Data transmission flow scheduling system based on AI cooperation

Abstract

The invention relates to the field of data transmission, and provides a data transmission flow scheduling system based on AI collaboration, and the system comprises a flow monitoring module which is used for monitoring a data transmission link, obtaining the current state information of the data transmission link, and sending the current state information of the data transmission link to a flow scheduling module when the current state information does not meet a preset condition; generating a flow scheduling instruction; the link selection module is used for determining a standby transmission link according to the data transmission link in response to the flow scheduling instruction; the data screening module is used for screening to-be-scheduled data from to-be-transmitted data in response to the traffic scheduling instruction; and the flow scheduling module is used for scheduling at least one part of the to-be-scheduled data from the data transmission link to the standby transmission link. The congestion problem in the data transmission process and frequent packet loss caused by congestion are avoided, and the intelligent adaptation capability of cross-domain data transmission is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of data transmission, in particular to an AI collaborative data transmission flow scheduling system. BACKGROUND

[0002] Secure Access Service Edge (SASE) is a cloud architecture model. In cross-regional data interaction scenarios, data needs to be transmitted between multiple SASE domains. Due to differences in network policies, security regulations and network infrastructure in different regions, traditional static transmission strategies are difficult to cope with complex cross-domain security requirements, and traffic congestion may cause transmission delays. For example, when AI medical data in Europe is transmitted to Asia, due to the fluctuation of intercontinental link bandwidth, transmission interruption or delay often occurs. The flow scheduling of existing SASE systems is mostly based on static rules, and lacks intelligent adaptation capabilities for cross-domain security risks and real-time traffic. SUMMARY

[0003] The main purpose of the present application is to provide an AI collaborative data transmission flow scheduling system, aiming to improve the intelligent adaptation capability of cross-domain data transmission.

[0004] In a first aspect, the present application provides an AI collaborative data transmission flow scheduling system, which comprises:

[0005] A flow monitoring module for monitoring a data transmission link, obtaining current state information of the data transmission link, and generating a flow scheduling instruction if the current state information does not meet a preset condition;

[0006] A link selection module for determining a backup transmission link according to the data transmission link in response to the flow scheduling instruction;

[0007] A data filtering module for filtering out scheduled data from the data to be transmitted in response to the flow scheduling instruction;

[0008] A flow scheduling module for scheduling at least part of the scheduled data from the data transmission link to the backup transmission link.

[0009] In some embodiments, the system further comprises a compliance analysis module, which is configured to:

[0010] grab the regulation information published by a preset site, and analyze the regulation information;

[0011] if it is determined that the regulation information belongs to data transmission regulations, analyze the regulation information through a preset large language model, and update the rule engine according to the analysis result;

[0012] determining, in response to the data transmission request, a target rule of data transmission based on the rule engine according to a data transmission starting node, a data transmission target node and a data type of the data transmission request;

[0013] The target rule at least includes a data desensitization rule, a data encryption rule and a transmission log retention time length.

[0014] In some embodiments, the system further comprises an identity authentication module, which is configured to:

[0015] In response to a data access request of a user, obtaining a role label corresponding to the user;

[0016] In the case where the role label belongs to a legal label, permitting the user to access the system;

[0017] After the user accesses the system, determining a behavior abnormality degree of the user according to a data operation performed by the user;

[0018] In the case where the behavior abnormality degree is greater than a preset abnormality degree, initiating secondary authentication for the user.

[0019] In some embodiments, after the user accesses the system, the behavior abnormality degree of the user is determined according to a data operation performed by the user, comprising:

[0020] calculating a first probability distribution of the user performing different data operations, the data operations including data reading operation and data writing operation;

[0021] calculating a KL divergence between the first probability distribution and a preset probability distribution corresponding to the role label to obtain the behavior abnormality degree.

[0022] In some embodiments, in the process of monitoring the data transmission link to obtain the current state information of the data transmission link, the traffic monitoring module is configured to:

[0023] sending a test data packet as to-be-transmitted data to the data transmission link based on a preset test frequency;

[0024] evaluating the data transmission link according to monitoring information returned by the test data packet to obtain the current state information.

[0025] In some embodiments, the sending of the test data packet as to-be-transmitted data to the data transmission link based on the preset test frequency comprises:

[0026] calculating a first packet loss rate P target of to-be-transmitted data in the data transmission link.

[0027] According to the first packet loss rate P target and the second packet loss rate P loss of the test data packet, iterates the preset frequency until the preset frequency meets a preset accuracy threshold, and takes the preset frequency as the test frequency.

[0028] In some embodiments, the preset frequency is iterated according to the first packet loss rate and the second packet loss rate of the test data packet until the preset frequency meets a preset accuracy threshold, and the preset frequency is taken as the test frequency, including:

[0029] The preset frequency includes: a first frequency with a time interval of a minimum interval T min , and a second frequency with a time interval of a maximum interval T max , where T low =T min , T high =T max .

[0030] The test data packet is sent at a frequency of T n , and the second packet loss rate P loss of the test data packet is calculated, where T n is the average value of T low and T high .

[0031] If the difference between the first packet loss rate P target and the second packet loss rate P loss is less than a preset threshold, T n is taken as T high , otherwise T n is taken as T low .

[0032] When the difference between T high and T low is less than a preset accuracy, the average value of T high and T low is taken as the sending interval of the test data packet, and the test frequency is obtained.

[0033] In some embodiments, the test data packet is sent to the data transmission link as the data to be transmitted based on the preset test frequency, including:

[0034] In the process of sending the test data packet to the data transmission link as the data to be transmitted, a confidence interval is calculated according to the second packet loss rate of m test data packets:

[0035] In a case where the first packet loss rate of the data transmission link is outside the confidence interval, the iteration is restarted to update the test frequency.

[0036] In some embodiments, the current state information is obtained by evaluating the data transmission link according to the monitoring information returned by the test data packets, including:

[0037] The monitoring information returned by the test data packets is obtained, the monitoring information being returned by each transmission node on the data transmission link after receiving the test data packets, and the monitoring information including node information of the transmission node.

[0038] The end node of the test data packet is determined according to the node information in the monitoring information returned by each test data packet.

[0039] In a case where the end node is not a preset node, the end node is determined as an abnormal node, and an abnormal frequency analysis is performed on the abnormal node to obtain an abnormal frequency of each abnormal node.

[0040] In some embodiments, in a case where the current state information does not satisfy a preset condition, a traffic scheduling instruction is generated, including:

[0041] In a case where the abnormal frequency of the abnormal node is greater than a preset frequency, the abnormal node is determined as a node to be replaced, and a traffic scheduling instruction is generated for the node to be replaced;

[0042] The backup transmission link is determined according to the data transmission link in response to the traffic scheduling instruction, including:

[0043] The node to be replaced is replaced with a backup node to obtain the backup transmission link in response to the traffic scheduling instruction.

[0044] The application provides an AI collaboration-based data transmission flow scheduling system. A flow monitoring module is used to monitor a data transmission link, obtain current state information of the data transmission link, and generate a flow scheduling instruction when the current state information does not satisfy a preset condition. A link selection module is used to determine a backup transmission link according to the data transmission link in response to the flow scheduling instruction. A data screening module is used to screen out to-be-scheduled data from to-be-transmitted data in response to the flow scheduling instruction. A flow scheduling module is used to schedule at least part of the to-be-scheduled data from the data transmission link to the backup transmission link. The flow monitoring module is used to monitor the data transmission link. When the monitoring result shows that there is a problem with the data transmission link, the link selection module is used to select a backup transmission link, so that at least part of the to-be-scheduled data is transmitted through the backup transmission link, the congestion problem in the data transmission process and the frequent packet loss caused by the congestion are avoided, and the intelligent adaptation capability of cross-domain data transmission is improved. BRIEF DESCRIPTION OF DRAWINGS

[0045] In order to more clearly illustrate the technical solutions of the embodiments of the application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor.

[0046] Figure 1 A schematic block diagram of an AI collaboration-based data transmission flow scheduling system according to an embodiment of the application is provided.

[0047] Figure 2 A step flowchart of an AI collaboration-based data transmission flow scheduling method according to an embodiment of the application is provided.

[0048] Figure 3 A schematic block diagram of the structure of a computer device according to an embodiment of the application is provided. DETAILED DESCRIPTION

[0049] The technical solutions in the embodiments of the application will be described clearly and completely in combination with the drawings in the embodiments of the application. Obviously, the described embodiments are some embodiments of the application, not all embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the application.

[0050] The flowchart shown in the accompanying drawings is only an example and does not necessarily include all the contents and operations / steps, nor does it have to be executed in the order described. For example, some operations / steps can be further decomposed, combined or partially merged, so the actual execution order can be changed according to the actual situation.

[0051] An AI collaboration-based data transmission flow scheduling system is provided in an embodiment of the present application.

[0052] Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. The following embodiments and features in the embodiments can be combined with each other without conflict.

[0053] Please refer to Figure 1 , Figure 1 An AI collaboration-based data transmission flow scheduling system provided in an embodiment of the present application is shown in a schematic block diagram. The AI collaboration-based data transmission flow scheduling system can be used in a terminal or a server, where the terminal can be an electronic device such as a mobile phone, a tablet computer, a notebook computer, a desktop computer, a personal digital assistant and a wearable device; and the server can be a standalone server, a server cluster, a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and basic cloud computing services such as big data and artificial intelligence platforms.

[0054] As shown in Figure 1 , the AI collaboration-based data transmission flow scheduling system includes a flow monitoring module 110, a link selection module 120, a data screening module 130 and a flow scheduling module 140.

[0055] The flow monitoring module 110 is configured to monitor a data transmission link, obtain current state information of the data transmission link, and generate a flow scheduling instruction when the current state information does not meet a preset condition.

[0056] The link selection module 120 is configured to determine a backup transmission link according to the data transmission link in response to the flow scheduling instruction.

[0057] The data screening module 130 is configured to screen out to-be-scheduled data from to-be-transmitted data in response to the flow scheduling instruction.

[0058] The flow scheduling module 140 is configured to schedule at least part of the to-be-scheduled data from the data transmission link to the backup transmission link.

[0059] Exemplarily, the data transmission link is composed of multiple nodes between the data sending end and the data receiving end, and the data packet is transmitted between the nodes so as to reach the data receiving end from the data sending end. Each node in the data transmission link has the possibility of packet loss. In order to avoid the influence of packet loss on data transmission, the existing data transmission protocol usually retransmits the lost data packet to ensure that the receiving end receives all data segments. However, in the SASE cross-domain data transmission scenario, the cross-country or even cross-continent data transmission link usually passes through more nodes. The lower packet loss rate of a single node is accumulated, which may cause a higher packet loss rate of the whole data transmission link, resulting in a large amount of bandwidth being used for retransmission. Moreover, in the existing data transmission method, the sending end can usually only determine whether the receiving end has accepted the data packet according to whether the acknowledgement information (ack) is received, and cannot determine which node the data packet is lost.

[0060] Exemplarily, the data to be scheduled screened by the data screening module can be data with a higher transmission priority.

[0061] The AI collaboration-based data transmission flow scheduling system provided by the embodiments of the present application monitors the data transmission link through the flow monitoring module. In the case that the monitoring result shows that there is a problem with the data transmission link, the standby transmission link is selected through the link selection module, so that at least part of the data to be scheduled is transmitted through the standby transmission link, avoiding the congestion problem in the data transmission process and the frequent packet loss caused by the congestion, and improving the intelligent adaptation capability of cross-domain data transmission.

[0062] In some embodiments, the system further comprises a compliance analysis module, configured to:

[0063] grab the regulatory information published by the preset site, and analyze the regulatory information;

[0064] In the case that it is determined that the regulatory information belongs to data transmission regulations, the regulatory information is analyzed by a preset large language model, and the rule engine is updated according to the analysis result;

[0065] In response to a data transmission request, according to the data transmission starting node, the data transmission target node and the data type of the data transmission request, the target rule of data transmission is determined based on the rule engine;

[0066] The target rule at least includes: data desensitization rule, data encryption rule, transmission log retention time.

[0067] Exemplarily, different countries and regions have different regulations on data security. A website publishing laws and regulations of each country and region can be set as a preset website, the regulation information published by the preset website is automatically captured, and the captured regulation information is classified by a natural language model to determine whether the regulation information belongs to data transmission regulations related to data security. In the case where the regulation information belongs to data transmission regulations, the preset rule engine is updated according to the regulation information.

[0068] Exemplarily, the rule engine can include data classification rules and data processing rules. The data classification rules are determined according to the classification of data in the regulations, so as to determine whether the to-be-transmitted data belongs to regulated data and which type of regulated data according to the data classification rules. Then, the corresponding data processing rules, i.e., target rules, are determined according to the type to which the to-be-transmitted data belongs, such as data desensitization rules, data encryption rules, and transmission log retention time length.

[0069] Among them, the data desensitization rules specify the desensitization degree and the desensitization algorithm used, such as replacing part of the information; the data encryption rules specify the encryption degree and the encryption algorithm used, such as AES-256 algorithm; and the transmission log retention time length specifies the time for which the data transmission log needs to be retained, such as 1 year.

[0070] In some embodiments, the system further comprises an identity authentication module, wherein the identity authentication module is configured to:

[0071] In response to a data access request of a user, obtain a role label corresponding to the user;

[0072] In the case where the role label belongs to a legal label, permit the user to access the system;

[0073] After the user accesses the system, determine a behavior abnormality degree of the user according to a data operation performed by the user;

[0074] In the case where the behavior abnormality degree is greater than a preset abnormality degree, initiate secondary authentication for the user.

[0075] Exemplarily, the embodiments of the present application adopt Role-Based Access Control (RBAC), which assigns users to different roles and assigns corresponding permissions to each role, thereby realizing access control of data. Among them, a role is a set of permissions, representing the responsibilities or functions of a user in the system; for example, the "administrator" role may have the permission of system management, and the "ordinary user" role may only have the permission of viewing data. Each user is assigned a role, and the user has the permission corresponding to the role.

[0076] Through role-based authentication, the user can be conveniently changed in authority, and the complexity of directly managing the user authority is reduced. The change of the role only needs to be performed at the role level, and the authority of the user does not need to be modified one by one, so that the maintainability and scalability of the authority management are improved.

[0077] For example, in order to improve the security of the system, after the user accesses the system, the data operation performed by the user is analyzed to determine the behavior abnormality degree. In the case where the behavior abnormality degree is greater than the preset abnormality degree, secondary authentication is initiated for the user. The secondary authentication can be password authentication, voice authentication, fingerprint authentication, etc., which will not be repeated here.

[0078] In some embodiments, after the user accesses the system, the behavior abnormality degree of the user is determined according to the data operation performed by the user, comprising:

[0079] The first probability distribution of the user performing different data operations is calculated, and the data operations include data reading operation and data writing operation.

[0080] The KL divergence of the first probability distribution and the preset probability distribution corresponding to the role label is calculated to obtain the behavior abnormality degree.

[0081] For example, the KL divergence is used to measure the difference between the first probability distribution and the preset probability distribution. Specifically, the KL divergence describes the amount of information lost when the first probability distribution is used to approximate the second probability distribution. For example, the first probability distribution can be the first operation frequency of the user, and the preset probability distribution can be the average operation frequency of all users under the role label.

[0082] For example, the smaller the KL divergence is, the closer the first probability distribution is to the preset probability distribution. Therefore, the KL divergence is used as the behavior abnormality degree. When the behavior abnormality degree is large, it indicates that the operation behavior of the user is greatly different from that of the normal user under the label, and further authentication is required for the user.

[0083] In some embodiments, in the process of monitoring the data transmission link to obtain the current state information of the data transmission link, the traffic monitoring module is configured to:

[0084] Based on the preset test frequency, the test data packet is sent to the data transmission link as the to-be-transmitted data.

[0085] The data transmission link is evaluated according to the monitoring information returned by the test data packet to obtain the current state information.

[0086] Exemplarily, the embodiment of the present application improves the existing communication protocol, determines the node where the packet loss occurs through the test data packet. Specifically, the test data packet returns the monitoring information during the transmission process, and it can be determined that the packet loss occurs at the node where the monitoring information is not returned. Therefore, the node where the packet loss is prone to occur in the data transmission link can be determined according to the monitoring information, and the current state information of the data transmission link is obtained.

[0087] In some embodiments, the test data packet is sent as the to-be-transmitted data to the data transmission link based on the preset test frequency, including:

[0088] calculating the first packet loss rate P target of the to-be-transmitted data in the data transmission link;

[0089] iterating the preset frequency according to the first packet loss rate P target and the second packet loss rate P loss of the test data packet until the preset frequency meets a preset accuracy threshold, and taking the preset frequency as the test frequency.

[0090] Exemplarily, since the test data packet needs to return the monitoring information at each node, if the test frequency of sending the test data packet is too high, it will cause the communication system overhead to increase. If the sending frequency of the test data packet is too high, the test effect cannot be achieved. Therefore, the test frequency of sending the test data packet is crucial.

[0091] Exemplarily, in order to determine the appropriate test frequency, the second packet loss rate of the test data packet needs to be adapted to the first packet loss rate of the to-be-transmitted data. Therefore, the preset frequency is iterated according to the first packet loss rate P target and the second packet loss rate P loss of the test data packet.

[0092] In some embodiments, the preset frequency is iterated according to the first packet loss rate and the second packet loss rate of the test data packet until the preset frequency meets a preset accuracy threshold, and the preset frequency is taken as the test frequency, including:

[0093] The preset frequency includes: a first frequency with a time interval of a minimum interval T min , and a second frequency with a time interval of a maximum interval T max , where T low =T min , and T high =T max .

[0094] The test data packet is sent at a frequency of T n , and the second packet loss rate P loss of the test data packet is calculated, where Tn T low and T high is an average value of T

[0095] If the difference between the first packet loss rate P target and the second packet loss rate P loss is less than a preset threshold, T low = T n , otherwise T high = T n .

[0096] When the difference between T high and T low is less than a preset accuracy, an average value of T high and T low is taken as the sending interval of the test data packet, and the test frequency is obtained.

[0097] For example, a maximum interval and a minimum interval of sending the test data packet twice are preset, and the maximum interval and the minimum interval can be set according to actual needs, for example, the maximum interval can be 30 minutes, and the minimum interval can be 1 minute. When the difference between the first packet loss rate P target and the second packet loss rate P loss is small, it indicates that the current test data packet sending frequency is too high, and the frequency needs to be reduced. The value of T high is updated to T n , the sending interval is extended, and the frequency is reduced. Conversely, the value of T low is updated to T n , and the test frequency is increased.

[0098] For example, when the difference between T high and T low is less than a preset accuracy, it is determined that the time interval converges, and an average value of T high and T low is taken as the sending interval of the test data packet, and the test frequency of sending the test data packet is obtained.

[0099] In some embodiments, the test data packet is sent to the data transmission link as the to-be-transmitted data based on the preset test frequency, including:

[0100] In the process of sending the test data packet to the data transmission link as the to-be-transmitted data, a confidence interval is calculated according to the second packet loss rate of the m test data packets:

[0101] When the first packet loss rate of the data transmission link is outside the confidence interval, the iteration for updating the test frequency is restarted.

[0102] Exemplarily, the second packet loss rate P The confidence interval is calculated as follows:

[0103]

[0104] wherein z α / 2 represents the quantile of the standard normal distribution;

[0105] Exemplarily, since there is fluctuation in the packet loss rate, the test frequency is updated according to the packet loss rate of the test data packet, the second packet loss rate P loss is calculated according to the above formula, and in the case that the first packet loss rate P target is outside the confidence interval, the iteration of updating the test frequency is restarted. The size of m may be 30, for example, indicating that the confidence interval is calculated according to the packet loss rate of 30 test data packets.

[0106] wherein z α / 2 represents the quantile of the standard normal distribution, determined by the confidence level 1-α, for example, when α=0.05, the 95% confidence level corresponds to z α / 2 =1.96.

[0107] In some embodiments, the data transmission link is evaluated according to the monitoring information returned by the test data packet to obtain the current state information, including:

[0108] The monitoring information returned by the test data packet is obtained, which is returned by each transmission node on the data transmission link after receiving the test data packet, and the monitoring information includes node information of the transmission node;

[0109] The end node of the test data packet is determined according to the node information in the monitoring information returned by each test data packet;

[0110] In the case that the end node is not a preset node, the end node is determined as an abnormal node, and the abnormal frequency analysis is performed on the abnormal node to obtain the abnormal frequency of each abnormal node.

[0111] Exemplarily, since the test data packet passes through each transmission node, the node corresponding to the last monitoring information of the test data packet can be considered as the end node of the test data packet.

[0112] Exemplarily, in the case of transmission sensing, the end node should be a preset node of the data receiving end; in the case that the end node is not a preset node, it indicates that the test data packet has been lost at the end node, and the end node is determined as an abnormal node.

[0113] In some embodiments, the generating the traffic scheduling instruction in the case that the current state information does not satisfy the preset condition comprises:

[0114] In the case that the abnormal frequency of the abnormal node is greater than the preset frequency, the abnormal node is determined as a node to be replaced, and a traffic scheduling instruction is generated for the node to be replaced.

[0115] For example, if a node is determined as an abnormal node too frequently, it indicates that the node has a problem, and the node is determined as a node to be replaced, and the traffic scheduling instruction indicates that the traffic of the node is scheduled.

[0116] In some embodiments, the determining the backup transmission link according to the data transmission link in response to the traffic scheduling instruction comprises:

[0117] The node to be replaced is replaced by a backup node to obtain the backup transmission link in response to the traffic scheduling instruction.

[0118] For example, the backup transmission link is obtained by bypassing the node to be replaced by the backup node. The number of backup nodes is greater than or equal to the number of nodes to be replaced, for example, one node to be replaced can be replaced by two backup nodes.

[0119] The application provides a data transmission traffic scheduling system based on AI collaboration. The traffic monitoring module is used to monitor the data transmission link to obtain the current state information of the data transmission link, and generate a traffic scheduling instruction in the case that the current state information does not satisfy the preset condition. The link selection module is used to determine a backup transmission link according to the data transmission link in response to the traffic scheduling instruction. The data filtering module is used to filter out to-be-scheduled data from to-be-transmitted data in response to the traffic scheduling instruction. The traffic scheduling module is used to schedule at least part of the to-be-scheduled data from the data transmission link to the backup transmission link. The data transmission link is monitored by the traffic monitoring module, and in the case that the monitoring result shows that the data transmission link has a problem, the backup transmission link is selected by the link selection module, so that at least part of the to-be-scheduled data is transmitted through the backup transmission link, the congestion problem in the data transmission process is avoided, and the frequent packet loss caused by the congestion is avoided, and the intelligent adaptation capability of cross-domain data transmission is improved.

[0120] Please refer to Figure 2 , Figure 2 The application provides a data transmission traffic scheduling method based on AI collaboration.

[0121] As Figure 2As shown, the present application also provides an AI collaboration-based data transmission flow scheduling method, which comprises the following steps:

[0122] In step S101, the data transmission link is monitored to obtain current state information of the data transmission link, and a flow scheduling instruction is generated if the current state information does not satisfy a preset condition.

[0123] In step S102, a backup transmission link is determined according to the data transmission link in response to the flow scheduling instruction.

[0124] In step S103, the to-be-scheduled data is selected from the to-be-transmitted data in response to the flow scheduling instruction.

[0125] In step S104, at least part of the to-be-scheduled data is scheduled from the data transmission link to the backup transmission link.

[0126] It should be noted that, for the convenience and brevity of description, the specific working process of the above-described method and each step can refer to the corresponding process in the foregoing system embodiments, which will not be described here.

[0127] The method and system of the present application can be used in many general or special computing system environments or configurations. For example: personal computers, server computers, handheld devices or portable devices, tablet devices, multi-processor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in a distributed computing environment in which tasks are performed by remote processing devices connected by a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0128] By way of example, the above-described method and system can be implemented as a computer program in the form of a computer program product that can run on a computer device as shown. Figure 3

[0129] Please refer to Figure 3 , Figure 3 A structural schematic block diagram of a computer device provided by an embodiment of the present application. The computer device can be a server or a terminal.

[0130] As Figure 3 ​As shown, the computer device includes a processor, a memory and a network interface connected through a system bus, wherein the memory can include a storage medium and an internal memory.

[0131] The storage medium can store an operating system and a computer program. The computer program includes program instructions which, when executed, can cause the processor to perform any one of the AI collaboration-based data transmission traffic scheduling methods.

[0132] The processor is configured to provide computing and control capabilities to support the operation of the entire computer device.

[0133] The internal memory provides an environment for the execution of the computer program in the storage medium, which, when executed by the processor, can cause the processor to perform any one of the AI collaboration-based data transmission traffic scheduling methods.

[0134] The network interface is configured to perform network communication, such as sending assigned tasks, etc. Those skilled in the art can understand that, Figure 3 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0135] It should be understood that the processor can be a central processing unit (CPU), and the processor can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0136] In one embodiment, the processor is configured to run a computer program stored in the memory to implement the following steps:

[0137] Step S101, monitoring a data transmission link to obtain current state information of the data transmission link, and generating a traffic scheduling instruction if the current state information does not satisfy a preset condition;

[0138] Step S102, determining a backup transmission link according to the data transmission link in response to the traffic scheduling instruction.

[0139] Step S103, in response to the flow scheduling instruction, screening out to-be-scheduled data from to-be-transmitted data;

[0140] Step S104, scheduling at least part of the to-be-scheduled data from the data transmission link to the backup transmission link.

[0141] It should be noted that, for the convenience and brevity of description, the specific working process of the computer device described above can be referred to the corresponding process in the foregoing embodiments of the AI collaborative data transmission flow scheduling system, which will not be described here.

[0142] The embodiments of the present application also provide a computer readable storage medium, the computer readable storage medium stores a computer program, the computer program includes program instructions, and the method implemented when the program instructions are executed can refer to each embodiment of the AI collaborative data transmission flow scheduling system of the present application.

[0143] The computer readable storage medium can be an internal storage unit of the computer device, such as a hard disk or a memory of the computer device. The computer readable storage medium can also be an external storage device of the computer device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc.

[0144] It should be understood that the terms used herein in the specification of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification of the present application and the appended claims, unless otherwise clearly indicated by the context, the singular forms "a", "an" and "the" are intended to include the plural forms.

[0145] It should also be understood that the term "and / or" used in the specification and the appended claims of the present application means any combination of one or more of the associated listed items and all possible combinations, and includes these combinations. It should be noted that in this document, the terms "include", "contain" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or system including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or system. Without more limitations, the element defined by the statement "including a" does not exclude the presence of other identical elements in the process, method, article or system including the element.

[0146] The above-mentioned sequence numbers of the embodiments of the present application are only for description, and do not represent advantages or disadvantages of the embodiments. The above describes only the specific implementation of the present application, but the protection scope of the present application is not limited to this. Any person skilled in the art can easily think of various equivalent modifications or replacements within the technical range disclosed by the present application, and these modifications or replacements should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An AI collaboration-based data transmission flow scheduling system, characterized in that, The system comprises: a traffic monitoring module for monitoring a data transmission link to obtain current state information of the data transmission link, and generating a traffic scheduling instruction if the current state information does not meet a preset condition; a link selection module for determining a backup transmission link according to the data transmission link in response to the traffic scheduling instruction; a data screening module for screening out to-be-scheduled data from to-be-transmitted data in response to the traffic scheduling instruction; a traffic scheduling module for scheduling at least part of the to-be-scheduled data from the data transmission link to the backup transmission link. 2.The AI collaboration-based data transmission flow scheduling system according to claim 1, characterized in that, The system further comprises a compliance analysis module, which is configured to: capture and analyze regulation information published by a preset website; if it is determined that the regulation information belongs to data transmission regulations, analyze the regulation information by using a preset large language model, and update a rule engine according to the analysis result; in response to a data transmission request, determine a target rule of data transmission based on the rule engine according to a data transmission starting node, a data transmission target node, and a data type of the data transmission request; wherein the target rule at least includes a data desensitization rule, a data encryption rule, and a transmission log retention time length. 3.The AI collaboration-based data transmission flow scheduling system according to claim 1, characterized in that, The system further comprises an identity authentication module, which is configured to: in response to a data access request of a user, obtain a role label corresponding to the user; if the role label is a legal label, grant the user access to the system; after the user accesses the system, determine a behavior abnormality degree of the user according to data operations performed by the user; if the behavior abnormality degree is greater than a preset abnormality degree, initiate secondary authentication for the user. 4.The AI collaboration-based data transmission flow scheduling system according to claim 3, characterized in that, After the user accesses the system, the behavior abnormality degree of the user is determined according to the data operations performed by the user, comprising: calculating a first probability distribution of different data operations performed by the user, wherein the data operations include data reading operation and data writing operation; calculating the KL divergence between the first probability distribution and a preset probability distribution corresponding to the role label to obtain the behavior abnormality degree. 5.The AI collaboration-based data transmission flow scheduling system according to claim 1, wherein, In the process of monitoring the data transmission link to obtain the current state information of the data transmission link, the traffic monitoring module is configured to: send test data packets to the data transmission link as to-be-transmitted data based on a preset test frequency; evaluate the data transmission link according to monitoring information returned by the test data packets to obtain the current state information. 6.The AI collaboration-based data transmission flow scheduling system according to claim 5, characterized in that, The test data packets are sent to the data transmission link as to-be-transmitted data based on a preset test frequency, comprising: calculating a first packet loss rate P of data to be transmitted in the data transmission link target ; According to the first packet loss rate P target And the second packet loss rate P of the test data packet loss Iterate on the preset frequency until the preset frequency meets the preset accuracy threshold, and take the preset frequency as the test frequency. 7.The AI collaboration-based data transmission flow scheduling system according to claim 6, characterized in that, The first packet loss rate and the second packet loss rate of the test data packets are iterated based on the preset frequency until the preset frequency meets a preset accuracy threshold, and the preset frequency is taken as the test frequency, comprising: The preset frequencies include a first frequency with a minimum interval T min , and a second frequency with a maximum interval T max ; T low = T min , T high = T max ; T n sends test data packets at a frequency and calculates a second packet loss rate P loss of the test data packets, wherein T n is the average of T low and T high . If the first packet loss rate P target is less than a preset threshold, the T loss is less than the preset threshold, the T n is taken as the T high , otherwise the T n is taken as the T low ; When the difference between T high and T low is less than a preset precision, the average value of T high and T low is taken as the sending interval of the test data packet, and the test frequency is obtained. 8.The AI collaboration-based data transmission flow scheduling system according to claim 5, characterized in that, The test data packets are sent to the data transmission link as to-be-transmitted data based on a preset test frequency, comprising: In the process of sending the test data packet as to-be-transmitted data to the data transmission link, a confidence interval is calculated according to the second packet loss rate of the m test data packets: In the case where the first packet loss rate of the data transmission link is outside the confidence interval, the iteration of updating the test frequency is restarted. 9.The AI collaboration-based data transmission flow scheduling system according to claim 5, wherein, The evaluation of the data transmission link according to the monitoring information returned by the test data packet to obtain the current state information includes: Obtaining the monitoring information returned by the test data packet, the monitoring information being returned by each transmission node on the data transmission link after receiving the test data packet, and the monitoring information including node information of the transmission node; According to the node information in the monitoring information returned by each test data packet, the terminal node of the test data packet is determined; In the case where the terminal node is not a preset node, the terminal node is determined as an abnormal node, and an abnormal frequency analysis is performed on the abnormal node to obtain an abnormal frequency of each abnormal node. 10.The AI collaboration-based data transmission flow scheduling system according to claim 9, characterized in that, In the case where the current state information does not satisfy a preset condition, a traffic scheduling instruction is generated, including: In the case where the abnormal frequency of the abnormal node is greater than a preset frequency, the abnormal node is determined as a to-be-replaced node, and a traffic scheduling instruction is generated for the to-be-replaced node; In response to the traffic scheduling instruction, a backup transmission link is determined according to the data transmission link, including: In response to the traffic scheduling instruction, the to-be-replaced node is replaced with a backup node to obtain the backup transmission link.

Images