Multi-protocol data flow routing control method and system

Abstract

The present application provides a routing control method and system for a multi-protocol data stream, which relates to the field of optical communication data transmission. The method includes: obtaining the data protocol type and content perception information corresponding to each real-time data stream to be transmitted by an optical communication device; determining a target protocol stack that matches the data protocol type of the real-time data stream, and preprocessing the real-time data stream according to the target protocol stack; obtaining the path attribute data of each transmission path in the optical communication device; determining the fitness matrix of the preprocessed real-time data stream relative to each transmission path according to the path attribute data of each transmission path and the content perception information and data protocol type of the data stream; and assigning a corresponding target transmission path to each preprocessed real-time data stream according to each fitness matrix. Thus, the network transmission requirements of data streams from different applications and services can be flexibly handled, and the transmission quality of data in the optical communication network can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of optical communication data transmission, and in particular to a routing control method and system for multi-protocol data streams. Background Art

[0002] In optical communication networks, high-speed data transmission and low latency are its significant advantages, making optical communication the core technology of modern communication systems. Currently, optical communication networks mostly use a single-protocol routing control mechanism, usually using a fixed protocol to manage the transmission of data streams. However, with the rapid growth in the types and number of data streams, the traditional single-protocol routing method has been unable to meet the diverse transmission needs.

[0003] In particular, in modern network environments, data streams often come from different applications and services, which may use different transmission protocols (such as HTTP, FTP, etc.). Traditional single-protocol routing control mechanisms usually require protocol conversion when processing multi-protocol data streams, which not only increases the complexity and latency of the system, but may also cause data loss or errors during the conversion process, affecting the quality and reliability of communication.

[0004] In response to the above problems, the industry has not yet proposed a better technical solution. Summary of the invention

[0005] The present application provides a routing control method, system, storage medium, computer program product and electronic device for a multi-protocol data stream, which are used to at least solve the problem of low efficiency and high data loss rate of optical communication devices in the current related technology when transmitting multi-protocol data streams.

[0006] In a first aspect, an embodiment of the present application provides a routing control method for a multi-protocol data stream, comprising: obtaining a data protocol type and content-aware information corresponding to each real-time data stream to be transmitted by an optical communication device; the content-aware information includes a data load type and a data sensitivity level; for each of the real-time data streams, determining a target protocol stack that matches the data protocol type of the real-time data stream from a multi-protocol stack pre-set in the optical communication device, and preprocessing the real-time data stream according to the target protocol stack; the multi-protocol stack includes a plurality of protocol stacks, and each protocol stack defines a data processing specification for a data stream of a corresponding protocol type; obtaining path attribute data of each transmission path in the optical communication device; the path attribute data includes an available bandwidth, a transmission delay, a packet loss rate, and a supported protocol type of the transmission path; for each preprocessed real-time data stream, determining an adaptation matrix of the preprocessed real-time data stream relative to each transmission path according to the path attribute data of each transmission path and the content-aware information and data protocol type of the preprocessed real-time data stream; and according to each of the adaptation matrices, assigning a corresponding target transmission path to each of the preprocessed real-time data streams.

[0007] In a second aspect, an embodiment of the present application provides a routing control system for a multi-protocol data stream, comprising: an acquisition unit, for acquiring a data protocol type and content-aware information corresponding to each real-time data stream to be transmitted by an optical communication device; the content-aware information includes a data load type and a data sensitivity level; a protocol stack processing unit, for determining, for each of the real-time data streams, a target protocol stack that matches the data protocol type of the real-time data stream from a multi-protocol stack pre-set in the optical communication device, and pre-processing the real-time data stream according to the target protocol stack; the multi-protocol stack includes a plurality of protocol stacks, and each protocol stack defines a data processing function for a data stream of a corresponding protocol type. specification; a path information acquisition unit, used to acquire path attribute data of each transmission path in the optical communication device; the path attribute data includes available bandwidth, transmission delay, packet loss rate and supported protocol type of the transmission path; an adaptation matrix determination unit, used to determine the adaptation matrix of the preprocessed real-time data stream relative to each transmission path for each preprocessed real-time data stream according to the path attribute data of each transmission path and the content perception information and data protocol type of the preprocessed real-time data stream; a target path allocation unit, used to allocate corresponding target transmission paths to each preprocessed real-time data stream according to each adaptation matrix.

[0008] 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 routing control method for a multi-protocol data stream of any embodiment of the present application.

[0009] In a fourth aspect, an embodiment of the present application provides a storage medium on which a computer program is stored, characterized in that when the program is executed by a processor, the steps of the routing control method for a multi-protocol data stream of any embodiment of the present application are implemented.

[0010] 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 routing control method for a multi-protocol data stream of any embodiment of the present application.

[0011] The multi-protocol data flow routing control method and system provided by the present application can produce at least the following technical effects:

[0012] (1) Through the introduction of multiple protocol stacks and a preprocessing mechanism based on content-aware information, accurate management of data streams of different protocol types is achieved. By using the corresponding protocol stack for preprocessing of data streams of different protocol types, unnecessary protocol conversion processes are avoided, potential risks of data in the protocol conversion process are eliminated, the probability of data loss and errors is significantly reduced, and the flexibility and overall transmission efficiency of multi-protocol data stream transmission are improved. In addition, in the routing control stage, by obtaining the path attribute data of each transmission path and combining the content-aware information and data protocol type of the real-time data stream, the adaptation matrix between each data stream and each transmission path can be calculated, fully considering the key factors of the transmission path, such as the available bandwidth, transmission delay, and packet loss rate, to ensure that the data stream can select the optimal transmission path, further optimizing the transmission performance.

[0013] (2) By conducting a comprehensive global analysis of the fitness matrices of different data streams, the transmission path resources are dynamically allocated within the global scope of the optical communication device according to the specific needs of each data stream, and the optimal path is automatically selected, thus avoiding resource waste and conflicts, thereby improving the overall utilization of network resources and meeting diverse transmission needs.

[0014] Through this technical solution, the comprehensive application of multiple protocol stacks, content-aware mechanisms and path resource monitoring technologies can flexibly handle the network transmission requirements of data streams from different applications and services, and comprehensively consider the content-aware information of the data stream and the actual transmission capacity of the path, so as to more reasonably allocate transmission resources, thereby effectively improving the reliability and stability of data communications. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below 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.

[0016] Figure 1 A flowchart showing an example of a routing control method for a multi-protocol data stream according to an embodiment of the present application is shown;

[0017] Figure 2 An operation flow chart showing an example of obtaining a data protocol type for a real-time data stream according to an embodiment of the present application is shown;

[0018] Figure 3 An operation flow chart of an example of obtaining content-aware information of a real-time data stream according to an embodiment of the present application is shown;

[0019] Figure 4 An operation flow chart of an example of determining the fitness matrix of each data stream according to an embodiment of the present application is shown;

[0020] Figure 5 A flowchart showing an example of allocating a target transmission path for a data stream according to an adaptability matrix according to an embodiment of the present application is shown;

[0021] Figure 6 A structural block diagram showing an example of a routing control system for multi-protocol data streams according to an embodiment of the present application is shown;

[0022] Figure 7 It is a schematic structural diagram of an embodiment of an electronic device of the present application. DETAILED DESCRIPTION

[0023] 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.

[0024] 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.

[0025] It should be noted that in order to solve some problems in multi-protocol data stream transmission, some experts and scholars in the industry have proposed some potential solutions, such as technical content that may not be fully disclosed to the public, specifically including Multi-Protocol Label Switching (MPLS) and Software Defined Network (SDN).

[0026] Specifically, MPLS technology inserts labels between the network layer and the data link layer to quickly forward data packets, providing high transmission efficiency and flexibility. However, MPLS mainly relies on static label allocation and preset paths, and is not adaptable enough to dynamically changing network environments, and cannot optimize the transmission path of data streams in real time. In addition, the implementation and maintenance costs of MPLS are high, and the consumption of network resources is large.

[0027] In addition, SDN technology achieves centralized control and management of network resources by separating the network control plane from the data forwarding plane, providing higher network flexibility. However, SDN technology still has shortcomings in processing multi-protocol data streams, mainly reflected in protocol compatibility issues. At the same time, SDN is highly dependent on network controllers. When the controller fails, the performance of the entire network may be seriously affected.

[0028] Therefore, the transmission of multi-protocol data streams in existing optical communication networks faces many challenges and limitations, and there is an urgent need for a more efficient routing control method for multi-protocol data streams to improve the transmission efficiency, resource utilization and adaptability of the network.

[0029] In view of this, Figure 1 A flowchart of an example of a method for routing control of a multi-protocol data stream according to an embodiment of the present application is shown.

[0030] Regarding the execution subject of the method of the embodiment of the present application, it can be any controller or processor with computing or processing capabilities. By introducing multiple protocol stacks and global optimization calculation of path adaptability, it not only improves the processing capability of diversified data streams, but also effectively improves the transmission efficiency and reliability of the optical communication network.

[0031] In some examples, it may be integrated and configured in an electronic device, terminal or server through software, hardware or a combination of software and hardware, and the types of the terminal, electronic device or server may be diverse, such as a mobile phone, tablet computer or desktop computer, etc.

[0032] like Figure 1As shown, in step S110, the data protocol type and content-aware information corresponding to each real-time data stream to be transmitted by the optical communication device are obtained, and the content-aware information includes a data load type and a data sensitivity level.

[0033] In some embodiments, the optical communication device can monitor and identify all real-time data streams to be transmitted, which may come from different applications or services and have different data protocol types, such as HTTP, FTP, RTSP, VoIP, etc.

[0034] Content-aware information includes data payload type and data sensitivity level. On the one hand, data payload type can refer to the specific nature of the data, such as video, text, audio, image, etc. In addition, data payload type can also refer to the scene type of the data, such as entertainment content, work content, etc. On the other hand, data sensitivity level refers to the security or sensitivity of the data, such as financial data with high security requirements. In addition, encrypted data in the data stream header information can also indicate a high data sensitivity level to a certain extent.

[0035] In step S120, for each real-time data stream, a target protocol stack matching the data protocol type of the real-time data stream is determined from the multiple protocol stacks preset in the optical communication device, and the real-time data stream is preprocessed according to the target protocol stack.

[0036] It should be noted that in modern optical communication networks, different data flows correspond to different applications or services, and may involve multiple transmission protocols (such as HTTPS, VoIP, VPN, etc.), each of which has its own unique requirements and characteristics. Specifically, HTTPS protocol traffic usually requires efficient web content transmission and often involves encryption. VoIP protocol traffic requires low latency and high real-time performance to ensure the quality of voice and video calls. VPN protocol traffic focuses on data security and confidentiality, and transmits sensitive information through encrypted tunnels.

[0037] Here, the multi-protocol stack includes multiple protocol stacks, and each protocol stack defines the data processing specifications for the data stream of the corresponding protocol type. It should be noted that the multi-protocol stack allows the system to support multiple protocols at runtime and switch between different protocols when necessary. Each protocol stack contains all the functional modules required to process the protocol, such as protocol parsing, data encapsulation, error handling, etc., to ensure that each optical communication node can process data streams of multiple protocols, load the corresponding protocol stack as needed, and dynamically adapt according to the protocol type of the data stream at runtime.

[0038] Specifically, once the protocol type of the data stream is identified, the optical communication device will find the best matching target protocol stack in the multiple protocol stacks and use the rules and specifications in the protocol stack to pre-process the data stream. For example, for a video stream, a stack that supports the RTSP protocol may be selected to handle the encapsulation and transmission parameter settings of the stream.

[0039] In some embodiments, when the optical communication device transmits multiple real-time data streams of different data protocol types in parallel, it can use the corresponding protocol stack to pre-process the corresponding real-time data streams respectively, and then control the routing of each pre-processed real-time data stream to the corresponding transmission path for transmission. In this way, by using the built-in multi-protocol stack, when transmitting multi-protocol data streams, it can flexibly adapt to various protocol types without the need for cross-protocol conversion operations, effectively reducing transmission delays and information loss during data conversion.

[0040] It should be noted that the types of stacks in the multi-protocol stack can be diverse and can be adjusted or optimized according to the actual network transmission business needs. For example, the multi-protocol stack includes RTSP protocol stack, FTP protocol stack, HTTP / HTTPS protocol stack, VoIP protocol stack and VPN / IPsec protocol stack. Through the multi-protocol stack, special security processing can be provided for specific data streams. For example, the VPN / IPsec protocol stack specializes in processing encrypted traffic to ensure the secure transmission of sensitive data. Therefore, the separate processing method can prevent interference between different protocols and improve the stability and security of multi-protocol data transmission.

[0041] In step S130, path attribute data of each transmission path in the optical communication device is obtained.

[0042] In some embodiments, the path attribute data of each transmission path in the optical communication device is collected in real time through the network monitoring module, and the path attribute data includes the available bandwidth, transmission delay, packet loss rate and supported protocol type of the transmission path. In addition, the collection of path attribute data can be achieved through network measurement tools and data acquisition devices, and updated in real time through the network management system to ensure the high timeliness of the acquired data. Therefore, by updating the sampled path attribute data in real time, the system can accurately grasp the current transmission capacity and status of each path, and ensure the accuracy of data flow routing control selection.

[0043] In step S140, for each preprocessed real-time data stream, the adaptability matrix of the preprocessed real-time data stream relative to each transmission path is determined according to the path attribute data of each transmission path and the content perception information and data protocol type of the preprocessed real-time data stream.

[0044] In some embodiments, the fitness matrix is ​​generated based on the following factors: the degree of match between the available bandwidth of the transmission path and the data load type, the requirements of the transmission delay and the data sensitivity level, the impact of the packet loss rate on the reliability of the data flow, and the compatibility of the path support protocol type and the data protocol type. In addition, the fitness can be calculated by weighted comprehensive evaluation of these factors to better reflect the advantages and disadvantages of each transmission path relative to each real-time data flow. In this way, the fitness matrix is ​​used to achieve a quantitative evaluation of the transmission effect of each data flow on different paths.

[0045] In step S150, a corresponding target transmission path is allocated to each pre-processed real-time data stream according to each adaptation matrix.

[0046] In some embodiments, the path allocation process can be implemented by an optimization algorithm (such as dynamic programming, genetic algorithm, etc.) to ensure that the data stream is transmitted on the optimal path. In addition, in the path allocation process, multiple path conflict allocation situations should be fully considered. For example, when multiple data streams may choose the same path at the same time, the system can determine the final allocation of the data stream according to specific strategies (such as priority sorting, load balancing, etc.) to ensure the optimal utilization of path resources. Therefore, by performing a comprehensive global analysis of the fitness matrix of each data stream and automatically matching the corresponding optimal path through optimization calculation, resource waste and conflict are avoided, thereby improving the overall utilization of network resources and the transmission efficiency of multi-protocol data.

[0047] Figure 2 An operational flow chart showing an example of obtaining a data protocol type for a real-time data stream according to an embodiment of the present application is shown.

[0048] like Figure 2 As shown, in step S210, a sample data packet is intercepted from the real-time data stream, and is matched with a predefined protocol type library based on a protocol identifier in a packet header of the sample data packet. The protocol type library contains multiple calibration protocol identifiers and corresponding calibration data protocol types.

[0049] In some embodiments, after receiving the real-time data stream, the optical communication device will intercept one or more sampled data packets from the data stream. These data packets are usually the starting packets of the data stream (such as handshake packets) or packets with specific protocol characteristics (such as HTTP request packets). Then, the packet header information of these sampled data packets is analyzed to find the protocol identifiers therein. The protocol identifiers are usually fields such as the protocol number and port number in the data packet header, which are used to identify the protocol used by the data packet. After that, the extracted protocol identifiers are matched with the pre-established protocol type library. The protocol type library stores identifiers of multiple common protocols and their corresponding protocol types (such as HTTP, FTP, VoIP, etc.). The library can be updated regularly to ensure the matching capability with the diverse protocol types of the network.

[0050] In step S221, if there is a matching calibration protocol identifier, the calibration data protocol type corresponding to the matching calibration protocol identifier is determined as the data protocol type of the real-time data stream.

[0051] In some implementations, after successfully matching the protocol identifier, the corresponding calibration data protocol type in the protocol type library is assigned to the data stream as its formal protocol type. Thereafter, the data stream will select an appropriate protocol stack for data preprocessing according to the matched protocol type during subsequent processing and transmission.

[0052] Through the embodiments of the present application, the protocol identifier in the packet header of the key data packet is first matched with the predefined protocol type library. If there is a matching calibrated protocol identifier, the protocol type of the data stream can be quickly and accurately determined, and most common protocols can be effectively processed, thereby improving the accuracy and efficiency of identification.

[0053] In step S223, if there is no matching calibration protocol identifier, the payload feature of the sampled data packet is extracted, and the feature vector corresponding to the payload feature is calculated. The cosine similarity between each protocol feature vector in the protocol feature database.

[0054] It should be noted that the payload is the part of the data packet other than the header, which usually contains application layer data, such as HTTP request content, FTP commands, VoIP data, etc. Protocol features are extracted by parsing these data. In the feature extraction process, the payload is divided into multiple fixed-length blocks, and important protocol feature fields such as handshake information are extracted from each block, and the extracted feature data is then converted into feature vectors. ,and Each element in represents the frequency or weight of a specific feature in the payload. Then, the cosine similarity between the feature vector and each protocol feature vector in the protocol feature database is calculated. The protocol feature database contains feature vectors of pre-calibrated protocol types, which represent the characteristic patterns of different protocol types.

[0055] Specifically, the calculation process of cosine similarity is as follows:

[0056] , formula (1);

[0057] In the formula, express With The protocol feature vector corresponding to the protocol type The cosine similarity between and Respectively and Model.

[0058] When no calibrated protocol identifier is matched, the payload features of key data packets are extracted, and the cosine similarity between the payload feature vector and each protocol feature vector in the protocol feature database is calculated to deeply analyze the actual content of the data packet, enabling the system to identify more complex or non-standard protocol types, such as custom protocols or tunnel-encapsulated protocols.

[0059] In step S233, the target protocol feature vector corresponding to the maximum cosine similarity is screened, and when it is determined that the maximum cosine similarity exceeds the similarity threshold, the protocol type corresponding to the target protocol feature vector is used as the data protocol type of the real-time data stream.

[0060] Specifically, the protocol feature vector with the largest cosine similarity is taken as a candidate target. If the maximum cosine similarity exceeds the preset similarity threshold (for example, 0.8 or 0.9), the protocol type corresponding to the target protocol feature vector is determined as the protocol type of the real-time data stream. If the maximum cosine similarity does not reach the threshold, it is considered that the protocol type of the data stream cannot be determined by the current feature matching, which may trigger an exception handling process or manual intervention. Therefore, by introducing the screening mechanism of the similarity threshold and the maximum cosine similarity, it is ensured that the protocol type selected by the system is the most matching with the data stream characteristics, thereby improving the high accuracy of the data protocol type extraction of the data stream.

[0061] Through the embodiment of the present application, a two-level protocol identification method is adopted (i.e., matching the packet header identifier first, and then performing payload analysis), and the system can flexibly respond to various network environments and data flow types, and can maintain efficient identification capabilities even when facing encrypted traffic, tunnel protocols, or traffic using non-standard ports, with high adaptability and flexibility. In addition, as network protocols evolve, the ability to identify new protocols can be maintained by simply updating the protocol feature database accordingly, which has relatively good scalability.

[0062] Figure 3 An operational flowchart of an example of obtaining content-aware information for a real-time data stream according to an embodiment of the present application is shown.

[0063] like Figure 3 As shown, in step S310, context information, encryption status, content characteristics and vulnerability threat information of the real-time data stream are obtained.

[0064] Here, the context information includes at least one of the following: application identification, data flow historical transmission mode and data timestamp. In some embodiments, the application identification is used to identify the application or service to which the data flow belongs, such as a web browser, video conferencing software, file transfer service, etc. The historical transmission mode describes the transmission behavior of the data flow in the past, such as transmission frequency, data packet size, transmission delay, etc. By comparing the current data flow with the historical records, the behavior pattern of the data flow can be predicted. In addition, the data timestamp records the time information of the data flow, which can determine the time characteristics of the data flow and the corresponding application scenarios, such as working hours or non-working hours.

[0065] The encryption status refers to whether the data stream has been encrypted, for example, the encryption protocol used by the data stream is detected through the packet header information. Content features include keywords, file types, data formats, etc. contained in the data stream, which reflect the content nature of the data stream. Vulnerability threat information contains security risk information of the data stream. Specifically, by comparing the vulnerability and attack information with the characteristic information of the current data stream, it is possible to identify whether there is a potential security threat in the data stream. For example, if a vulnerability is widely exploited on a specific port number, the corresponding threat information can be identified based on the port number match. By introducing vulnerability threat information, the system can track and identify the latest security threats faced by the current data stream in real time, so that the system can promptly identify high-risk data streams.

[0066] In step S320, the data load type corresponding to the real-time data stream is determined according to the context information.

[0067] For example, when there is an application identifier of HTTP and the historical transmission mode is high-frequency large packet traffic, the data stream may be a video stream, and if the timestamp shows non-working hours, the business traffic may be an entertainment content type.

[0068] In step S330, the basic layer sensitivity score corresponding to the real-time data stream is determined according to the data protocol type and encryption status, the intermediate layer sensitivity score corresponding to the real-time data stream is determined according to the sensitivity risk analysis results of the content characteristics, and the advanced layer sensitivity score for the real-time data stream is determined according to the vulnerability threat information.

[0069] It should be noted that open protocols refer to widely used and highly standardized protocols, such as HTTP, FTP, etc., which may be more likely to become attack targets due to their wide application and open standards. In addition, since proprietary protocols are not widely used and have a smaller attack surface, they may have a lower base layer sensitivity score in some cases.

[0070] In some embodiments, the system calculates the base layer sensitivity score based on the data protocol type (such as HTTP, FTP, VoIP) and encryption status (such as unencrypted, TLS encryption, IPsec encryption). The stronger the encryption status, the higher the sensitivity score. The middle layer sensitivity score is calculated by analyzing content features (such as sensitive words in the text, file type, data format, etc.). The presence of sensitive information (such as passwords, personal identity information) will increase the middle layer score. The high-level sensitivity score is calculated based on externally acquired vulnerability threat information (such as currently active attack types, vulnerability exploitation, etc.). Data streams related to known vulnerabilities will receive higher high-level scores, which can identify and prevent potential attacks in advance. For example, when a data stream is detected to be threatened by a known vulnerability, its sensitivity level can be immediately increased, and protective measures can be taken, such as restricting access, encrypting transmission, or triggering security alarms.

[0071] Here, the sensitivity of data flow is evaluated hierarchically based on data protocol type and encryption status, middle-layer content feature analysis, and high-level security threat information. Through this multi-level evaluation mechanism, it can dynamically respond to different types of security risks, allowing the system to flexibly respond to various complex network environments and ensure that the judgment of data flow sensitivity level is more comprehensive and accurate.

[0072] In step S340, the data sensitivity level corresponding to the real-time data stream is determined based on the basic layer sensitivity score, the intermediate layer sensitivity score and the advanced layer sensitivity score.

[0073] In some implementations, the sensitivity scores of the basic layer, the intermediate layer, and the advanced layer are weighted and comprehensively calculated to obtain the data sensitivity level of the data flow. By accurately identifying the load type and sensitivity level of the data flow, more targeted resource allocation is supported. For example, data flows with high sensitivity levels can be processed first, encrypted more strongly, or deeply reviewed, while data flows with low sensitivity levels can be processed with simplified processing procedures, which not only improves processing speed, but also improves resource utilization efficiency.

[0074] Figure 4 An operational flow chart of an example of determining the fitness matrix of each data stream according to an embodiment of the present application is shown.

[0075] like Figure 4 As shown, in step S410, a content-aware comprehensive score corresponding to the data stream is calculated based on the content-aware information of the preprocessed real-time data stream.

[0076] More specifically, the content-aware comprehensive score corresponding to each data stream is calculated by the following formula:

[0077] , formula (2);

[0078] , formula (3);

[0079] , formula (4);

[0080] In the formula, It is a data stream The content-aware composite score, A characteristic value representing the data payload type of the data stream, Indicates the content feature weight corresponding to the data payload type; Representing data flow The basic score corresponding to the data load type, Representing data flow Load type calibration weights; Representing data flow The characteristic value of the data sensitivity level, Indicates the content feature weight corresponding to the data sensitivity level; Indicates the data sensitivity level of the data flow. Indicates the maximum sensitivity level of the system. Represents the sensitivity importance coefficient.

[0081] here, and The value of can be preset according to business needs, allowing the influence of load characteristics and sensitivity level characteristics to be adjusted according to the needs of different scenarios, thus improving the adaptability of system decision-making. It is calculated based on the specific load type of the data flow (such as video streaming, file transfer, voice call, etc.), reflecting the requirements of this type of data flow for network resources. It can be pre-calibrated based on empirical data or statistical analysis to reflect the general demand of this type of data flow for transmission path resources (such as bandwidth and delay). For example, the load type score of video flow may be higher because it has higher requirements for bandwidth and delay. It can be adaptively set according to the data load type, for example, for high-definition video streaming, , while for text data streams, . It is a coefficient that measures the importance of data sensitivity. It determines the weight of the data flow sensitivity level in the entire routing selection process. Data flows with higher data sensitivity levels also require higher security and more precise path control. The value of is correspondingly higher.

[0082] Through this embodiment, when evaluating the content perception information of the data flow, not only the load characteristics of the data flow are considered, but also the sensitivity level of the data flow is taken as an important factor. Comprehensive evaluation is performed to more accurately reflect the actual needs of the data flow, which helps to achieve more reasonable path selection.

[0083] In step S420, the protocol adaptability score of the preprocessed real-time data stream relative to each transmission path is calculated according to the data protocol type of the preprocessed real-time data stream and the path attribute data of each transmission path.

[0084] , formula (5);

[0085] In the formula, Is the data flow in the transmission path The protocol fitness score on Represents the total number of path attribute features; Indicates The influence weight of each path attribute; Representing data flow Protocol type With Path attribute features Compatibility scores between

[0086] In some embodiments, as described above, the path attribute data includes the available bandwidth, transmission delay, packet loss rate and supported protocol types of the transmission path. First, the data protocol type corresponding to the data stream should belong to the protocol type supported by the path. If it is a protocol type not supported by the path, the corresponding protocol adaptability score is 0. Then, the bandwidth compatibility, delay compatibility and packet loss rate compatibility between the path and the data stream are calculated. For bandwidth compatibility, if the available bandwidth of the path is greater than or equal to the minimum bandwidth required by the protocol type, the compatibility score is 1 (i.e., perfect match), and if the path bandwidth is less than the required bandwidth, the score is reduced proportionally. For delay compatibility, if the path delay is less than or equal to the maximum delay acceptable to the protocol type, the compatibility score is 1, and when the delay exceeds the acceptable range, the score decreases proportionally, with a minimum of 0. For packet loss rate compatibility, if the path packet loss rate is less than or equal to the maximum packet loss rate acceptable to the protocol type, the compatibility score is 1, and when it exceeds the acceptable packet loss rate range, the score decreases proportionally. Finally, these compatibility indicators are summarized by the influence weights of the corresponding path attributes to obtain the final protocol adaptability score. Therefore, by refining the protocol adaptability into multiple levels and calculating the adaptability scores between the protocol type and the path characteristics at different levels, the adaptability between each transmission path and a specific data stream can be evaluated more accurately.

[0087] In step S430, the fitness matrix corresponding to the preprocessed real-time data stream is calculated according to the content-aware comprehensive score and the fitness scores of each protocol.

[0088] , formula (6);

[0089] In the formula, and Respectively and The corresponding factor fusion weight, For data flow The fitness matrix of the data flow Through the transmission path The fitness score of .

[0090] Through the refined adaptation matrix construction method provided in the embodiment of the present application, the load characteristics, sensitivity level and protocol adaptability of the data flow are fully considered in the path selection, and detailed content-aware information evaluation and protocol adaptability calculation are achieved. By integrating the dual guarantees of content-aware comprehensive score and protocol adaptability score, the high quality of routing control of real-time data flow is guaranteed.

[0091] It should be noted that in the fitness calculation formula, the factor fusion weights and determine the influence of content-aware information and protocol fitness in the final fitness score. In one example, it can be set according to demand, while in other examples, it can also be dynamically adjusted according to the current network status and data flow requirements.

[0092] In some implementations, in order to implement dynamic weighted fitness calculation to ensure that the system can flexibly adjust the matching of data streams and transmission paths under different network conditions, the factor fusion weights may be determined by adopting a dynamic weight modulation mechanism:

[0093] , formula (7);

[0094] , formula (8);

[0095] , formula (9);

[0096] , formula (10);

[0097] In the formula, and It's time The dynamic fusion weight factor, and Respectively and The value at the current moment; and They represent the corresponding adjustment amplitude factors, which are used to control the amplitude of the weight change; and They represent dynamic adjustment functions based on network conditions and data flow requirements, respectively; Representing data flow In time The sensitivity level, Representing data flow time The load type score, and is the network condition weight factor, which determines the sensitivity level and load type. The impact of It is the transmission path In time The transmission delay, It is the transmission path In time Available bandwidth, Indicates the maximum available bandwidth value. and is the data flow demand weight factor, which determines the latency and bandwidth impact.

[0098] By dynamically merging weight factors and ,The system can dynamically adjust the weights of different factors in path selection according to the ,real-time network status and changes in data flow demand, and ,automatically adjust the optimal path selection strategy under different network conditions, ,making data flow transmission more efficient and stable.

[0099] Regarding the description of the dynamic adjustment mechanism of factor fusion weights, in some embodiments, when the system is started, the weight factor and The initial setting can be made based on empirical data or historical analysis results. Afterwards, as network conditions and data flow requirements change, the weight factor needs to be adjusted according to the actual situation. The dynamic adjustment process can refer to the above equations (7) to (10).

[0100] It should be noted that This reflects the importance of content-aware information in the current network environment. For example, when the sensitivity level of data streams increases, Should be increased to increase the weight of content-aware information in the fitness calculation. This reflects the importance of protocol adaptability in the current network environment. For example, when the delay of a path increases, It should be reduced to reduce the weight of protocol adaptability. In this way, in the case of highly sensitive data flows, the weight of content-aware information is increased, so that paths with higher security are preferred. In addition, in the case of high-latency paths, the weight of protocol adaptability is reduced to avoid selecting an unsuitable path for the data flow.

[0101] Through the embodiments of the present application, it is possible to adapt to the needs of different network scenarios. For example, in scenarios with high real-time requirements, more attention can be paid to delay factors, while in scenarios with large file transfers, more attention can be paid to bandwidth factors. This allows efficient transmission services to be provided in the face of a changing network environment, achieving better flexibility and being able to effectively handle various network emergencies.

[0102] Figure 5 A flowchart of an example of allocating a target transmission path for a data stream according to an adaptation matrix according to an embodiment of the present application is shown.

[0103] like Figure 5 As shown, in step S510, each fitness matrix is ​​fused to determine a corresponding global fitness matrix.

[0104] Specifically, the fitness matrix of all data streams Combined together to form a global fitness matrix ,in Each element of Representing data flow On the path The fitness score on the path takes into account multiple factors such as bandwidth, delay, and packet loss rate.

[0105] Specifically, the global fitness matrix It is expressed by the following formula:

[0106] , formula (11);

[0107] In the formula, represents the global fitness matrix, Indicates the total number of data flows, Indicates the total number of transmission paths.

[0108] In step S520, a matrix optimization calculation is performed on the global fitness matrix to determine an optimal path allocation combination, where the optimal path allocation combination includes target transmission paths that are matched to each pre-processed real-time data stream.

[0109] Here, the objective function used in matrix optimization calculation is:

[0110] , formula (12);

[0111] In the formula, is a binary variable, indicating the data flow Is the transmission path assigned? superior, Indicates allocation, Indicates no allocation; is the matrix element of the global fitness matrix, representing the data flow In the transmission path The fitness score on ; It is the sum of the fitness corresponding to the path allocation combination and is used to express the optimization objective function of the matrix optimization calculation.

[0112] Through the above objective function, we aim to find the global fitness matrix The optimal path allocation combination in maximizes the total fitness score. By constructing a global fitness matrix And calculate the objective function , the optimal path allocation combination can be found globally, and the solution that maximizes the sum of fitness can be found among all possible path allocation combinations, thereby optimizing the transmission efficiency and quality of the data stream as a whole.

[0113] The constraints used in matrix optimization calculation are:

[0114] , formula (13);

[0115] , formula (14);

[0116] , formula (15);

[0117] In the formula, and Respectively represent data flow Required bandwidth and required latency; and Respectively represent the transmission path Available bandwidth and transmission delay, For each data stream .

[0118] Through the above constraints, by imposing bandwidth constraints and delay constraints on the bandwidth requirements and delay requirements of each data flow on each path, it can ensure that the transmission requirements of each data flow are met, avoiding data flow transmission failure or quality degradation due to insufficient resources. In addition, each data flow is represented by a binary variable To indicate whether to select a certain path, each data stream can only be assigned to one path. Therefore, according to the optimal allocation scheme solved, each data stream is assigned to the corresponding target transmission path. The allocation scheme is determined by the final The value of is determined during the data stream transmission process, and the allocation plan can also be dynamically adjusted according to the real-time network status or changes in data stream information.

[0119] Through the embodiments of the present application, under the premise of ensuring that the transmission requirements of each data stream are met, the optimization algorithm can maximize the utilization of network resources through refined path selection, so that bandwidth and delay resources are optimally configured, reducing resource waste and improving the overall network operation efficiency. In addition, by optimizing the resource status of different paths and comprehensively considering factors such as packet loss rate and delay, it is possible to give priority to paths that perform better in these aspects, maintain efficient transmission performance in a complex and changeable network environment, and have good robustness.

[0120] Here, the types of optimization algorithms for matrix optimization calculations can be diverse. In one example of an embodiment of the present application, the above optimization problem can be modeled as a linear programming problem. By using a standard linear programming solver (such as CPLEX optimizer, Gurobi optimizer, etc.) to solve the linear programming problem, the optimal path allocation solution can be obtained. In another example of an embodiment of the present application, since the actual problem may be large in scale, various heuristic algorithms (such as genetic algorithms, ant colony algorithms, or simulated annealing algorithms, etc.) can be used to solve the optimization problem of the global matrix, and a near-optimal solution can be found within a reasonable time.

[0121] In some examples of the embodiments of the present application, an enhanced simulated annealing algorithm is used to perform matrix optimization calculations. By optimizing the global fitness matrix, the optimal transmission path can be selected for each data stream, ensuring that the transmission path is highly matched with the content perception information and protocol type of the data stream, and the path selection strategy is dynamically adjusted according to the sensitivity level of the data stream to ensure that highly sensitive data streams give priority to paths with higher security, reduce potential security risks, and significantly improve the transmission efficiency of the data stream, reduce delays, and reduce packet loss rates.

[0122] Specifically, the global fitness matrix is ​​processed by a greedy selection algorithm to select a transmission path that satisfies the constraint conditions and has the largest corresponding value for each data stream, thereby obtaining an initial path allocation combination.

[0123] , formula (16);

[0124] , formula (17);

[0125] In the formula, represents the initial path allocation combination, Represents the initial optimal path of the data flow.

[0126] Here, the path allocation combination with the highest fitness is selected from the global fitness matrix as the initial solution. ,choose Make The maximum and constraints are met, the initial path allocation combination Generated by the above greedy selection, although this combination may not be the global optimal, it provides a good starting point for subsequent optimization.

[0127] The simulated annealing algorithm is used to process the initial path allocation combination to iteratively search for the optimal path allocation combination, including:

[0128] Dynamically update the temperature of each iteration according to the iteration round:

[0129]

[0130] , formula (18);

[0131] In the formula, and Respectively represent The iteration and The temperature of the iteration; Indicates The temperature reduction coefficient at the iteration, Indicates the total number of iterations.

[0132] Based on the temperature adjustment mechanism, the search intensity can be dynamically adjusted according to the iterative process, so that the algorithm has a strong exploration ability in the early stage and gradually converges to the optimal solution in the later stage. By dynamically adjusting the temperature parameters, it can adapt to the changes in network status at different stages and maintain a high optimization efficiency.

[0133] In each iteration, randomly select The perturbation of path allocation for each data stream:

[0134] , formula (19);

[0135] , formula (20);

[0136] In the formula, represents the path allocation combination after disturbance, Indicates the path allocation combination for the current iteration A function for multidimensional perturbation, where is the set of perturbed data streams; represents the number of perturbation dimensions that are dynamically adjusted, represents the maximum value function, Represents a floor function.

[0137] Here, in each iteration, the algorithm adjusts the path selection through a multi-dimensional perturbation mechanism, which not only improves the algorithm's optimization speed, but also enables it to more flexibly adapt to the dynamic changes in network status and avoid the negative impact of excessive adjustment in one dimension on the overall performance.

[0138] Through dynamic temperature adjustment and multi-dimensional perturbation mechanism, the enhanced simulated annealing algorithm can avoid falling into the local optimal solution during the optimization process, and can effectively deal with the complexity and uncertainty of network status and data flow characteristics. In addition, in the face of network failures or emergencies, it can quickly readjust the path selection to maintain the continuity of data flow and transmission stability.

[0139] Calculate the sum of the fitness corresponding to the perturbed path allocation combination:

[0140] , formula (21);

[0141] In the formula, express The corresponding first fitness sum, Indicates the index of the transmission path after the disturbance.

[0142] If the sum of the first fitness degrees is greater than the sum of the second fitness degrees corresponding to the path allocation combination of the current iteration, the perturbed path allocation combination As the better solution for the current iteration. And, if the sum of the first fitness is not greater than the sum of the second fitness, then the acceptance probability (or annealing temperature probability) Decide whether to As a better solution for the current iteration.

[0143] , formula (22);

[0144] In the formula, represents the temperature of the current iteration, represents the exponential function, express The corresponding second fitness sum.

[0145] Through the dynamic path selection and load balancing strategies in the embodiments of the present application, network resources can be effectively allocated, and the resource allocation strategy can be dynamically adjusted according to the real-time network status and data flow characteristics to avoid overloading of certain paths and waste of resources on other paths. For bandwidth-sensitive and delay-sensitive data flows, resource paths that meet their needs can be preferentially allocated, and the resource utilization of the entire network can be optimized through dynamic load balancing.

[0146] 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.

[0147] Figure 6 A structural block diagram of an example of a routing control system for multi-protocol data streams according to an embodiment of the present application is shown.

[0148] like Figure 6As shown, the routing control system 600 for multi-protocol data flows includes an acquisition unit 610 , a protocol stack processing unit 620 , a path information acquisition unit 630 , an adaptability matrix determination unit 640 and a target path allocation unit 650 .

[0149] The acquisition unit 610 is used to acquire the data protocol type and content-aware information corresponding to each real-time data stream to be transmitted by the optical communication device; the content-aware information includes the data load type and the data sensitivity level.

[0150] The protocol stack processing unit 620 is used to determine, for each of the real-time data streams, a target protocol stack that matches the data protocol type of the real-time data stream from the multi-protocol stack pre-set in the optical communication device, and pre-process the real-time data stream according to the target protocol stack; the multi-protocol stack includes multiple protocol stacks, and each protocol stack defines a data processing specification for a data stream of a corresponding protocol type.

[0151] The path information acquisition unit 630 is used to acquire path attribute data of each transmission path in the optical communication device; the path attribute data includes available bandwidth, transmission delay, packet loss rate and supported protocol type of the transmission path.

[0152] The adaptability matrix determination unit 640 is used to determine the adaptability matrix of the preprocessed real-time data stream relative to each transmission path for each preprocessed real-time data stream based on the path attribute data of each transmission path and the content perception information and data protocol type of the preprocessed real-time data stream.

[0153] The target path allocation unit 650 is used to allocate a corresponding target transmission path to each of the pre-processed real-time data streams according to each of the adaptation matrices.

[0154] 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 multi-protocol data stream routing control methods of the present application.

[0155] 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 executes the steps of any one of the above-mentioned multi-protocol data stream routing control methods.

[0156] In some embodiments, an embodiment of the present application also provides 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 routing control method for multi-protocol data streams.

[0157] Figure 7 is a schematic diagram of the hardware structure of an electronic device for executing a routing control method for a multi-protocol data stream provided by another embodiment of the present application, such as Figure 7 As shown, the device includes:

[0158] One or more processors 710 and memory 720, Figure 7 A processor 710 is taken as an example.

[0159] The device for executing the routing control method for multi-protocol data streams may further include: an input device 730 and an output device 740 .

[0160] The processor 710, the memory 720, the input device 730 and the output device 740 may be connected via a bus or other means. Figure 7 The example of connecting through bus is taken in the following.

[0161] The memory 720, 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 routing control method for multi-protocol data streams in the embodiment of the present application. The processor 710 executes various functional applications and data processing of the server by running the non-volatile software programs, instructions and modules stored in the memory 720, that is, implementing the routing control method for multi-protocol data streams in the above method embodiment.

[0162] The memory 720 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 720 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 720 may optionally include a memory remotely arranged relative to the processor 710, 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.

[0163] The input device 730 may receive input digital or character information and generate signals related to user settings and function control of the electronic device. The output device 740 may include a display device such as a display screen.

[0164] The one or more modules are stored in the memory 720, and when executed by the one or more processors 710, the routing control method for multi-protocol data stream in any of the above method embodiments is executed.

[0165] 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.

[0166] The electronic devices of the embodiments of the present application exist in various forms, including but not limited to:

[0167] (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.

[0168] (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.

[0169] (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.

[0170] (4) Other onboard electronic devices with data interaction functions, such as on-board devices installed in vehicles.

[0171] 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.

[0172] 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 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 disk, an optical disk, etc., including 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 embodiment.

[0173] 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 make equivalent replacements for some of the technical features therein. 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

1. A routing control method for a multi-protocol data stream, comprising: Acquire data protocol type and content perception information corresponding to each real-time data stream to be transmitted by the optical communication device; The content-aware information includes data payload type and data sensitivity level; For each of the real-time data streams, determining a target protocol stack that matches the data protocol type of the real-time data stream from the multiple protocol stacks preset in the optical communication device, and preprocessing the real-time data stream according to the target protocol stack; The multi-protocol stack includes a plurality of protocol stacks, and each protocol stack defines a data processing specification for a data stream of a corresponding protocol type; Acquiring path attribute data of each transmission path in the optical communication device; the path attribute data includes available bandwidth, transmission delay, packet loss rate and supported protocol type of the transmission path; For each preprocessed real-time data stream, determining an adaptability matrix of the preprocessed real-time data stream relative to each transmission path according to path attribute data of each transmission path and content perception information and data protocol type of the preprocessed real-time data stream; According to each of the adaptation matrices, a corresponding target transmission path is allocated to each of the preprocessed real-time data streams; The step of determining the adaptability matrix of the preprocessed real-time data stream relative to each transmission path according to the path attribute data of each transmission path and the content perception information and data protocol type of the preprocessed real-time data stream comprises: According to the content perception information of the preprocessed real-time data stream, the content perception comprehensive score corresponding to the data stream is calculated: In the formula, It is a data stream The content-aware composite score, Representing data flow The characteristic value of the data payload type, Indicates the content feature weight corresponding to the data payload type; Representing data flow The basic score corresponding to the data load type, Representing data flow Load type calibration weights; Representing data flow The characteristic value of the data sensitivity level, Indicates the content feature weight corresponding to the data sensitivity level; Representing data flow The data sensitivity level, Indicates the maximum sensitivity level of the system. It represents the sensitivity importance coefficient; According to the data protocol type of the preprocessed real-time data stream and the path attribute data of each transmission path, the protocol adaptability score of the preprocessed real-time data stream relative to each transmission path is calculated: In the formula, Is the data flow in the transmission path The protocol fitness score on Represents the total number of path attribute features; Indicates The influence weight of each path attribute; Representing data flow Protocol type With Path attribute features Compatibility scores between According to the content perception comprehensive score and each of the protocol adaptability scores, the adaptability matrix corresponding to the preprocessed real-time data stream is calculated: In the formula, and Respectively and The corresponding factor fusion weight, For data flow The fitness matrix of the data flow Through the transmission path The fitness score of Wherein, the step of allocating a corresponding target transmission path to each of the preprocessed real-time data streams according to each of the adaptation matrices comprises: The fitness matrices are combined to determine the corresponding global fitness matrix: In the formula, represents the global fitness matrix, Indicates the total number of data flows, Indicates the total number of transmission paths; Performing matrix optimization calculation on the global fitness matrix to determine an optimal path allocation combination; the optimal path allocation combination includes target transmission paths matched respectively to each of the preprocessed real-time data streams; The objective function used in the matrix optimization calculation is: In the formula, is a binary variable, indicating the data flow Is the transmission path assigned? superior, Indicates allocation, Indicates no allocation; is the matrix element of the global fitness matrix, representing the data flow In the transmission path The fitness score on ; It is the sum of the fitness corresponding to the path allocation combination and is used to express the optimization objective function of the matrix optimization calculation; The constraints used in the matrix optimization calculation are: In the formula, and Respectively represent data flow Required bandwidth and required latency; and Respectively represent the transmission path Available bandwidth and transmission delay, For each data stream ; The performing of matrix optimization calculation on the global fitness matrix includes: The global fitness matrix is ​​processed by a greedy selection algorithm to select a transmission path that satisfies the constraint condition and corresponds to the maximum for each data stream, thereby obtaining an initial path allocation combination: In the formula, represents the initial path allocation combination, Representing data flow The initial optimal path of The initial path allocation combination is processed by a simulated annealing algorithm to iteratively search for the optimal path allocation combination, specifically including: Dynamically update the temperature of each iteration according to the iteration round: In the formula, and Respectively represent The iteration and The temperature of the iteration; Indicates The temperature reduction coefficient at the iteration, Indicates the total number of iterations; In each iteration, randomly select The perturbation of path allocation for each data stream: In the formula, represents the path allocation combination after disturbance, Indicates the path allocation combination for the current iteration A function for multidimensional perturbation, where is the set of perturbed data streams; represents the number of perturbation dimensions that are dynamically adjusted, represents the maximum value function, represents the function of rounding down; Calculate the sum of the fitness corresponding to the perturbed path allocation combination: In the formula, express The corresponding first fitness sum, Represents the index of the transmission path after the disturbance; If the first fitness degree sum is greater than the second fitness degree sum corresponding to the path allocation combination of the current iteration, the perturbed path allocation combination As a better solution for the current iteration; If the first fitness sum is not greater than the second fitness sum, then the acceptance probability is Decide whether to As a better solution for the current iteration; Probability of acceptance It is expressed by the following formula: In the formula, represents the temperature of the current iteration, represents the exponential function, express The corresponding second fitness sum.

2. The method according to claim 1, wherein: Acquisition of data protocol types for real-time data streams, including: Intercepting a sampling data packet from a real-time data stream, and matching the sampling data packet with a predefined protocol type library according to a protocol identifier in a packet header of the sampling data packet; the protocol type library includes a plurality of calibration protocol identifiers and corresponding calibration data protocol types; If there is a matching calibration protocol identifier, the calibration data protocol type corresponding to the matching calibration protocol identifier is determined as the data protocol type of the real-time data stream; If there is no matching calibration protocol identifier, the payload feature of the sampled data packet is extracted and the feature vector corresponding to the payload feature is calculated. The cosine similarity between each protocol feature vector in the protocol feature database: In the formula, express With The protocol feature vector corresponding to the protocol type The cosine similarity between and Respectively and Model; The target protocol feature vector corresponding to the maximum cosine similarity is selected, and when it is determined that the maximum cosine similarity exceeds a similarity threshold, the protocol type corresponding to the target protocol feature vector is used as the data protocol type of the real-time data stream.

3. The method according to claim 1, wherein: Acquisition of content-aware information for real-time data streams, including: Acquire context information, encryption status, content characteristics, and vulnerability threat information of the real-time data stream; the context information includes at least one of the following: application identification, data stream historical transmission mode, and data timestamp; Determining, according to the context information, a data load type corresponding to the real-time data stream; Determine the basic layer sensitivity score corresponding to the real-time data flow based on the data protocol type and encryption status, determine the intermediate layer sensitivity score corresponding to the real-time data flow based on the sensitivity risk analysis results of the content characteristics, and determine the advanced layer sensitivity score for the real-time data flow based on the vulnerability threat information; Based on the basic layer sensitivity score, the intermediate layer sensitivity score and the advanced layer sensitivity score, a data sensitivity level corresponding to the real-time data stream is determined.

4. The method according to claim 1, wherein: The factor fusion weights are determined by adopting a dynamic weight modulation mechanism: In the formula, and It's time The dynamic fusion weight factor, and Respectively and The value at the current moment; and They represent the corresponding adjustment amplitude factors, which are used to control the amplitude of the weight change; and They represent dynamic adjustment functions based on network conditions and data flow requirements, respectively; Representing data flow In time The sensitivity level, Representing data flow time The load type score, and is the network condition weight factor, which determines the sensitivity level and load type. The impact of It is the transmission path In time The transmission delay, It is the transmission path In time Available bandwidth, Indicates the maximum available bandwidth value. and is the data flow demand weight factor, which determines the latency and bandwidth impact.

5. A routing control system for a multi-protocol data stream, used to implement the routing control method for a multi-protocol data stream as claimed in any one of claims 1 to 4, the system comprising: An acquisition unit, used to acquire data protocol type and content perception information corresponding to each real-time data stream to be transmitted by the optical communication device; The content-aware information includes data payload type and data sensitivity level; A protocol stack processing unit, configured to determine, for each of the real-time data streams, a target protocol stack that matches the data protocol type of the real-time data stream from the multiple protocol stacks preset in the optical communication device, and preprocess the real-time data stream according to the target protocol stack; The multi-protocol stack includes a plurality of protocol stacks, and each protocol stack defines a data processing specification for a data stream of a corresponding protocol type; A path information acquisition unit, used to acquire path attribute data of each transmission path in the optical communication device; the path attribute data includes available bandwidth, transmission delay, packet loss rate and supported protocol type of the transmission path; an adaptability matrix determining unit, configured to determine, for each preprocessed real-time data stream, an adaptability matrix of the preprocessed real-time data stream relative to each transmission path according to path attribute data of each transmission path and content perception information and data protocol type of the preprocessed real-time data stream; The target path allocation unit is used to allocate a corresponding target transmission path to each of the preprocessed real-time data streams according to each of the adaptation matrices.

Images