CN118695144A - Multipath signal transmission method and system in optical communication network - Google Patents

Abstract

The present application provides a multipath signal transmission method and system in an optical communication network, which relates to the field of optical communication transmission. The method includes: obtaining a target data packet to be transmitted by an optical communication device and path state data of each transmission path of the optical communication device; adaptively splitting the target data packet into corresponding sub-data packet groups according to content perception information of the target data packet, and screening at least one key sub-data packet from the sub-data packet group; for each key sub-data packet, determining the forward error correction code corresponding to the key sub-data packet to update the target sub-data packet group; determining the target transmission path corresponding to each target sub-data packet in the target sub-data packet group to transmit the corresponding sub-data packet, and using the optimal transmission path to transmit each forward error correction code and the path identifier of the corresponding target transmission path. Thus, it is ensured that the system can maintain efficient transmission performance and low bit error rate when facing network state fluctuations and emergencies.

Description

Multipath signal transmission method and system in optical communication network

Technical Field

The present application relates to the field of optical communication transmission technology, and in particular to a multi-path signal transmission method and system in an optical communication network.

Background Art

Optical communication networks have become the backbone of modern communication networks due to their advantages of high bandwidth, low latency and long-distance transmission. In optical communication networks, information is usually transmitted in the form of optical signals to ensure high-speed and efficient communication. With the in-depth development of informatization and the popularization of various data services, the types and quantities of data transmitted in the network have increased rapidly, and the size and complexity of data packets have also increased. In this context, multipath transmission technology has been widely adopted to improve the efficiency and reliability of data transmission by utilizing multiple transmission paths at the same time.

In complex network environments, packet loss and bit errors frequently occur during data transmission due to factors such as signal attenuation, interference, and noise. Especially in high-bandwidth applications (such as high-definition video and high-fidelity audio), data loss and errors may cause serious user experience problems, such as image freezes and intermittent sounds, resulting in poor data transmission reliability.

In addition, due to the differences in the path states of each transmission path, the transmission delay is different, resulting in interference and superposition problems of the signals received by the receiving end. However, the existing signal recovery technology has limited effect when dealing with the delay differences in multi-path transmission, and it is difficult to ensure the integrity and accuracy of the data packet.

In response to the above problems, the industry has not yet proposed a better technical solution.

Summary of the invention

The present application provides a multipath signal transmission method, system, storage medium, computer program product and electronic device in an optical communication network, which are used to at least solve the problem of poor reliability of multipath data transmission in the current related technology.

In a first aspect, an embodiment of the present application provides a multipath signal transmission method in an optical communication network, comprising: obtaining a target data packet to be transmitted by an optical communication device and path status data of each transmission path of the optical communication device; adaptively splitting the target data packet into corresponding sub-data packet groups according to content perception information of the target data packet, and screening at least one key sub-data packet from the sub-data packet group; for each of the key sub-data packets, determining a forward error correction code corresponding to the key sub-data packet, and attaching the forward error correction code to the key sub-data packet to determine a target sub-data packet group according to an updated sub-data packet group; determining an optimal transmission path according to the path status data of each of the transmission paths, and determining a target transmission path corresponding to each target sub-data packet in the target sub-data packet group; using each of the target transmission paths to respectively transmit the corresponding sub-data packets in the target sub-data packet group, and using the optimal transmission path to transmit each forward error correction code and the path identifier of the corresponding target transmission path.

In a second aspect, an embodiment of the present application provides a multipath signal transmission system in an optical communication network, comprising: an acquisition unit, configured to acquire a target data packet to be transmitted by an optical communication device and path status data of each transmission path of the optical communication device; an adaptive unpacking unit, configured to adaptively split the target data packet into corresponding sub-data packet groups according to content perception information of the target data packet, and screen at least one key sub-data packet from the sub-data packet group; a code attachment unit, configured to determine, for each of the key sub-data packets, a forward error correction code corresponding to the key sub-data packet, and attach the forward error correction code to the key sub-data packet to determine a target sub-data packet group according to an updated sub-data packet group; a path division unit, configured to determine an optimal transmission path according to the path status data of each of the transmission paths, and determine a target transmission path corresponding to each target sub-data packet in the target sub-data packet group; a transmission unit, configured to respectively transmit corresponding sub-data packets in the target sub-data packet group using each of the target transmission paths, and transmit each forward error correction code and a path identifier of the corresponding target transmission path using the optimal transmission path.

According to a third aspect, an electronic device is provided, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the steps of the multipath signal transmission method in an optical communication network of any embodiment of the present application.

In a fourth aspect, an embodiment of the present application provides a storage medium having a computer program stored thereon, characterized in that when the program is executed by a processor, the steps of the multipath signal transmission method in an optical communication network of any embodiment of the present application are implemented.

In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program/instruction, which, when executed by a processor, implements the steps of the multipath signal transmission method in an optical communication network of any embodiment of the present application.

The multipath signal transmission method and system in an optical communication network provided by the present application can produce at least the following technical effects:

(1) Split the target data packet to be transmitted into multiple sub-data packets based on the content-aware information of the target data packet, so that the data packets can be processed differently according to their importance, and key sub-data packets are screened out. FEC (Forward Error Correction) is added to the key sub-data packets. In this way, if data packet loss or bit error occurs during multi-path data parallel transmission, the receiving end can recover the key sub-data packets through the error correction code, thereby ensuring the complete reliability of the key information in the transmitted data packet.

(2) The target data packet to be transmitted is split into multiple sub-data packets based on the content-aware information of the target data packet. In this way, when performing the data packet path allocation operation, the key sub-data packets can be preferentially allocated to paths with better quality, ensuring the priority transmission of important data. Therefore, the transmission path of the data packet can be dynamically adjusted according to the real-time network status and transmission requirements, which can significantly improve the utilization of network resources.

(3) By analyzing the status data of each transmission path, the transmission path with the best status is selected to ensure that the receiving end can receive the FEC code and corresponding path identifier of all key information transmission paths transmitted by the optimal transmission path. In this way, when a serious transmission failure occurs in a key information transmission path and the FEC code is lost or damaged, the receiving end can still recover the key sub-data packet of the path through the FEC code of the corresponding path identifier, effectively improving the transmission reliability of the key information in the data packet.

Through this technical solution, the transmission path and processing method of the data packet are dynamically adjusted according to the real-time network status and transmission requirements, ensuring that the system can maintain efficient transmission performance and low bit error rate when facing network status fluctuations and emergencies, and can adapt to diverse network environments and business application scenarios.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

FIG1 is a flowchart showing an example of a multipath signal transmission method in an optical communication network according to an embodiment of the present application;

FIG2 is a flowchart showing an example of determining a forward error correction code corresponding to a key sub-data packet according to an embodiment of the present application;

FIG3 shows an operation flow chart of an example of determining a target transmission path for each target sub-data packet according to an embodiment of the present application;

FIG4 shows an operation flow chart of an example of determining each target transmission path according to a packet content impact factor matrix according to an embodiment of the present application;

FIG5 shows a structural block diagram of an example of a multipath signal transmission system in an optical communication network according to an embodiment of the present application;

FIG. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

DETAILED DESCRIPTION

In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

In the technical solution of this application, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved shall comply with the provisions of relevant laws and regulations and shall not violate public order and good morals.

FIG. 1 shows a flowchart of an example of a multipath signal transmission method in an optical communication network according to an embodiment of the present application.

Regarding the executor of the method of the embodiment of the present application, it can be any controller or processor with computing or processing capabilities. By optimizing strategies such as data packet splitting, path selection and forward error correction, the data transmission quality and efficiency of the optical communication network are significantly improved, while effectively reducing the interference problems caused by delay differences, thereby enhancing the reliability and flexibility of the system.

In some examples, it can be a multi-path data transmission platform for an optical communication device, and can be integrated and configured in a processor, electronic device, terminal or server by software, hardware or a combination of software and hardware, and the types of terminals, electronic devices or servers can be diverse, such as mobile phones, tablet computers or desktop computers, etc.

As shown in FIG. 1 , in step S110 , a target data packet to be transmitted by an optical communication device and path state data of each transmission path of the optical communication device are acquired.

In some embodiments, the optical communication device receives a target data packet to be transmitted from an upper layer protocol or an application layer, which may be a data packet of various types, such as video, audio, text, etc. Here, the optical communication device monitors the status data of each transmission path in real time through a built-in monitoring module or an external monitoring device, thereby being able to accurately and real-time evaluate the transmission quality and reliability of each path.

In some examples of the embodiments of the present application, the path status data includes at least one of the following: path available bandwidth, path delay, path packet loss rate, path bit error rate, path signal attenuation level and signal interference intensity. Specifically, the path available bandwidth indicates the amount of bandwidth available on the current path. In the path selection process, it is ensured that important data packets select a path with sufficient available bandwidth to avoid network congestion. Path delay indicates the time required for a data packet to travel from the sender to the receiver. It is a key indicator of real-time data packets (such as video conferencing, online games, etc.). By selecting a path with lower delay, low-latency transmission of real-time data packets can be ensured to improve user experience. Path packet loss rate indicates the proportion of data packets lost during transmission to the total transmitted data packets. The packet loss rate reflects the transmission stability of the path. Selecting a path with a low packet loss rate helps to ensure the complete transmission of data packets and reduce data loss. Path bit error rate indicates the ratio of error bits received during transmission to total transmitted bits. In high-fidelity audio and video data and financial data transmission, paths with low bit error rates should be preferred to ensure data accuracy and quality. The path signal attenuation level indicates the degree of signal strength reduction during transmission. Large signal attenuation may make it difficult for the signal to be correctly decoded at the receiving end. The signal interference strength indicates the impact of other signals on the target signal. Signal interference may come from other optical fiber channels or external electromagnetic sources, especially in high-density channels or environments with external interference sources.

In step S120, the target data packet is adaptively split into corresponding sub-data packet groups according to the content-aware information of the target data packet, and at least one key sub-data packet is screened from the sub-data packet groups.

In some embodiments, the target data packet may be analyzed for content by various content-aware technologies, and then the target data packet may be split according to the content-aware results. Specifically, when the target data packet is split by content-aware technology, the system dynamically adjusts the size of the sub-data packet according to the difference in content-aware information (e.g., static video frames and dynamic video frames, background audio and speaker audio, etc.), so that the total number of sub-data packets generated by each target data packet is different, and the number of corresponding transmission paths may also fluctuate.

Through this embodiment, adaptive splitting is performed according to the content of the data packet, so that key data and ordinary data can be processed separately, and the screening and priority transmission of key sub-data packets are ensured, thereby ensuring the transmission quality of key data and reducing the negative impact caused by the loss or delay of important data. The specific details will be expanded in conjunction with other examples below.

In step S130, for each key sub-data packet, a forward error correction code corresponding to the key sub-data packet is determined, and the forward error correction code is added to the key sub-data packet, so as to determine a target sub-data packet group according to the updated sub-data packet group.

In some implementations, for each key sub-data packet, a forward error correction algorithm, such as a convolutional code, a polar code, etc., is used to calculate a corresponding forward error correction code. The calculated forward error correction code is appended to the corresponding key sub-data packet to form a new target sub-data packet group. Thus, by appending the forward error correction code, the receiving end can perform error correction and recovery when the data packet is lost or damaged, effectively reducing user experience problems caused by data loss or bit errors in high-bandwidth applications, such as video freezes, audio interruptions, etc.

In step S140, an optimal transmission path is determined according to the path status data of each transmission path, and a target transmission path corresponding to each target sub-data packet in the target sub-data packet group is determined.

In some embodiments, the acquired transmission path status data is processed to calculate the transmission quality and applicability of each transmission path to determine the optimal transmission path. In addition, from the remaining transmission paths, each target sub-packet in the target sub-packet group is allocated to the corresponding transmission path, for example, the sub-packet with key information is preferentially allocated to the transmission path with better status.

In step S150, the corresponding sub-data packets in the target sub-data packet group are transmitted respectively by using the respective target transmission paths, and the respective forward error correction codes and the path identifier of the corresponding target transmission path are transmitted by using the optimal transmission path.

Here, the path identifier of each target sub-packet is attached to the data packet, so that the receiving end can perform integrity detection and error correction on the data packets received in the path. In addition, all FEC codes and corresponding path identifiers are transmitted using the optimal transmission path, so that when a serious transmission failure occurs in a key information transmission path and the FEC code is lost or damaged, the receiving end can still recover the key sub-packet of the path through the FEC code of the corresponding path identifier, effectively improving the transmission reliability of the key information in the data packet. Therefore, by transmitting sub-packets in parallel over multiple paths, the speed and efficiency of the overall data transmission are improved, and the forward error correction code is transmitted using the optimal transmission path to ensure the high-reliability transmission of error correction information, further improving the reliability of data transmission.

Regarding the implementation details of step S120, in some examples of the embodiments of the present application, each type of data packet has different characteristics and priority requirements, and the content-aware adaptive splitting strategy can reasonably allocate network resources according to the characteristics of different data types. Content-aware information is selected from multiple dimensions of visual, auditory and text information to fully cover the characteristics of different data packets and ensure the effectiveness and efficiency of data transmission.

In the first aspect, when the target data packet is a video data packet, first content perception information corresponding to the video data packet is determined, and the video data packet is adaptively split into corresponding sub-data packet groups according to the first content perception information, and the first content perception information is the number of edge pixels and the range of motion vectors of the video frame.

In some embodiments, based on an edge detection algorithm (e.g., Canny edge detection algorithm), the number of edge pixels of each video frame is calculated, and frames with more edge pixels contain more details and require higher priority. In addition, using a motion estimation algorithm (e.g., optical flow method), motion vectors between video frames are calculated, and frames with intense motion require more bandwidth and lower latency.

Here, the complexity of the photon-encoded video frame is calculated based on the number of edge pixels and the size of the motion vector in the video frame data packet. By dynamically adjusting the module size according to the complexity of each video frame and the range of the motion vector, redundant data can be reduced and the transmission efficiency can be improved. For example, the module generated by the high-complexity frame is smaller, and the module generated by the low-complexity frame is larger. This can reduce the delay when transmitting high-complexity frames and improve the overall transmission rate. By dynamically adjusting the size of the sub-packet, the network bandwidth is ensured to be optimally utilized and the data transmission efficiency is improved. For the video data packet, based on the number of edge pixels and the range of the motion vector, it is ensured that the transmitted key frame can retain important visual information and improve the viewing experience.

Secondly, when the target data packet is an audio data packet, second content perception information corresponding to the audio data packet is determined, and the audio data packet is adaptively split into corresponding sub-data packet groups according to the second content perception information, and the second content perception information is the audio spectrum bandwidth and audio energy distribution.

In some implementations, the frequency components of the audio signal are analyzed by FFT (Fast Fourier Transform) to calculate its spectrum bandwidth. A larger bandwidth means that it contains more sound details, and a wider spectrum bandwidth means that it contains more sound details, such as the high-pitched part of a musical instrument or the delicateness of a human voice. In addition, based on the energy distribution of the audio signal at different frequencies, the important frequency bands are determined. The energy-concentrated parts usually contain the main audio content, and the main information of the audio is usually concentrated in a specific frequency band (such as the human voice frequency band). Therefore, these energy-concentrated parts are transmitted first to ensure the transmission of important information.

Here, the audio spectrum bandwidth represents the frequency range of the audio signal. Audio with a wider spectrum bandwidth contains more sound details and usually requires higher audio quality. Audio energy distribution describes the energy distribution characteristics of the audio signal over frequency and is used to determine the importance and transmission requirements of the audio frame. For audio data packets, based on the spectrum bandwidth and energy distribution, the part containing key sound information is split first and its transmission quality is guaranteed.

On the third aspect, when the target data packet is a text data packet, the third content perception information corresponding to the text data packet is determined, and the text data packet is adaptively split into corresponding sub-data packet groups according to the third content perception information, and the third content perception information includes text semantic density and keyword frequency.

In some embodiments, the semantic density of the text is calculated through NLP (Natural Language Processing) technology, such as word embedding or topic model. Paragraphs with high semantic density usually contain more key information, and these contents should be transmitted first to ensure the completeness and accuracy of the information. In addition, the TF-IDF (Term Frequency-Inverse Document Frequency) method is used to identify keywords in the text and their frequency of occurrence. Keywords with high frequency indicate their importance, so the parts with high frequency keywords should be transmitted first to ensure that users can receive the main information.

Here, semantic density is used to measure the semantic information density of text data packets. Text with high semantic density usually contains more key information. Keyword frequency indicates the frequency of occurrence of important keywords in the text, which is used to identify the distribution of key information. For text data packets, based on semantic density and keyword frequency, the part with high information density is transmitted first to ensure the complete transmission of key text information.

Through this embodiment, the content perception information of the target data packet is analyzed, and the critical and non-critical parts of the data packet can be effectively identified and extracted. Critical sub-data packets (such as high-detail video frames, important audio clips or critical text information) can be transmitted first, ensuring that when network bandwidth is limited or transmission conditions are not ideal, important information is transmitted first to ensure user experience.

In some examples of the embodiments of the present application, in the process of generating FEC codes, content-aware information and adaptive coding and modulation methods can also be combined to further improve the data transmission reliability of the optical communication network.

FIG. 2 shows an operational flow chart of an example of determining a forward error correction code corresponding to a key sub-data packet according to an embodiment of the present application.

As shown in FIG. 2 , in step S210 , the corresponding target redundancy is adaptively determined according to the content-aware information of the key sub-packets.

It should be understood that the higher the redundancy, the stronger the error correction capability of the FEC code. The redundancy of the corresponding FEC code is adaptively determined based on the content perception information of the key sub-packets. Exemplarily, corresponding redundancies can be set for different types of data packets. For example, the redundancy of key frames in video data packets can be set higher to ensure the integrity of important picture information; and the redundancy of important sound clips in audio data packets can also be appropriately increased. In addition, different redundancy levels can be set according to the importance of the data packet, such as criticality. The higher the criticality of the sub-packet, the greater its redundancy. By analyzing the content perception information of the data packet and adaptively setting the redundancy, the integrity and reliability of the FEC code are ensured.

In step S220, the key sub-data packet is encoded according to the target redundancy and the packet type of the key sub-data packet to determine the forward error correction code corresponding to the corresponding key sub-data packet, and the packet type includes any one of the following video type, audio type and text type.

It should be noted that different types of data packets have different requirements for transmission quality and error correction capabilities. By selecting appropriate FEC coding methods and parameter adjustments, the reliability and efficiency of data transmission can be effectively improved. Here, the video type key sub-data packet adopts RS coding (Reed-Solomon). For key frames in high-resolution video data packets (frames with a large number of edge pixels and a large motion vector range), RS coding is used, and high redundancy is set to ensure the reliability of the FEC code. The audio type key sub-data packet adopts LDPC coding (Low-Density Parity-Check). For audio data packets with high sound quality requirements (frames with wide spectrum bandwidth and concentrated energy distribution), LDPC coding is used and the redundancy ratio is dynamically adjusted to ensure high-quality transmission of important sound fragments. The text type key sub-data packet adopts Hamming coding. For text data packets containing high-frequency keywords, a simple error correction coding method is applied to reduce redundant overhead and optimize the use of system resources.

By adaptively setting redundancy and selecting the appropriate FEC encoding method, data errors during transmission can be effectively corrected. Especially in harsh transmission environments, forward error correction codes can repair some or all of the erroneous data at the receiving end, reducing packet loss and retransmission. In addition, for key sub-packets, the increased redundancy can provide stronger error recovery capabilities, ensuring the transmission integrity and accuracy of these important data, which can guarantee the recovery accuracy of key data (such as video key frames, important audio clips, and key information text).

FIG. 3 shows an operational flowchart of an example of determining a target transmission path for each target sub-data packet according to an embodiment of the present application.

As shown in FIG. 3 , in step S310 , the packet attribute data of each target sub-data packet in the target sub-data packet group is obtained, and the packet attribute data includes the key sub-data packet identifier, content type and required transmission bandwidth of the target sub-data packet.

In some embodiments, in the target sub-data packet group, each target sub-data packet is parsed to obtain its packet attribute data. Specifically, the key sub-data packet and the ordinary sub-data packet are distinguished by the key sub-data packet identifier, and the required transmission bandwidth can reflect the bandwidth requirement of the sub-data packet. Here, the content type of the sub-data packet can be video, audio or text. It should be noted that the content type of the sub-data packet can be consistent with or different from the data packet type. For example, when the target data packet is a converged media data packet, the converged media data packet is decomposed into sub-data packets containing multiple content types, such as audio sub-data packets, text sub-data packets, and video sub-data packets.

In step S320, the optimal transmission path is screened out from the various transmission paths to update them into various candidate transmission paths.

In this way, the optimal transmission path dedicated to transmitting FEC codes is screened out from all transmission paths, and the remaining transmission paths are updated as candidate transmission paths to prevent repeated use of the optimal transmission path and ensure the transmission reliability and real-time performance of the optimal transmission path.

In step S330, for each target sub-data packet, based on the packet attribute data of the target sub-data packet and the path state data of each candidate transmission path, the packet content impact factor of the target sub-data packet relative to each candidate transmission path is calculated to obtain a corresponding packet content impact factor matrix.

Here, the packet content impact factor of the target sub-data packet relative to each candidate transmission path can be calculated by various calculation methods, such as weighted average, fuzzy logic, machine learning model, etc. Then, the calculation results of the packet content impact factor of all target sub-data packets for each candidate transmission path are stored in a matrix, i.e., a packet content impact factor matrix, wherein the rows of the matrix correspond to the target sub-data packets and the columns correspond to the candidate transmission paths.

In some implementations, the packet content impact factor can be characterized as a priority or a matching degree, and a higher packet content impact factor should be supported, thereby accurately evaluating the transmission effect of each sub-data packet on different paths and providing a quantitative basis for path selection.

In step S340, the target transmission path corresponding to each target sub-data packet is determined according to the packet content impact factor matrix of each target sub-data packet.

Here, various path selection algorithms, such as dynamic programming and greedy algorithms, can be used to determine the corresponding target transmission path for each target sub-data packet and record the path selection results. Thus, refined path selection is achieved to ensure that each target sub-data packet can be transmitted optimally, and the flexibility and adaptability of the system are improved, and the path selection can be adjusted dynamically to adapt to changes in the network environment and maintain efficient data transmission performance.

In some examples of the embodiments of the present application, in order to more accurately reflect the degree of adaptation of each target sub-packet relative to each candidate transmission path, comprehensive consideration is mainly given to the three aspects of the impact of the key sub-packet identifier, the impact of the content type, and the impact of the required transmission bandwidth. Specifically, key sub-packets need to be transmitted first, and considering their sensitivity to transmission delay, stability, and error recovery, it is necessary to ensure that they pass through paths with high reliability and low latency. In addition, different content types have different requirements for transmission characteristics. For example, video data is sensitive to delay and bandwidth, while audio data has higher requirements for delay, and text data has relatively low requirements for bandwidth and delay. In addition, the required transmission bandwidth directly affects the choice of path, because data packets with high bandwidth requirements need to choose paths with sufficient bandwidth to avoid delays caused by congestion and insufficient bandwidth.

More specifically, the package content impact factor can be calculated by the following formula:

, formula (1);

, formula (2);

, formula (3);

, formula (4);

In the formula, Indicates the target sub-packet In the candidate transmission path The impact factor of the package content on and Represents the target sub-packet In the candidate transmission path The key influencing factors, content type influencing factors and bandwidth demand influencing factors on the network; represents the critical weight coefficient; express The key sub-packet identifier of For key sub-packets, ,otherwise ; express transmission delay; for The inverse of the packet loss rate; is a preset constant; Indicates the content type weight coefficient, express Content Type The corresponding delay sensitivity weight, express Content Type The bandwidth sensitivity weight of express Content Type The bit error rate sensitivity weight of express Available bandwidth, express bit error rate; represents the bandwidth demand weight coefficient, express The required bandwidth, express The total bandwidth capacity of express The current bandwidth utilization of the

Explanation of the calculation formula for the above key impact factors: The importance of key sub-packets in the weighted calculation of key impact factors is emphasized. Key sub-packets usually need to be transmitted first, so they are given a higher weight coefficient. Key sub-packet identification is a binary variable used to distinguish whether it is a critical data packet. The impact factor is calculated only when the delay is inversely proportional to the time delay. This ensures that paths with smaller path delays are selected first. Lower delays mean that data packets can be transmitted faster. It is used to characterize the reliability of a path, and a highly reliable path can reduce the probability of data packet loss or transmission errors. This ensures that critical data packets can choose paths with high reliability and low latency, and reasonably guarantees the priority transmission and quality of critical data.

Explanation of the calculation formula for content type impact factor, It reflects the importance of different types of data packets in the weighted calculation of key influencing factors. Here, the sensitivity weights of delay, bandwidth, and bit error rate are According to the content type of the sub-packet Adaptive adjustments are made. For example, video data may be more sensitive to bandwidth and latency, while text data is more sensitive to bit error rate. The inverse term of latency and bandwidth ensures that under the same content type, the path with low latency and large bandwidth is given priority; the inverse term of bit error rate ensures the priority of transmission quality. As a result, the system can dynamically select the most appropriate transmission path according to the different requirements of the data packet content type, thereby improving the overall transmission efficiency and quality.

Explanation of the calculation formula for the bandwidth demand influencing factor. This reflects the importance of bandwidth in transmission selection. Required bandwidth It is an indicator that directly reflects the network resource demand of data packets. Higher required bandwidth usually requires the selection of a path with larger bandwidth. In addition, the inverse term of available bandwidth is Taking into account the current bandwidth utilization of the path and total bandwidth ,ensuring that a path with low bandwidth utilization and large available bandwidth is selected to avoid congestion.,Thus, the bandwidth demand of the data packet and the current load status of the path are comprehensively considered,,so that bandwidth-sensitive data packets can select the most appropriate transmission path.

It should be noted that by weighted combination of various factors, the system can find a balance point in multi-objective optimization, ensure the overall performance of transmission is optimized, and realize the global comprehensive optimization capability of the optical communication network.

In one example of the embodiment of the present application, the above-mentioned weights may be set by inputting information, such as input by a manager during the testing phase. In another example of the embodiment of the present application, they may also be intelligently set by data-driven weight learning.

More specifically, in a specific implementation method of setting weights, before calculating the packet content impact factor of the target sub-packet relative to each candidate transmission path, the target content type corresponding to the target sub-packet is parsed. Then, the delay sensitivity weight, bandwidth sensitivity weight and bit error rate sensitivity weight that match the target content type are determined according to the content sensitivity weight table. The content sensitivity weight table records a variety of content types and corresponding sensitive weight settings, and the sensitive weight settings include calibrated delay sensitivity weights, bandwidth sensitivity weights and bit error rate sensitivity weights. Exemplarily, the sensitive weights corresponding to each content type are calibrated in the test phase. For example, the bandwidth sensitivity weight and delay sensitivity weight calibrated for the video data type are larger, while the bit error rate sensitivity weight for the text data type is larger. Therefore, through the pre-calibrated content sensitivity weight table, the corresponding weight settings can be quickly and accurately adaptively assigned to various types of sub-packets, which is easy to operate and has high efficiency.

In another example of an embodiment of the present application, in data-driven weight learning, historical data in network transmission can be collected and sorted to extract features that affect packet content influencing factors. Specifically, historical network transmission data is collected from optical communication devices (e.g., optical transmitters or routers), traffic monitoring systems, etc., including bandwidth utilization, data packet transmission delay, packet loss rate, and data packet attributes. Then, based on historical bandwidth utilization, the features of data packets with high bandwidth requirements are extracted, and the features of key data packets are extracted based on information such as data packet content type, and their performance in network transmission, such as delay sensitivity and bandwidth requirements, is extracted based on data packets of different content types. Furthermore, the model is trained using a supervised learning method to determine the contribution of each feature to the packet content influencing factor, and the model architecture can use a multilayer perceptron. Finally, according to the latest model output, the critical weight coefficient, content type weight coefficient, and bandwidth requirement weight coefficient are dynamically adjusted.

Through the embodiments of the present application, multiple factors such as criticality, content type and bandwidth requirements are comprehensively considered, and the adaptability of each path can be accurately evaluated, so that the system can select the most suitable transmission path according to the characteristics of each data packet, ensuring the optimization of transmission quality and efficiency. In addition, by introducing real-time network status parameters such as delay, bandwidth and bit error rate, the system can dynamically adapt to the current state of the network and adjust the path selection strategy. When the network load changes, the system can respond quickly and select the optimal path to avoid congestion and reduced transmission quality.

Furthermore, in terms of selecting the target transmission path according to the packet content impact factor matrix, in an example of an embodiment of the present application, for each target sub-data packet, its packet content impact factor on all candidate paths is calculated, and the calculated packet content impact factors are sorted in descending order to form a sorted path list. For key sub-data packets, the path with the highest impact factor ranking is preferentially selected to ensure priority transmission. For other sub-data packets, the most suitable path is selected according to their content type and bandwidth requirements. For example, video data preferentially selects a path with high bandwidth, and text data preferentially selects a path with low bit error rate.

In another example of the embodiment of the present application, the target transmission path can also be automatically allocated by using a bipartite graph analysis method to ensure the best global network transmission effect.

FIG. 4 shows an operational flowchart of an example of determining various target transmission paths according to a packet content impact factor matrix according to an embodiment of the present application.

As shown in FIG. 4 , in step S410 , a bipartite graph is constructed.

Here, the bipartite graph contains a set of data packet vertices and a set of path vertices. The set of data packet vertices is defined by all target sub-data packets, and the set of path vertices is defined by all candidate transmission paths. Therefore, by constructing a bipartite graph, a clear structured representation method is provided to transform the matching problem of data packets and transmission paths into a maximum matching problem in graph theory, which is convenient for solving using various graph algorithms.

In step S420, the edge weights of the bipartite graph are configured based on each package content impact factor matrix.

Here, the edge weight between each data packet vertex and the path vertex in the bipartite graph is determined by the corresponding packet content impact factor. Therefore, by converting the packet content impact factor into an edge weight, the transmission effect of each data packet on different transmission paths is accurately reflected. The configuration of the edge weight enables the maximum matching algorithm to more effectively find the match with the largest total weight, thereby optimizing the path selection.

In step S430 , the bipartite graph is processed based on a maximum matching algorithm to determine a maximum weight matching edge set between the data packet vertex set and the path vertex set.

In some embodiments, various algorithms, such as the Hopcroft-Karp algorithm, the Dinic algorithm, or the KM algorithm (Kuhn-Munkres, Kuhn-Monks algorithm), etc., can be used to find the maximum weight matching edge set in the bipartite graph, and the matching edge set corresponding to the maximum weight matching edge set has the largest total edge weight. Thus, the matching edge set found by the maximum matching algorithm ensures that each sub-data packet is assigned to the global optimal transmission path, thereby maximizing transmission efficiency and reliability.

In step S440, the target transmission path corresponding to each target sub-data packet is determined according to the maximum weight matching edge set.

In some implementations, the target transmission path corresponding to each target sub-data packet is parsed according to the result of the maximum matching algorithm, and the parsed transmission path is used as the final selection to record the transmission path of each target sub-data packet. Thus, the path selection process is optimized by using the result of the maximum weight matching edge set to ensure the global optimal transmission process of each sub-data packet.

Regarding the implementation details of step S430, in some implementations, the maximum matching algorithm is an improved KM algorithm. More specifically, the vertex matching state initialization operation is performed, including:

Create an initial empty set of matches ,

For the data packet vertex set Each vertex in , select and The connected maximum edge weight is used as the initial label:

, formula (5);

In the formula, Indicates the target sub-packet The corresponding data packet vertex; Represents a packet vertex The initial label of

For the path vertex set Each vertex in , initialize the label ,

In the formula, Indicates candidate transmission paths The corresponding path vertex; Represents the path vertex The initial label of .

Execute the main loop operation to iteratively find augmenting paths to increase the total edge weight of the matching edge set; the operation of each iteration is as follows:

Mark the access status of each data packet vertex and each path vertex,

The heuristic function is used to calculate the heuristic value of each unmatched data packet vertex, and the initial vertex is selected heuristically. A vertex is selected from the unmatched data packet vertex set as the starting point of the augmenting path. At this time, it is expected to find an augmenting path starting from this vertex to increase the total matching weight.

More specifically, the heuristic function formula is:

, formula (6);

In the formula, and are the factor adjustment weights, Represents a packet vertex The heuristic value of

The unmatched packet vertex with the largest corresponding heuristic value is selected as the initial packet vertex for augmenting path search.

Here, the heuristic function is used to evaluate each unmatched packet vertex Then, the heuristic value is selected first. The largest vertex , that is, the packet vertex with the highest potential gain. Through the above operations, it is possible to ensure that the initial augmenting path search starts from the vertex that is most likely to increase the matching weight. This strategy can quickly lock the potential starting point of the augmenting path, reduce unnecessary calculations, and thus speed up the convergence of the algorithm.

It should be noted that the matching set The update is mainly performed in the augmenting path search phase, and the label update is an auxiliary operation used to adjust the label value of the vertex for the next search. Specifically, at the beginning of the algorithm, the matching set Initialized as an empty set, the set is used to store the currently found matches, that is, the matching edges between the packet vertex and the path vertex. Then, iterate through the main loop, which consists of two major steps, namely augmenting path search and label update. Each loop aims to find and utilize augmenting paths to increase the total weight of matching edges.

Use Breadth-First Search (BFS) to find the augmenting path starting from the initial packet vertex. During the search, for each edge The search criteria are:

, formula (7);

Here, through the hierarchical search of BFS, it is ensured that the shortest augmenting path is found in each search, the matching gain of a single iteration is maximized, and the matching adjustment process is significantly accelerated.

If an augmenting path is found, reverse the matched and unmatched edges in the augmenting path and add the unmatched edges on the augmenting path to the matching set. , and remove the original matching edges Here, an augmenting path refers to a path starting from an unmatched vertex, through alternating unmatched edges and matched edges, and finally returning to an unmatched vertex. In this way, by reversing the matched and unmatched edges in the augmenting path to update the matching state, the updated matching set Can increase the total weight.

If no augmenting path is found, update each vertex label to narrow the gap between unmatched points and matched points, so as to provide conditions for the next round of augmenting path search. The calculation rule for the update is:

, formula (8);

In the formula, represents the minimum adjustment to update vertex labels to ensure that the path and data packets Minimize the differences in package content impact factors between them;

For visited , update the corresponding data packet vertex label by the following formula:

, formula (9);

For visited , update the corresponding path vertex labels by:

, formula (10);

By finding augmenting paths, the algorithm can increase the total weight of the matching set, ensuring that each update is meaningful. In addition, when an augmenting path cannot be found, the label update operation can effectively adjust the search space to create conditions for the next round of augmenting path search, thereby maintaining the progress of the algorithm.

When it is detected that the total edge weight of the matching edge set determined by iteration exceeds the preset number of iterations and does not increase, the iteration is stopped and the current matching set is Output the maximum weight matching edge set. This ensures that the algorithm stops after reaching the optimal matching state, avoiding invalid calculations and infinite loops.

By considering the packet content influencing factors, the algorithm can comprehensively consider multiple factors such as the priority, content type and transmission requirements of the data packet in path selection, which not only ensures that important data packets get the best path first, but also reasonably allocates network resources and improves the overall transmission quality. By searching and reversing the augmented path, the algorithm can continuously update the matching status to ensure that the matching set is always the current optimal one, and finally maximize the total weight of the matching edge set. By fine-tuning the weights of the packet content influencing factors and the heuristic method, the algorithm can still reasonably allocate resources under different network load conditions, ensuring that high-priority data packets are processed first, while low-priority data packets are processed when resources allow, improving the user experience quality under high traffic conditions.

It should be noted that, for the aforementioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of actions combined, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application. In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

FIG5 shows a structural block diagram of an example of a multipath signal transmission system in an optical communication network according to an embodiment of the present application.

As shown in FIG. 5 , a multipath signal transmission system 500 in an optical communication network includes an acquisition unit 510 , an adaptive unpacking unit 520 , a coding unit 530 , a path division unit 540 and a transmission unit 550 .

The acquisition unit 510 is used to acquire a target data packet to be transmitted by the optical communication device and path status data of each transmission path of the optical communication device.

The adaptive depacketizing unit 520 is used to adaptively split the target data packet into corresponding sub-data packet groups according to the content-aware information of the target data packet, and select at least one key sub-data packet from the sub-data packet groups.

The code attaching unit 530 is used to determine the forward error correction code corresponding to each of the key sub-data packets, and attach the forward error correction code to the key sub-data packet, so as to determine the target sub-data packet group according to the updated sub-data packet group.

The path division unit 540 is used to determine the optimal transmission path according to the path state data of each of the transmission paths, and determine the target transmission path corresponding to each target sub-data packet in the target sub-data packet group;

The transmission unit 550 is used to respectively transmit the corresponding sub-data packets in the target sub-data packet group using each of the target transmission paths, and to transmit each forward error correction code and a path identifier of the corresponding target transmission path using the optimal transmission path.

In some embodiments, an embodiment of the present application provides a non-volatile computer-readable storage medium, in which one or more programs including execution instructions are stored, and the execution instructions can be read and executed by an electronic device (including but not limited to a computer, a server, or a network device, etc.) to execute the steps of any of the above-mentioned multipath signal transmission methods in an optical communication network of the present application.

In some embodiments, the embodiments of the present application also provide a computer program product, which includes a computer program stored on a non-volatile computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer performs the steps of any one of the above-mentioned multipath signal transmission methods in an optical communication network.

In some embodiments, the embodiments of the present application also provide an electronic device, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the steps of the multipath signal transmission method in an optical communication network.

FIG6 is a schematic diagram of the hardware structure of an electronic device for executing a multipath signal transmission method in an optical communication network provided by another embodiment of the present application. As shown in FIG6 , the device includes:

One or more processors 610 and a memory 620 , with one processor 610 being taken as an example in FIG. 6 .

The apparatus for executing the multipath signal transmission method in an optical communication network may further include: an input device 630 and an output device 640 .

The processor 610, the memory 620, the input device 630 and the output device 640 may be connected via a bus or other means, and FIG6 takes the connection via a bus as an example.

The memory 620, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as program instructions/modules corresponding to the multi-path signal transmission method in the optical communication network in the embodiment of the present application. The processor 610 executes various functional applications and data processing of the server by running the non-volatile software programs, instructions and modules stored in the memory 620, that is, the multi-path signal transmission method in the optical communication network in the above method embodiment is implemented.

The memory 620 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 620 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 620 may optionally include a memory remotely arranged relative to the processor 610, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

The input device 630 can receive input digital or character information and generate signals related to user settings and function control of the electronic device. The output device 640 can include a display device such as a display screen.

The one or more modules are stored in the memory 620, and when executed by the one or more processors 610, the multipath signal transmission method in the optical communication network in any of the above method embodiments is executed.

The above-mentioned product can execute the method provided in the embodiment of the present application, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not fully described in this embodiment, please refer to the method provided in the embodiment of the present application.

The electronic devices of the embodiments of the present application exist in various forms, including but not limited to:

(1) Mobile communication equipment: This type of equipment is characterized by having mobile communication functions and its main purpose is to provide voice and data communications. This type of terminal includes: smart phones, multimedia phones, functional phones, and low-end phones.

(2) Ultra-mobile personal computer devices: These devices belong to the category of personal computers, have computing and processing functions, and generally also have mobile Internet access features. These terminals include: PDA, MID and UMPC devices, etc.

(3) Portable entertainment devices: These devices can display and play multimedia content. They include audio and video players, handheld game consoles, e-books, smart toys, and portable car navigation devices.

(4) Other onboard electronic devices with data interaction functions, such as on-board devices installed in vehicles.

The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution, in essence or in other words, the part that contributes to the relevant technology, can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some of the technical features therein with equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims (10)

1. A multipath signal transmission method in an optical communication network, comprising: Acquire a target data packet to be transmitted by an optical communication device and path state data of each transmission path of the optical communication device; Adaptively splitting the target data packet into corresponding sub-data packet groups according to content-aware information of the target data packet, and selecting at least one key sub-data packet from the sub-data packet groups; For each of the key sub-data packets, determine a forward error correction code corresponding to the key sub-data packet, and append the forward error correction code to the key sub-data packet, so as to determine a target sub-data packet group according to the updated sub-data packet group; Determine an optimal transmission path according to the path state data of each of the transmission paths, and determine a target transmission path corresponding to each target sub-data packet in the target sub-data packet group; The corresponding sub-data packets in the target sub-data packet group are transmitted respectively by using each of the target transmission paths, and each forward error correction code and the path identifier of the corresponding target transmission path are transmitted by using the optimal transmission path. 2. The method according to claim 1, wherein the step of determining the target transmission path corresponding to each target sub-data packet in the target sub-data packet group comprises: Acquire packet attribute data of each target sub-data packet in the target sub-data packet group; the packet attribute data includes a key sub-data packet identifier, a content type, and a required transmission bandwidth of the target sub-data packet; Screening out the optimal transmission path from the various transmission paths to update them into various candidate transmission paths; For each of the target sub-data packets, according to the packet attribute data of the target sub-data packet and the path state data of each of the candidate transmission paths, the packet content impact factor of the target sub-data packet relative to each of the candidate transmission paths is calculated to obtain a corresponding packet content impact factor matrix; According to the packet content influence factor matrix of each of the target sub-data packets, the target transmission path corresponding to each of the target sub-data packets is determined. 3. The method according to claim 2, wherein the calculating the packet content impact factor of the target sub-data packet relative to each candidate transmission path comprises: In the formula, Indicates the target sub-packet In the candidate transmission path The impact factor of the package content on and Represents the target sub-packet In the candidate transmission path The key influencing factors, content type influencing factors and bandwidth demand influencing factors on the network; represents the critical weight coefficient; express The key sub-packet identifier of For key sub-packets, ,otherwise ; express transmission delay; for The inverse of the packet loss rate; is a preset constant; Indicates the content type weight coefficient, express Content Type The corresponding delay sensitivity weight, express Content Type The bandwidth sensitivity weight of express Content Type The bit error rate sensitivity weight of express Available bandwidth, express bit error rate; represents the bandwidth demand weight coefficient, express The required bandwidth, express The total bandwidth capacity of express The current bandwidth utilization of the 4. The method according to claim 3, wherein before calculating the packet content impact factor of the target sub-data packet relative to each candidate transmission path, the method further comprises: Parsing the target content type corresponding to the target sub-data packet; Determine the delay sensitivity weight, bandwidth sensitivity weight and bit error rate sensitivity weight that match the target content type according to the content sensitivity weight table; the content sensitivity weight table records multiple content types and corresponding sensitivity weight settings, and the sensitivity weight settings include calibrated delay sensitivity weights, bandwidth sensitivity weights and bit error rate sensitivity weights. 5. The method according to claim 3, wherein determining the target transmission path corresponding to each target sub-data packet according to the packet content impact factor matrix of each target sub-data packet comprises: Constructing a bipartite graph; the bipartite graph includes a data packet vertex set and a path vertex set, the data packet vertex set is defined by all target sub-data packets, and the path vertex set is defined by all candidate transmission paths; configuring the edge weights of the bipartite graph based on each of the packet content impact factor matrices; wherein the edge weights between each data packet vertex and a path vertex in the bipartite graph are determined by the corresponding packet content impact factor; Processing a bipartite graph based on a maximum matching algorithm to determine a maximum weight matching edge set between the data packet vertex set and the path vertex set; the matching edge set corresponding to the maximum weight matching edge set has the maximum total edge weight; According to the maximum weight matching edge set, a target transmission path corresponding to each target sub-data packet is determined. 6. The method according to claim 5, wherein the maximum matching algorithm is an improved KM algorithm. The method of processing the bipartite graph based on a maximum matching algorithm to determine a maximum weight matching between a first side vertex set and a second side vertex set includes: Perform vertex matching state initialization operations, including: Create an initial empty set of matches , For the data packet vertex set Each vertex in , select and The connected maximum edge weight is used as the initial label: In the formula, Indicates the target sub-packet The corresponding data packet vertex; Represents a packet vertex The initial label of For the path vertex set Each vertex in , initialize the label , In the formula, Indicates candidate transmission paths The corresponding path vertex; Represents the path vertex The initial label of Execute the main loop operation to iteratively find augmenting paths to increase the total edge weight of the matching edge set; the operation of each iteration is as follows: Mark the access status of each data packet vertex and each path vertex, The heuristic function is used to calculate the heuristic value of each unmatched data packet vertex. The heuristic function formula is: In the formula, and are the factor adjustment weights, Represents a packet vertex The heuristic value of Select the unmatched data packet vertex with the largest corresponding heuristic value as the initial data packet vertex for augmented path search. Use breadth-first search to find the augmenting path from the initial packet vertex. During the search, for each edge The search criteria are: If an augmenting path is found, reverse the matched and unmatched edges in the augmenting path and add the unmatched edges on the augmenting path to the matching set. , and remove the original matching edges ; If no augmenting path is found, update each vertex label to narrow the gap between unmatched points and matched points, so as to provide conditions for the next round of augmenting path search; the updated calculation rule is: In the formula, represents the minimum adjustment to update vertex labels to ensure that the path and data packets Minimize the differences in package content impact factors between them; For visited , update the corresponding data packet vertex label by the following formula: For visited , update the corresponding path vertex labels by: When it is detected that the total edge weight of the matching edge set determined by iteration exceeds the preset number of iterations and does not increase, the iteration is stopped and the current matching set is Output the maximum weight matching edge set. 7. The method according to any one of claims 1 to 6, wherein the step of adaptively splitting the target data packet into corresponding sub-data packet groups according to content-aware information of the target data packet comprises: When the target data packet is a video data packet, first content perception information corresponding to the video data packet is determined, and the video data packet is adaptively split into corresponding sub-data packet groups according to the first content perception information; the first content perception information is the number of edge pixels and the range of motion vectors of a video frame; When the target data packet is an audio data packet, determining second content perception information corresponding to the audio data packet, and adaptively splitting the audio data packet into corresponding sub-data packet groups according to the second content perception information; the second content perception information is an audio spectrum bandwidth and an audio energy distribution; When the target data packet is a text data packet, third content-aware information corresponding to the text data packet is determined, and the text data packet is adaptively split into corresponding sub-data packet groups according to the third content-aware information; the third content-aware information includes text semantic density and keyword frequency. 8. The method according to claim 7, wherein determining the forward error correction code corresponding to the key sub-data packet comprises: Adaptively determining a corresponding target redundancy according to content perception information of the key sub-data packet; Encoding the key sub-data packet according to the target redundancy and the packet type of the key sub-data packet to determine a forward error correction code corresponding to the corresponding key sub-data packet; the packet type includes any one of the following: a video type, an audio type, and a text type; Among them, the key sub-packets of the video type are encoded by RS, the key sub-packets of the audio type are encoded by LDPC, and the key sub-packets of the text type are encoded by Hamming. 9. The method according to any one of claims 1-6, wherein the path status data comprises at least one of the following: path available bandwidth, path delay, path packet loss rate, path bit error rate, path signal attenuation level and signal interference strength. 10. A multipath signal transmission system in an optical communication network, comprising: an acquisition unit, configured to acquire a target data packet to be transmitted by the optical communication device and path state data of each transmission path of the optical communication device; an adaptive depacketizing unit, configured to adaptively split the target data packet into corresponding sub-data packet groups according to content-aware information of the target data packet, and select at least one key sub-data packet from the sub-data packet groups; A code attaching unit, configured to determine, for each of the key sub-data packets, a forward error correction code corresponding to the key sub-data packet, and attach the forward error correction code to the key sub-data packet, so as to determine a target sub-data packet group according to the updated sub-data packet group; A path division unit, used to determine an optimal transmission path according to the path state data of each of the transmission paths, and determine a target transmission path corresponding to each target sub-data packet in the target sub-data packet group; The transmission unit is used to respectively transmit the corresponding sub-data packets in the target sub-data packet group by using each of the target transmission paths, and to transmit each forward error correction code and a path identifier of the corresponding target transmission path by using the optimal transmission path.