i ], e i Indicates the earliest arrival time, l i This represents the latest arrival time (stay time is negligible). The path distance function μ for optimizing the pheromone transfer matrix is ​​then adjusted as follows: As shown in formula (5);

[0164] Step S510: For each ant colony process k (k∈[1,n]), perform the following processing;

[0165] Step S511: Update the pheromone τ(a,b) based on the instantaneous flow velocity, and cyclically update the pheromone parameters. The specific method for updating the pheromone is as follows: calculate the pheromone concentration based on the path distance μ and the fair sharing rate R(t) of the link, and continuously update the pheromone τ.

[0166] Step S512: Update the dynamic routing table. Execute the optimized path selection function to select the optimal path. The operation is as follows: Select the best path s based on the pheromone concentration, as shown in formula (6);

[0167] Step S513: Complete the routing table update and begin multi-party data transmission.

[0168] This application also provides a network transmission path determination device. It should be noted that the network transmission path determination device of this application can be used to execute the network transmission path determination method provided in this application. The network transmission path determination device provided in this application will be described below.

[0169] According to an embodiment of this application, an apparatus for determining the network transmission path described above is also provided. Figure 6 This is a schematic diagram of an optional network transmission path determination device according to an embodiment of this application, as shown below. Figure 6 As shown, the device includes: a first determining unit, a first processing unit, a first updating unit, and a second determining unit.

[0170] Optionally, the first determining unit is used to determine the fair sharing rate of the data link in the network at time t when the i-th data transmission node in the network is not the target node, where i is an integer greater than or equal to 1, the target node is the last data transmission node through which the traffic in the network flows, and time t is any time; the first processing unit is used to initialize the ant colony according to the state transition rule, where the ant colony represents the search process of the network transmission path, and the state transition rule is used to dynamically update the selection of the network transmission path according to the pheromone and the path distance; the first updating unit is used to update the pheromone according to the fair sharing rate at time t and the path length already traversed by the ant colony; the second determining unit is used to determine the target transmission path from the i-th data transmission node to the target node at time t according to the updated pheromone.

[0171] Optionally, the first determining unit includes: a first detection subunit, a second detection subunit, a third detection subunit, a fourth detection subunit, and a first determining subunit. The first detection subunit is used to detect the capacity of the data link, where capacity represents the maximum transmission rate of the data link; the second detection subunit is used to detect the average utilization of data packets entering the data link at time t, where average utilization represents the ratio of the total bandwidth to the capacity when all data packets enter the data link; the third detection subunit is used to detect the average round-trip time of traffic traversing the data link at time t; the fourth detection subunit is used to detect the average queue size of the data link at time t, where the average queue size represents the amount of data waiting to be sent in the data link; and the first determining subunit is used to determine the fair sharing rate of the data link in the network at time t based on the capacity, average utilization, average round-trip time, and average queue size.

[0172] Optionally, the first determining subunit includes: a first detection module and a first determining module. The first detection module is used to detect the fair sharing rate of the data link at time tT, where T is a preset fair sharing rate update period for the data link; the first determining module is used to determine the fair sharing rate of the data link at time t based on capacity, average utilization, average round-trip time, average queue size, and the fair sharing rate of the data link at time tT.

[0173] Optionally, the first processing unit includes: a first acquisition subunit, a second determination subunit, a third determination subunit, and a fourth determination subunit. The first acquisition subunit is used to acquire the pheromone concentration along the path from a first node to a second node in the network, wherein the pheromone concentration is proportional to the frequency of use of the path from the first node to the second node, and the first node and the second node are two different data transmission nodes in the network. The second determination subunit is used to use the reciprocal of the path distance from the first node to the second node as a heuristic value. The third determination subunit is used to determine the probability that the ant colony will choose to move from the first node to the second node based on the heuristic value and the pheromone concentration. The fourth determination subunit is used to determine the state transition rule based on the probability that the ant colony will choose to move from the first node to the second node.

[0174] Optionally, the third determining subunit includes: a first acquisition module, a second detection module, and a second determining module. The first acquisition module is used to acquire a first parameter, which is used to balance the dependence of the heuristic value and pheromone concentration when selecting a network transmission path. The second detection module is used to detect the set of data transmission nodes that the ant colony can choose to move from the first node to the second node. The second determining module is used to determine the probability that the ant colony will choose to move from the first node to the second node based on the first parameter, the set, the heuristic value, and the pheromone concentration.

[0175] Optionally, the first update unit includes: a fourth determining subunit and a first update subunit. The fourth determining subunit is used to determine the incremental update value corresponding to the pheromone concentration based on the fair sharing rate at time t and the length of the path already traversed by the ant colony after detecting that the ant colony has traversed the path from the first node to the second node; wherein the first node and the second node are two different data transmission nodes in the network; the first update subunit is used to update the pheromone based on the incremental update value, the number of ants, and the pheromone decay factor, wherein the pheromone decay factor is used to simulate the rate at which the pheromone disappears over time.

[0176] Optionally, the network transmission path determination device further includes: a third determination unit, used to determine the incremental update value corresponding to the pheromone concentration as 0 when it is detected that the ant colony has not traversed the path from the first node to the second node.

[0177] Optionally, the second determining unit includes: a fifth determining subunit, used to determine the target transmission path from the i-th data transmission node to the target node at time t based on the path distance function and the updated pheromone, wherein the path distance function is used to select the network transmission path between different data transmission nodes based on the time window and the load of the data link.

[0178] Optionally, the network transmission path determination device further includes: a first detection unit, a second detection unit, a third detection unit, a fourth detection unit, and a fourth determination unit. The first detection unit is used to detect the file fragment size, where the file fragment size is the size of the data packets transmitted in the network; the second detection unit is used to detect the time window, where the time window represents the time range within which data packets arrive at the target node; the third detection unit is used to detect the load parameter, where the load parameter represents the load of the data link when the ant colony passes through the i-th data transmission node at time t; the fourth detection unit is used to detect the time parameter, where the time parameter represents the degree of matching between the time of data packets arriving at the target node according to the path selected by the ant colony and the time window when the ant colony passes through the i-th data transmission node at time t; and the fourth determination unit is used to determine the path distance function based on the file fragment size, the time window, the load parameter, and the time parameter.

[0179] Optionally, the fifth determining subunit includes: a third determining module, used to determine the target transmission path from the i-th data transmission node to the target node at time t based on random values, preset constant parameters, target random variables, updated pheromones, and path distance functions, wherein the random values ​​are values ​​randomly determined from the data range of 0 to 1, the preset constant parameters are constants greater than or equal to 0 and less than or equal to 1, and the target random variables are variables randomly selected according to state transition rules.

[0180] Optionally, the data packets transmitted in the network include at least one of the following elements: the packet header; the next-hop routing information corresponding to the data packet; the message type corresponding to the data packet; the public key of the recipient of the data packet; the public key of the sender of the data packet; the identifier of the switch that processes the data packet; the length of the data queue in which the data packet is located; the temporary credential corresponding to the data packet; the sending time corresponding to the data packet; and the physical address corresponding to the data packet.

[0181] Optionally, the network transmission path determination device further includes: a first generation unit, configured to generate a hash-form header information corresponding to the data packet after the data packet passes through the i-th data transmission node, based on the content information of the data packet structure and the public key of the i-th data transmission node.

[0182] Optionally, the network transmission path determination device further includes: a fifth determination unit, used to determine the instantaneous flow rate of the data link at each moment based on the capacity of the data link and the initial average flow rate of the data link.

[0183] According to another aspect of this application, a computer-readable storage medium is also provided, which includes a stored executable program, wherein, when the executable program is running, it controls the device where the computer-readable storage medium is located to execute the above-described method for determining the network transmission path.

[0184] According to another aspect of this application, an electronic device is also provided, comprising: a memory storing an executable program; and a processor for running the program, wherein the program executes the aforementioned method for determining a network transmission path during runtime.

[0185] According to another aspect of this application, a computer program product is also provided, including computer instructions that, when executed by a processor, implement the steps of the above-described method for determining a network transmission path.

[0186] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0187] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0188] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0189] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0190] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0191] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0192] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for determining a network transmission path, characterized in that, include: If the i-th data transmission node in the network is not the target node, determine the fair sharing rate of the data link in the network at time t, where i is an integer greater than or equal to 1, the target node is the last data transmission node through which the traffic in the network flows, and time t is any time. The ant colony is initialized according to the state transition rule, wherein the ant colony represents the search process of the network transmission path, and the state transition rule is used to dynamically update the selection of the network transmission path based on pheromones and path distance. The pheromone is updated based on the fair sharing rate at time t and the length of the path already traversed by the ant colony; The target transmission path from the i-th data transmission node to the target node at time t is determined based on the updated pheromone.

2. The method for determining a network transmission path according to claim 1, characterized in that, When the i-th data transmission node in the network is not the target node, determining the fair sharing rate of the data link in the network at time t includes: The capacity of the data link is detected, wherein the capacity characterizes the maximum transmission rate of the data link; The average utilization of data packets entering the data link at time t is detected, wherein the average utilization represents the ratio of the total bandwidth to the capacity when all data packets enter the data link; Detect the average round-trip time of traffic traversing the data link at time t; The average queue size of the data link at time t is detected, wherein the average queue size is used to characterize the amount of data waiting to be sent in the data link; The fair sharing rate of the data links in the network at time t is determined based on the capacity, the average utilization, the average round-trip time, and the average queue size.

3. The method for determining a network transmission path according to claim 2, characterized in that, Determining the fair sharing rate of data links in the network at time t based on the capacity, average utilization, average round-trip time, and average queue size includes: The fair sharing rate of the data link at time tT is detected, where T is the preset fair sharing rate update period for the data link; The fair sharing rate of the data link at time t is determined based on the capacity, the average utilization, the average round-trip time, the average queue size, and the fair sharing rate of the data link at time tT.

4. The method for determining a network transmission path according to claim 1, characterized in that, The process of determining the state transition rules includes: The pheromone concentration along the path from the first node to the second node in the network is obtained, wherein the pheromone concentration is proportional to the frequency of use of the path from the first node to the second node, and the first node and the second node are two different data transmission nodes in the network. Use the reciprocal of the path distance from the first node to the second node as a heuristic value; The probability that the ant colony will choose to move from the first node to the second node is determined based on the heuristic value and the pheromone concentration. The state transition rule is determined based on the probability that the ant colony will choose to move from the first node to the second node.

5. The method for determining a network transmission path according to claim 4, characterized in that, Determining the probability that the ant colony will choose to move from the first node to the second node based on the heuristic value and the pheromone concentration includes: Obtain a first parameter, wherein the first parameter is used to balance the dependence on the heuristic value and the pheromone concentration when selecting the network transmission path; The set of data transmission nodes that the ant colony can choose to move from the first node to the second node is detected. Based on the first parameter, the set, the heuristic value, and the pheromone concentration, the probability that the ant colony will choose to move from the first node to the second node is determined.

6. The method for determining a network transmission path according to claim 1, characterized in that, The pheromone is updated based on the fair sharing rate at time t and the path length already traversed by the ant colony, including: Upon detecting that the ant colony has traversed the path from the first node to the second node, the incremental update value corresponding to the pheromone concentration is determined based on the fair sharing rate at time t and the length of the path already traversed by the ant colony; wherein, the first node and the second node are two different data transmission nodes in the network; The pheromone is updated based on the incremental update value, the number of ants, and the pheromone decay factor, wherein the pheromone decay factor is used to simulate the rate at which the pheromone disappears over time.

7. The method for determining a network transmission path according to claim 6, characterized in that, The method for determining the network transmission path also includes: If it is detected that the ant colony has not traversed the path from the first node to the second node, the incremental update value corresponding to the pheromone concentration is determined to be 0.

8. The method for determining a network transmission path according to claim 1, characterized in that, Determining the target transmission path from the i-th data transmission node to the target node at time t based on the updated pheromone includes: Based on the path distance function and the updated pheromone, the target transmission path from the i-th data transmission node to the target node at time t is determined, wherein the path distance function is used to select the network transmission path between different data transmission nodes based on the time window and the load of the data link.

9. The method for determining a network transmission path according to claim 8, characterized in that, Before determining the target transmission path from the i-th data transmission node to the target node at time t based on the path distance function and the updated pheromone, the method further includes: Detect file fragment size, wherein the file fragment size is the size of the data packets transmitted in the network; A detection time window, wherein the time window represents the time range within which the data packet arrives at the target node; Detect load parameters, wherein the load parameters characterize the load of the data link when the ant colony passes through the i-th data transmission node at time t; The detection time parameter represents the degree of matching between the time when the data packet arrives at the target node according to the path selected by the ant colony at time t, when the ant colony passes through the i-th data transmission node, and the time window. The path distance function is determined based on the file fragment size, the time window, the load parameter, and the time parameter.

10. The method for determining a network transmission path according to claim 8, characterized in that, Based on the path distance function and the updated pheromone, the target transmission path from the i-th data transmission node to the target node at time t is determined, including: Based on the random value, the preset constant parameter, the target random variable, the updated pheromone, and the path distance function, the target transmission path from the i-th data transmission node to the target node at time t is determined. The random value is a value randomly determined from the data range of 0 to 1, the preset constant parameter is a constant greater than or equal to 0 and less than or equal to 1, and the target random variable is a variable randomly selected according to the state transition rule.

11. The method for determining a network transmission path according to claim 1, characterized in that, The data packets transmitted in the network include at least one of the following elements: The header of the data packet; The next-hop routing information corresponding to the data packet; The message type corresponding to the data packet; The public key of the recipient of the data packet; the public key of the sender of the data packet; The identifier of the switch that processed the data packet; The length of the data queue containing the data packet; The temporary credential corresponding to the data packet; The sending time corresponding to the data packet; The physical address corresponding to the data packet.

12. The method for determining a network transmission path according to claim 1, characterized in that, The method further includes: After a data packet passes through the i-th data transmission node in the network, a hash-format header is generated based on the content information of the data packet's structure and the public key of the i-th data transmission node.

13. The method for determining a network transmission path according to claim 1, characterized in that, Before updating the pheromone based on the fair sharing rate at time t and the path length already traversed by the ant colony, the method further includes: The instantaneous flow rate of the data link at each moment is determined based on the capacity of the data link and the initial average flow rate of the data link.

14. A device for determining a network transmission path, characterized in that, include: The first determining unit determines the fair sharing rate of the data link in the network at time t when the i-th data transmission node in the network is not the target node, where i is an integer greater than or equal to 1, the target node is the last data transmission node through which the traffic in the network flows, and time t is any time. The first processing unit initializes the ant colony according to the state transition rules, wherein the ant colony represents the search process of the network transmission path, and the state transition rules are used to dynamically update the selection of the network transmission path based on pheromones and path distance. The first update unit updates the pheromone based on the fair sharing rate at time t and the path length already traversed by the ant colony; The second determining unit determines the target transmission path from the i-th data transmission node to the target node at time t based on the updated pheromone.

15. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored executable program, wherein, when the executable program is executed, it controls the device on which the computer-readable storage medium is located to perform the network transmission path determination method according to any one of claims 1 to 13.

16. An electronic device, characterized in that, include: Memory, which stores executable programs; A processor for running the program, wherein the program, when running, executes the method for determining a network transmission path as described in any one of claims 1 to 13.

17. A computer program product comprising computer instructions, characterized in that, When the computer instructions are executed by the processor, they implement the steps of the method for determining the network transmission path as described in any one of claims 1 to 13.

Images