A method of p2p telecommunication

Abstract

The application discloses a kind of p2p remote communication method, it is related to communication technical field, including, collection network environment data and communication data, and carry out pre-processing;The network quality of each path is predicted by inputting the network environment data after pre-processing into machine learning model;Based on network quality prediction result, analysis is carried out by intelligent scheduling algorithm, and the distribution strategy of each path selection is obtained;According to the distribution strategy of each path selection, communication data is split into multiple data blocks and proportionally distributed to each path for transmission;Based on the transmission of communication data, the receiving end and the sending end node exchange network state information and dynamically adjust the communication data distribution;The receiving end node recombines according to the data block transmitted from each path, and obtains complete communication data.The application collects and pre-processes network environment and communication data, ensures high-quality communication data input, and predicts the network quality of each path using a long short-term memory network model.

Description

Technical Field

[0001] This invention relates to the field of communication technology, and in particular to a method for peer-to-peer remote communication. Background Technology

[0002] With the continuous development of Internet technology and information communication networks, P2P communication has been widely used in video conferencing, file transfer, real-time communication and other fields. P2P communication faces many challenges in practical applications, especially in dynamic network environments. How to efficiently select transmission paths and ensure the reliability and real-time performance of data transmission has become an important factor affecting its performance.

[0003] Existing technologies also have shortcomings in bandwidth allocation. Most methods use a fixed-ratio allocation approach, lacking intelligent scheduling algorithms and dynamic adjustment mechanisms, thus failing to cope with bandwidth and latency fluctuations in complex network environments. Such methods often exhibit low adaptability when facing environments with significant changes in network quality, leading to increased transmission latency, higher packet loss rates, and impacting communication stability and efficiency. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a p2p remote communication method that solves the problems of static bandwidth allocation, lack of intelligent scheduling and dynamic adjustment in the prior art.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] In a first aspect, the present invention provides a method for p2p remote communication, which includes collecting network environment data and communication data, and performing preprocessing;

[0008] The preprocessed network environment data is input into the machine learning model to predict the network quality of each path;

[0009] Based on the network quality prediction results, an intelligent scheduling algorithm is used to analyze and obtain the allocation strategy for each path selection.

[0010] Based on the allocation strategy selected for each path, the communication data is split into multiple data blocks and proportionally allocated to each path for transmission;

[0011] Based on the transmission of communication data, the receiving and sending nodes exchange network status information to dynamically adjust the allocation of communication data.

[0012] The receiving node reassembles the data blocks transmitted from each path to obtain complete communication data.

[0013] As a preferred embodiment of the p2p remote communication method of the present invention, the collection of network environment data and communication data, and the preprocessing thereof, includes the following steps:

[0014] The collected network data includes bandwidth, latency, and packet loss rate, and the collected communication data includes files, video streams, and messages. All collected data undergoes noise reduction and standardization processing.

[0015] As a preferred embodiment of the p2p remote communication method described in this invention, the following steps are included: inputting preprocessed network environment data into a machine learning model to predict the network quality of each path.

[0016] Principal component analysis (PCA) is used to extract bandwidth, latency, and packet loss rate features from preprocessed network environment data. These features are then input into a Long Short-Term Memory (LSTM) network model to predict the network quality of each path. The expression is as follows:

[0017]

[0018] Among them, Q i (t) represents the predicted network quality value of the i-th path at time t, where x is the network quality prediction value. k (t) represents the value of the k-th network quality feature at time t, w k Let z(t) be the weight of the k-th network quality feature, z(t) be the sum of network quality features at time t, n be the number of paths, β be the adjustment parameter of the sum of network quality features, k be the network quality feature index, and f be the nonlinear activation function.

[0019] As a preferred embodiment of the p2p remote communication method described in this invention, the following steps are included: analyzing network quality prediction results using an intelligent scheduling algorithm to obtain the allocation strategy for each path selection.

[0020] The actual traffic and maximum available bandwidth for each path are extracted from network devices using the SNMP protocol to obtain bandwidth utilization.

[0021] The transmission delay can be obtained by measuring the round-trip time from the sender to the receiver on each path using the ICMP ping command.

[0022] Based on network quality predictions, bandwidth utilization, and transmission latency, an intelligent scheduling algorithm dynamically predicts data for each path, resulting in an allocation strategy for each path selection. The expression is as follows:

[0023]

[0024] Where F(p) is the fitness score of the assignment strategy p, and B i Let D be the bandwidth utilization of the i-th path.i The transmission delay of the i-th path, α i The importance coefficient of the i-th path, μ is the average value of all paths in the network quality prediction, γ is the sensitivity to changes in network quality, δ is the reference point for network quality, j1 is the power of the network quality prediction, o2 is the power of the bandwidth utilization, l3 is the power of the transmission delay, λ is the weighting coefficient of the transmission delay on the fitness score of the allocation strategy, A is the adjustment coefficient for controlling the sensitivity to changes in network quality, and p is the allocation strategy.

[0025] Based on the fitness score of the allocation strategy, all paths are sorted from high to low using the quicksort algorithm to obtain the allocation strategy for each path selection.

[0026] As a preferred embodiment of the p2p remote communication method described in this invention, splitting communication data into multiple data blocks according to the allocation strategy selected for each path includes the following steps:

[0027] Based on the allocation strategy for each path, the communication data to be transmitted is split according to the weight ratio of the path.

[0028] Communication data is broken down into small blocks along high-latency and low-bandwidth paths;

[0029] On low-latency and high-bandwidth paths, communication data is broken down into large data blocks.

[0030] As a preferred embodiment of the p2p remote communication method of the present invention, the method of distributing the split data blocks proportionally to various paths for transmission includes the following steps:

[0031] Based on the bandwidth utilization of each path, the bandwidth allocation ratio for each path is obtained;

[0032] The split data blocks are then distributed proportionally to each path based on the bandwidth allocation ratio of each path.

[0033] Data blocks on each path are transmitted using the specified transport protocol.

[0034] As a preferred embodiment of the p2p remote communication method described in this invention, the dynamic adjustment of communication data allocation by exchanging network status information between the receiving and sending nodes based on the transmission of communication data includes the following steps.

[0035] The sending and receiving ends exchange real-time network status information through a control channel;

[0036] The sending end encapsulates all network status information into data packets and sends them to the receiving end.

[0037] After receiving the network status information from the sender, the receiver decodes the network performance of each path, extracts bandwidth, latency, and packet loss rate data, and calculates the network health status of each path using the following expression:

[0038]

[0039] Among them, H i (t) represents the network health score of the i-th path at time t, B max D is the maximum bandwidth of all paths. max Let κ be the maximum delay across all paths, θ be the path bandwidth weighting coefficient, φ be the delay weighting coefficient, and P be the packet loss rate weighting coefficient. i (t) represents the packet loss rate at time t for the i-th path;

[0040] Based on the network health score, the receiving end will sort the paths to obtain the highest priority path and dynamically adjust the communication data.

[0041] As a preferred embodiment of the p2p remote communication method described in this invention, the receiving node reassembles the data blocks transmitted from each path to obtain complete communication data, including the following steps.

[0042] The sending end assigns a number to each data block, and the receiving end allocates an independent buffer area for each path;

[0043] The receiving end numbers the paths, groups multiple data blocks from different paths, and sorts the data blocks of each path according to the data block sequence number.

[0044] The receiving end reads data blocks one by one from the buffer according to the data block sequence number, and merges the read data blocks into complete communication data.

[0045] In a second aspect, the present invention provides a computer device including a memory and a processor, wherein the memory stores a computer program, wherein when the computer program is executed by the processor, it implements any step of the p2p remote communication method as described in the first aspect of the present invention.

[0046] Thirdly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the p2p remote communication method as described in the first aspect of the present invention.

[0047] The beneficial effects of this invention are as follows: By collecting and preprocessing network environment and communication data, high-quality communication data input is ensured. It utilizes a long short-term memory network model to predict the network quality of each path, achieving a forward-looking assessment of future network conditions. This optimizes path selection and resource allocation, improving transmission efficiency and user experience. By combining SNMP protocol and ICMP ping command to obtain real-time network status information, it calculates the fitness score of each path, dynamically adjusts path selection and resource allocation strategies, considers current network conditions, and can predict future trends, maximizing network resource utilization. Simultaneously, it improves data transmission speed and stability. The receiving node reassembles the data blocks transmitted from each path using an independent buffer area and data block sequence number sorting method, ensuring the integrity and reliability of communication data and guaranteeing an efficient and stable communication experience in complex and ever-changing network environments. Attached Figure Description

[0048] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 This is a flowchart of the p2p remote communication method in Example 1.

[0050] Figure 2 This is a flowchart illustrating the process of proportionally allocating data blocks to various paths for transmission in Example 1. Detailed Implementation

[0051] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0052] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0053] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0054] Example 1, referring to Figure 1and Figure 2 This is the first embodiment of the present invention, which provides a method for p2p remote communication, including the following steps:

[0055] S1. Collect network environment data and communication data, and perform preprocessing.

[0056] The collected network data includes bandwidth, latency, and packet loss rate, while the collected communication data includes files, video streams, and messages. All collected data undergoes noise reduction and standardization processing.

[0057] S1.1 goes a step further by collecting bandwidth utilization for each path via the SNMP protocol, collecting transmission latency for each path via the ICMP Ping command, collecting packet loss rate for each path by periodically sending data packets and monitoring packet loss, collecting transmitted file data, recording file size, type and transmission requirements, collecting file data to be transmitted, recording file size, type and transmission requirements, and collecting message data transmitted at the application layer, mainly including text and image information.

[0058] S1.2 goes a step further by using median filtering to denoise the collected network environment data. For bandwidth and latency data, outliers are removed to ensure that communication data accurately reflects long-term network trends. When denoising packet loss rate data, a sliding window averaging method is used to reduce the impact of instantaneous network condition changes on data prediction. All collected network environment and communication data are standardized using Z-score standardization. The standardization process ensures that different types of data (such as bandwidth, latency, and packet loss rate data) can be processed on the same scale, thereby improving the accuracy of machine learning model predictions.

[0059] S2. Input the preprocessed network environment data into the machine learning model to predict the network quality of each path.

[0060] S2.1. Using principal component analysis, bandwidth, latency, and packet loss rate features are extracted from the preprocessed network environment data and input into a long short-term memory network model to predict the network quality of each path. The expression is as follows:

[0061]

[0062] Among them, Q i (t) represents the predicted network quality value of the i-th path at time t, where x is the network quality prediction value. k (t) represents the value of the k-th network quality feature at time t, w kLet z(t) be the weight of the k-th network quality feature, z(t) be the sum of network quality features at time t, n be the number of paths, β be the adjustment parameter of the sum of network quality features, k be the network quality feature index, and f be the nonlinear activation function.

[0063] Furthermore, in the principal component analysis method, the covariance matrix is ​​used to measure the correlation between different bandwidth data, and the principal components of the bandwidth data are extracted through eigenvalue decomposition. Finally, the most representative principal components are selected to represent the bandwidth characteristics.

[0064] For delayed data, the PCA method is applied to identify the main trends of change in delayed data through the covariance matrix, and principal components are extracted through eigenvalue decomposition to retain the features that can explain the delay changes to the greatest extent.

[0065] The processing of packet loss rate data is similar to that of bandwidth and latency. First, the packet loss rate is denoised and standardized to make it comparable on the same scale. The PCA method is used to extract the most informative principal components from the covariance matrix. These principal components can effectively represent network packet loss behavior.

[0066] For each path at time t, it is necessary to determine the weights w of each feature. k The network quality characteristics are weighted and summed to form the final path.

[0067] To enhance the expressive power of the Long Short-Term Memory network model, the feature sum z(t) is processed through a nonlinear activation function f. This nonlinear activation function introduces a nonlinear relationship so that the network can better fit the complex network quality prediction task 1+exp(-β·z(t)).

[0068] S3. Based on the network quality prediction results, an intelligent scheduling algorithm is used to analyze and obtain the allocation strategy for each path selection.

[0069] S3.1 Use the SNMP protocol to extract the actual traffic and maximum available bandwidth of each path from the network device to obtain the bandwidth utilization rate.

[0070] Furthermore, the SNMP protocol is used to extract the actual traffic and maximum available bandwidth of each path from network devices (such as routers and switches) to obtain the bandwidth utilization of the path, providing a basis for subsequent path selection.

[0071] S3.2. Measure the round-trip time from the sender to the receiver on each path using the ICMP ping command to obtain the transmission delay.

[0072] Furthermore, several data packets (e.g., 10) are sent to the receiving node using the ICMP ping command, and the round-trip time of each data packet is recorded to obtain the average value as the transmission delay of the path.

[0073] S3.3. Based on network quality predictions, bandwidth utilization, and transmission delay, an intelligent scheduling algorithm is used to dynamically predict data for each path, resulting in an allocation strategy for each path selection. The expression is as follows:

[0074]

[0075] Where F(p) is the fitness score of the assignment strategy p, and B i Let D be the bandwidth utilization of the i-th path. i The transmission delay of the i-th path, α i The importance coefficient of the i-th path, μ is the average value of all paths in the network quality prediction, γ is the sensitivity to changes in network quality, δ is the reference point for network quality, j1 is the power of the network quality prediction, o2 is the power of the bandwidth utilization, l3 is the power of the transmission delay, λ is the weighting coefficient of the transmission delay on the fitness score of the allocation strategy, A is the adjustment coefficient for controlling the sensitivity to changes in network quality, and p is the allocation strategy.

[0076] Furthermore, by using the Sigmoid function It is used to smoothly adjust the score so that the score changes slowly when the network quality of the path is close to the reference point δ, and accelerates when it moves away from the reference point.

[0077] Using the natural logarithm function The scoring mechanism can distinguish the differences between different paths. For paths whose network quality is significantly different from the average value μ, the absolute value ensures that the differences in scores between different paths will be distinguished regardless of whether the network quality is higher or lower than the average.

[0078] By combining the bandwidth utilization and transmission delay of each path using a weighted summation method, the importance of the path is reflected.

[0079] S3.4. Based on the fitness score of the allocation strategy, use quicksort to sort all paths from high to low to obtain the allocation strategy for each path selection.

[0080] Furthermore, the quicksort algorithm is used to sort all paths based on their fitness scores. The quicksort algorithm partitions all paths according to their scores using a pivot element, thus obtaining the allocation strategy for each path selection.

[0081] S4. Based on the allocation strategy selected for each path, split the communication data into multiple data blocks.

[0082] S4.1. Based on the allocation strategy of each path, the communication data to be transmitted is split according to the weight ratio of the path.

[0083] Furthermore, the communication data is in the form of files, video streams, or messages. Based on the allocation strategy and the weight of each path, the communication data is divided into multiple data blocks, and the size of each data block is adjusted according to the adaptation score of the allocation strategy and bandwidth requirements.

[0084] S4.2 Communication data is broken down into small data blocks on high-latency and low-bandwidth paths.

[0085] Furthermore, based on path latency and bandwidth utilization, an allocation strategy is used to control the size of data blocks. For high-latency and low-bandwidth paths, application-layer fragmentation technology is used to split communication data into smaller data blocks on high-latency and low-bandwidth paths to reduce latency and packet loss rate, while improving the transmission success rate of these paths. This is to avoid excessively large data blocks from being lost due to network fluctuations, thereby reducing latency and packet loss rate and improving the transmission success rate of these paths.

[0086] S4.3 On low-latency and high-bandwidth paths, communication data is broken down into large data blocks.

[0087] Furthermore, by using application-layer fragmentation technology, communication data is broken down into larger data blocks along low-latency and high-bandwidth paths, allowing large volumes of data to be transmitted through these efficient paths.

[0088] S5. Based on the multiple data blocks that have been split, the split data blocks are distributed proportionally to various paths for transmission.

[0089] S5.1. Based on the bandwidth utilization of each path, obtain the bandwidth allocation ratio for each path.

[0090] Furthermore, bandwidth utilization refers to the ratio of the bandwidth used by a path during the current transmission process to the maximum bandwidth. It is used to measure the available bandwidth of each path. The bandwidth allocation ratio for each path is calculated using bandwidth utilization, expressed as follows:

[0091]

[0092] Among them, P i E represents the bandwidth allocation ratio for the i-th path. i This represents the sum of bandwidth utilization across all paths.

[0093] The bandwidth allocation ratio reflects the proportion of bandwidth load that each path should bear during the entire communication data transmission process. Paths with a higher ratio will bear more data block transmissions.

[0094] S5.2. After splitting the data blocks, allocate the data blocks to each path proportionally according to the bandwidth allocation ratio of each path.

[0095] Furthermore, based on the bandwidth allocation ratio, data blocks are distributed proportionally to each path to ensure that the number of data blocks received by each path matches its bandwidth allocation ratio.

[0096] S5.3 Data blocks on each path are transmitted using the specified transmission protocol.

[0097] Furthermore, data blocks are allocated to various paths and transmitted using the selected TCP transport protocol, with each path's data blocks being transmitted via a specified protocol.

[0098] S6. Based on the transmission of communication data, the receiving and sending nodes exchange network status information to dynamically adjust the allocation of communication data.

[0099] S6.1 The sending and receiving ends exchange real-time network status information through the control channel.

[0100] Furthermore, the sending and receiving ends periodically exchange network status information through a dedicated control channel (such as a UDP control channel). The exchanged information includes bandwidth, latency, packet loss rate, and traffic status data for each path.

[0101] S6.2 The sending end encapsulates all network status information into data packets and sends them to the receiving end.

[0102] Furthermore, all the collected network status information is encapsulated into a data packet, and the encapsulated data packet is sent to the receiving end through the control channel.

[0103] S6.3 After receiving the network status information from the sender, the receiver will decode the network performance of each path, extract bandwidth, latency, and packet loss rate data, and calculate the network health status of each path using the following expression:

[0104]

[0105] Among them, H i (t) represents the network health score of the i-th path at time t, B max D is the maximum bandwidth of all paths. max Let κ be the maximum delay across all paths, θ be the path bandwidth weighting coefficient, φ be the delay weighting coefficient, and P be the packet loss rate weighting coefficient. i(t) represents the packet loss rate at time t for the i-th path.

[0106] Furthermore, the network status of each path is decoded using extended headers, and bandwidth, latency, and packet loss rate data are extracted according to the TCP protocol. The extracted bandwidth, latency, and packet loss rate data are then used with weighting coefficients κ (bandwidth), θ (latency), and φ (packet loss rate). These weighting coefficients can flexibly adjust the importance of bandwidth, latency, and packet loss rate to ensure the quality and efficiency of communication.

[0107] S6.4. Based on the network health score, the receiving end will sort the paths to obtain the highest priority path and dynamically adjust the communication data.

[0108] Furthermore, based on the path health score ranking results, the receiving end will adjust the communication data allocation strategy. Paths with higher network health scores will receive more communication data allocation to improve transmission stability and efficiency. Communication data is allocated by optimizing the bandwidth allocation ratio, prioritizing paths with larger bandwidth, lower latency, and lower packet loss rate for data transmission.

[0109] S7. The receiving node reassembles the data blocks transmitted from each path to obtain complete communication data.

[0110] S7.1 The sending end assigns a number to each data block, and the receiving end allocates an independent buffer area for each path.

[0111] Furthermore, the sending end numbers all data blocks, assigning each data block a unique sequence number so that the receiving end can correctly reassemble the data based on the sequence number. These sequence numbers are globally unique, ensuring that the same data blocks transmitted on different paths will not be confused. The receiving end allocates an independent buffer area for each path to store data blocks received from different paths.

[0112] S7.2 The receiving end numbers the paths, groups multiple data blocks from different paths, and sorts the data blocks of each path according to the data block sequence number.

[0113] Furthermore, the receiving end assigns a number to each path and groups the received data blocks based on the path number. Data blocks for each path are stored in a buffer according to their path number for subsequent sorting and reassembly. For each path, the receiving end stores all transmitted data blocks in a separate buffer, with each slot in the buffer corresponding to one data block. The receiving end sorts these data blocks according to their sequence number. This sorting operation ensures that the received data blocks are in the correct order.

[0114] S7.3 The receiving end reads data blocks one by one from the buffer according to the data block sequence number, and merges the read data blocks into complete communication data.

[0115] Furthermore, the receiving end reads the stored blocks one by one according to the data block sequence number in the buffer of each path, and extracts them in the correct order according to the sorting order. The reading operation adopts a sequential reading method, extracting data blocks in order from the smallest to the largest sequence number. After reading all data blocks, the receiving end merges them into complete communication data. The merging operation is achieved by sequentially splicing the contents of each data block, and finally obtaining the original communication data sent by the sending end.

[0116] This embodiment also provides a computer device suitable for the p2p remote communication method, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the p2p remote communication method as proposed in the above embodiment.

[0117] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0118] This embodiment also provides a storage medium storing a computer program, which, when executed by a processor, implements the p2p remote communication method proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0119] In summary, this invention ensures high-quality communication data input by collecting and preprocessing network environment and communication data. It utilizes a Long Short-Term Memory (LSTM) network model to predict the network quality of each path, enabling a forward-looking assessment of future network conditions. This optimizes path selection and resource allocation, improving transmission efficiency and user experience. By combining SNMP protocol and ICMPping command to obtain real-time network status information, it calculates the fitness score for each path, dynamically adjusting path selection and resource allocation strategies. This approach considers current network conditions and anticipates future trends, maximizing network resource utilization while improving data transmission speed and stability. The receiving node reassembles data blocks transmitted from each path using an independent buffer area and data block sequence number sorting method, ensuring the integrity and reliability of communication data and guaranteeing an efficient and stable communication experience in complex and ever-changing network environments.

[0120] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for peer-to-peer remote communication, characterized in that: include, Collect network environment data and communication data, and preprocess them; The preprocessed network environment data is input into the machine learning model to predict the network quality of each path; Based on the network quality prediction results, an intelligent scheduling algorithm is used to analyze the data and derive the allocation strategy for each path selection. Includes the following steps, The actual traffic and maximum available bandwidth for each path are extracted from network devices using the SNMP protocol to obtain bandwidth utilization. The transmission delay can be obtained by measuring the round-trip time from the sender to the receiver on each path using the ICMP ping command. Based on network quality predictions, bandwidth utilization, and transmission latency, an intelligent scheduling algorithm dynamically predicts data for each path, resulting in an allocation strategy for each path selection. The expression is as follows: ； in, For allocation strategy fitness score For the first Bandwidth utilization of each path No. The transmission delay of the path, No. The importance coefficient of each path This is the average of the network quality predictions for all paths. To control sensitivity to changes in network quality, As a reference point for network quality, The power of the predicted network quality value. The power of bandwidth utilization. The power of the transmission delay. To control the weighting coefficient of transmission delay on the fitness score of the allocation strategy, This is an adjustment coefficient used to control the sensitivity to changes in network quality. For allocation strategy, For the first The path at time The predicted network quality values ​​are as follows; Based on the fitness score of the allocation strategy, all paths are sorted from high to low using the quicksort method to obtain the allocation strategy for each path selection. Based on the allocation strategy selected for each path, communication data is split into multiple data blocks and proportionally distributed across various paths for transmission, including the following steps. Based on the allocation strategy for each path, the communication data to be transmitted is split according to the weight ratio of the path. Communication data is broken down into small blocks along high-latency and low-bandwidth paths; On low-latency and high-bandwidth paths, communication data is broken down into large data blocks; Based on the transmission of communication data, the receiving and sending nodes exchange network status information to dynamically adjust the allocation of communication data, including the following steps. The sending and receiving ends exchange real-time network status information through a control channel; The sending end encapsulates all network status information into data packets and sends them to the receiving end. After receiving the network status information from the sender, the receiver decodes the network performance of each path, extracts bandwidth, latency, and packet loss rate data, and calculates the network health status of each path using the following expression: ； in, For the first The path at time Internet health score For the first The path at time Available bandwidth, The maximum bandwidth for all paths. The maximum delay for all paths. This is the path bandwidth weighting coefficient. The weighting coefficient for the delay. The weighting coefficient of packet loss rate, For the first Path time The packet loss rate; Based on the network health score, the receiving end will sort the paths to obtain the highest priority path and dynamically adjust the communication data. The receiving node reassembles the data blocks transmitted from each path to obtain complete communication data.

2. The p2p remote communication method as described in claim 1, characterized in that: Collecting and preprocessing network environment data and communication data includes the following steps: The collected network data includes bandwidth, latency, and packet loss rate; the collected communication data includes files, video streams, and messages. All collected data were denoised and standardized.

3. The p2p remote communication method as described in claim 2, characterized in that: The process of inputting preprocessed network environment data into a machine learning model to predict the network quality of each path includes the following steps. Principal component analysis (PCA) is used to extract bandwidth, latency, and packet loss rate features from preprocessed network environment data. These features are then input into a Long Short-Term Memory (LSTM) network model to predict the network quality of each path. The expression is as follows: ； in, For a moment Next The numerical values ​​of each network quality characteristic, For the first The weights of each network quality feature value For a moment The sum of network quality characteristics under the following conditions For the number of paths, This is an adjustment parameter for the sum of network quality characteristics. For network quality feature indexing, It is a non-linear activation function.

4. The p2p remote communication method as described in claim 1, characterized in that: Based on the split data blocks, the process of distributing the split data blocks proportionally across various paths for transmission includes the following steps: Based on the bandwidth utilization of each path, the bandwidth allocation ratio for each path is obtained; The split data blocks are then distributed proportionally to each path based on the bandwidth allocation ratio of each path. Data blocks on each path are transmitted using the specified transport protocol.

5. The p2p remote communication method as described in claim 1, characterized in that: The receiving node reassembles the data blocks transmitted from each path to obtain complete communication data, including the following steps. The sending end assigns a number to each data block, and the receiving end allocates an independent buffer area for each path; The receiving end numbers the paths, groups multiple data blocks from different paths, and sorts the data blocks of each path according to the data block sequence number. The receiving end reads data blocks one by one from the buffer according to the data block sequence number, and merges the read data blocks into complete communication data.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the p2p remote communication method according to any one of claims 1 to 5.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the p2p remote communication method according to any one of claims 1 to 5.

Images