30 results about "Packet classification" patented technology

The invention relates to a packet classification device for flow table normalization storage, electronic equipment and a storage medium, and the device comprises a flow table normalization unit which is used for cutting an original rule set according to two dimensions of a matching domain and a rule domain of the original rule set to obtain rule subsets; the storage mapping unit is used for determining a comparison and selection character string; matching the comparison and selection character string with the rule subsets corresponding to the lengths to obtain first matching results, and forming a single rule subblock by the first matching results corresponding to the same rule subset; taking the regular sub-blocks as a whole, and storing the first matching result in the regular sub-blocks into a storage device; the packet classification searching unit is used for reading a target first matching result matched with a packet header character string from the storage device based on the packet header character string of a to-be-classified data packet; and determining a target forwarding rule corresponding to the to-be-classified data packet based on the target first matching result. Therefore, the scale of the flow table can be improved, and the to-be-classified data can be classified more finely.

A method for processing packets, the method comprising receiving a packet by a data processing unit (DPU), making a first determination that there is no exact match flow entry in a hardware switch pipeline in the DPU for the packet, in response to the first determination, classifying, in the DPU, the packet as a data packet, in response to the classifying of the packet: identifying, using a software data plane in the DPU, a forwarding information base (FIB) entry to be used to transmit the packet towards its intended destination, identifying, using the software data plane, a flow associated with the packet, initiating, using the software data plane, programming of an exact match flow entry in the hardware switch pipeline, and initiating, using the software data plane, transmission of the packet towards its intended destination using the FIB entry and the hardware switch pipeline.

Embodiments of the present application disclose a log packet classification method and a computing device, which are used for classifying a to-be-classified log packet. In the present application, the computing device first determines a plurality of feature types of the to-be-classified log packet, and then determines a plurality of model parameters of the to-be-classified log packet based on the plurality of feature types. Next, the computing device calculates similarities between the to-be-classified log packet and each of K log packet types based on the plurality of model parameters, and obtains K similarities. Finally, the computing device determines a log packet type to which the to-be-classified log packet belongs from the K log packet types according to the K similarities. Thus, the to-be-classified log packet that does not conform to any rule of any of the K log packet types can also be classified.

Disclosed is a system (104) and a method (500) for stream-based packet processing in a communication network. The method comprises receiving values corresponding to a plurality of configuration parameters including a parsing unit count. The method further comprises receiving, from a network interface, a plurality of packets corresponding to one or more data streams based upon the values of the plurality of configuration parameters and forming one or more batches of the plurality of packets based on the values corresponding to the plurality of configuration parameters. The method further comprises retrieving the one or more batches stored in a shared memory based on the value of the parsing unit count. The method further comprises parsing the plurality of packets in the retrieved batches to extract protocol header fields and classifying, based on the parsing, the plurality of packets into parsed packets and unparsed packets to enable the stream-based packet processing.

The invention provides a network communication device and method with a dynamic packet transmission sorting mechanism. The packet classification circuit sets each low-latency packet as a selected low-latency packet for storage in a corresponding selected low-latency queue circuit. The transmission sorting circuit calculates a queue time parameter for the selected low-delay packet to sort the selected low-delay packet with other low-delay packets so as to update a sorting list. Wherein the queue time parameter is the proportion of the total queue time of the selected low-delay packet stored in the selected low-delay queue circuit exceeding the dynamic service time threshold value set corresponding to the selected low-delay queue circuit. The communication circuit sequentially transmits the low-latency packets according to the sorting list. The dynamic adjustment circuit calculates the difference between the total packet transmission time of the selected low-delay packet and the target delay threshold value so as to dynamically adjust the dynamic service time threshold value according to the difference.

Systems and methods for determining whether to perform deep packet inspection (DPI) on packets received at a network device based on shallow packet inspection data are disclosed. Embodiments may include DPI classification data in a combined lookup table that is utilized for shallow packet data based packet classification at a network device. Using the results of lookups in such a combined look table based on received packets, determinations can be made whether to perform DPI on such received packets, and those packets forwarded accordingly.

The application provides a packet classification parallel method and system based on ensemble learning, comprising the following steps: S1, establishing a rule search cost model to quantify the complementarity between different instances of an algorithm; S2, using a genetic algorithm to generate an optimal combination scheme of different instances of the algorithm, and after finding an algorithm instance meeting the requirements, constructing an algorithm instance library; and S3, constructing a packet classification prediction model, and selecting a suitable algorithm instance from the constructed algorithm instance library to complete a packet classification operation. The application first acutely observes the worst case existing in the existing packet classification method and the cause thereof, and under the enlightenment of ensemble learning, mines the complementarity existing between different instances of an algorithm to optimize the performance.

A plurality of captured packets are received. The plurality of captured packets are from a plurality of packet flows. A packet flow is a communication session between two devices. For example, a packet flow may be a communication session between a client and a server. The plurality of captured packets are sorted into individual packet flows. The individual packet flows are converted into individual videos. For example, each packet from each packet flow is stored as a separate video frame in an individual video. A machine learning algorithm is applied to the individual videos to perform analytic tasks on the individual videos. For example, the machine learning algorithm may be used to identify anomalies within a packet flow and / or between packet flows.

A hardware-based framework is provided that enables a network device to accurately estimate the cardinality of (or in other words, the number of unique elements in) a stream of network packets processed by the device, using minimal memory and compute resources. For example, this framework can enable the network device to accurately estimate the number of unique network flows in the packet stream, the number of unique source Internet Protocol (IP) addresses in the packet stream, the number of unique flows for each of a plurality of packet classification characteristics (e.g., ingress ports on which the packets were received, egress ports on which the packets are sent out, etc.), and so on.

A method of providing differential security services for a ship network by a service provider connected to a client performing the differential security services may comprise: receiving a service request from a user terminal by an authentication performing unit of a service provider including a processor; returning or issuing, by the authentication performing unit, an ID token and an authentication code to the user terminal in response to the service request; receiving, by the client, the ID token and the authentication code from the user terminal; verifying, by the client, validity of the ID token; setting, by the client, a session cookie for the service request when the validity is verified; transmitting, by the client, an access token request including the authentication code to a token issuing unit of the service provider; and receiving, by the client, an access token from the token issuing unit.

An ultra-high speed electronic communications device includes: a network communications interface; a memory; and one or more processing units, communicatively coupled to the memory and the network communications interface, wherein the memory stores instructions configured to cause the one or more processing units to: receive a data packet using the network communications interface; determine a classification of the data packet based, at least in part, on a plurality of factors, wherein the plurality of factors comprises a rate at which the data packet was received and a time at which the data packet was received; select, based at least in part, on the classification, an operation from a plurality of operations, wherein the plurality of operations comprises a cut-through operation and a store-and-forward operation; and perform the selected operation.

The invention provides a message classification method. A decision-making unit comprises a TCAM (Ternary Content Addressable Memory), a plurality of boundary value memories cascaded behind the TCAM, and a rear rule memory connected to the last level of boundary value memory, a bit value group is stored in the TCAM, the bit value group corresponds to a bit decision of a decision tree of a rule, a boundary value is stored in the boundary value memory, the boundary value corresponds to a range decision or a bit decision of the decision tree, and the rule is stored in the rule memory; the method comprises the steps of extracting a target key value from a target message and inputting the target key value into a decision-making unit; searching a bit value group matched with the target key value in a TCAM (Ternary Content Addressable Memory), and determining a first-level address index; acquiring a boundary value from each level of boundary value memory according to the address index of the corresponding level, comparing the boundary value with a target key value, and determining the address index of the next level according to a comparison result; and acquiring the rule from the rule memory according to the last-level address index. The invention also provides a message classification device.

Interval binary tree definitions and binary tree definitions can be stored in the memory of a networking device. The interval binary trees can map IP address ranges and port ranges to class identifiers. A networking device receives an IP packet that has a layer 3 header that includes an IP address and a port number. The networking device can use the IP address, the port number, and the interval binary trees to determine a first class identifier and a second class identifier. The first class identifier can indicate a binary tree definition that is searched for the second class identifier. The search identifies yet another class identifier that the networking device uses to determine a networking rule to apply to the IP packet. This technique uses far less memory than the RFC algorithm commonly used to determine a networking rule to apply to the IP packet.

This invention discloses a packet classification processing system based on the joint compilation of multi-mode DFA automata, comprising: a feature extraction module for extracting the state transition path features of each independent DFA automaton participating in the joint compilation and the features of the network packets to be classified; an integrated compilation core module that integrates a quantum hash processing unit and a biological sequence alignment processing unit to achieve collaborative compilation of path optimization and index construction; and a global homogeneous path sharing pool for storing path-related data output by the integrated compilation core module, enabling the reuse of homogeneous path segments among multiple DFAs. This invention, through the collaborative work of quantum hash processing and biological sequence alignment, accurately identifies and reuses homogeneous path segments in multi-mode DFAs, avoiding the repeated storage and computation of paths caused by traditional independent compilation, significantly reducing the overall redundancy of the state machine, improving storage and computation efficiency, and enhancing matching accuracy and reliability.

A method for controlling packet transmission at a PTN access node for an ITS communication network and an apparatus for the same are disclosed. A packet transmission control method according to an embodiment of the present invention may include: a step of classifying into a plurality of service classes including control traffic and video traffic based on the header and service identifier of a received frame; a step of receiving traffic event metadata including signal cycles, conflicting traffic events, and priority signal events from a control policy server; a step of generating scheduling parameters including time slot allocation parameters for a control traffic queue and weight adjustment parameters for a video traffic queue based on the metadata; a step of calculating a microburst indicator based on frame inflow characteristics in a short-time observation window, and determining the output order by performing queue management and scheduling control for a queue by service class according to the scheduling parameters and the microburst indicator; a step of transmitting by applying a predetermined transmission encapsulation according to a service identifier; and a step of maintaining an independent protection domain for each service and performing linear or ring protection switching only for the corresponding service when a threshold is exceeded based on an OAM performance indicator for each service.

Network devices, systems, and methods are provided. In one example, a network device includes one or more packet classification circuits and one or more hash selection circuits that cooperate with the one or more packet classification circuits to provide the one or more packet classification circuits with a hash table selection order. The hash table selection order may be determined for a packet to be classified with the support of machine learning by the one or more packet classification circuits based on information contained in the packet.

Systems, methods, and computer-readable storage media for packet classification, and more specifically to cloud-driven traffic classification. A system can receive, at a packet identifier, a packet comprising a packet header and packet data, and generate a Universally Unique Identifier (UUID) based on the packet header. The system can then transmit the UUID from the packet identifier to a UUID cloud database and receive, at the packet identifier from the UUID cloud database, packet management instructions. The system can then provide the packet and the packet management instructions to a router.

A network device, system-on-a-chip, and method of performing packet handling are described. A packet is received, and a lookup based on one or more packet header fields of the packet is performed using a lookup generator action handler. An artificial intelligence engine processes packet header data associated with the packet, and a smart indication is generated. A forwarding decision is made for the packet based on the lookup performed by the lookup generator action handler as well as based on the smart indication generated with the artificial intelligence engine.

A wireless IEEE 802.11 queuing architecture supporting Low Latency Low Loss Scalable throughput (L4S) and Dual Queue Active Queue Management (AQM) in which queues for both L4S streams and classic streams are contained in the medium access control (MAC) layer, and one or more of these queues are configured with more than one internal queue, to which different L4S packets and other packet types are retained in different internal queues within the MAC transmit queues. The MAC queues are configured for MAC layer buffering of L4S packets and classical packets in separate queues and / or queues having internal queues for buffering different packet types, classifications, latency sensitivity, QoS considerations, and so forth. The architecture also allows for multiple packet queues in the upper layers above the MAC layer.

The present application relates to a kind of online packet classification method based on rule prefix space, first initialization rule grouping mapping table and rule split mapping table, respectively for recording rule grouping that rule is assigned to, whether the split of a rule occurs.Record addition and deletion rule, carry out packet classification such as operation can be carried out after the initialization of two mapping tables, when adding rule, scale to rule prefix space, it is added to suitable rule grouping;When deleting rule, it is realized fast processing by the record of two mapping tables.The present application has the advantages that rule prefix space is scaled, and the number of rule grouping is reduced;When selecting rule grouping, optimization is carried out based on priority, so that high priority rule is mainly concentrated in the front rule grouping, while guaranteeing rule update performance, the packet matching rate is improved.

A system and method for quality of experience (QoE)-aware transmission over multi-transport is disclosed. The system receives requests for transmitting data packets from source node to destination node in wireless communication network. Further, the system determines payload data of the data packet and n-tuple information associated with the data packet. Furthermore, the system analyzes packet level metrics associated with determined payload data of data packet. Additionally, system classifies data packets into a latency class (LC) and a Quality of Service (QoS) class based on the analyzed packet level metrics. Further, the system determines connection identifier (ID) associated with data packet. Further, the system determines appropriate multi-transport access network (MTAN) among plurality of MTANs for transmitting data packet to destination node. Furthermore, the system establishes multi-path (MP) backbone connection with destination node using determined appropriate MTAN. Additionally, the system transmits data packet to destination node through established MP backbone connection.

A wireless IEEE 802.11 queuing architecture supporting Low Latency Low Loss Scalable throughput (L4S) and Dual Queue Active Queue Management (AQM) in which queues for both L4S streams and classic streams are contained in the medium access control (MAC) layer, and one or more of these queues are configured with more than one internal queue, to which different L4S packets and other packet types are retained in different internal queues within the MAC transmit queues. The MAC queues are configured for MAC layer buffering of L4S packets and classical packets in separate queues and / or queues having internal queues for buffering different packet types, classifications, latency sensitivity, QoS considerations, and so forth. The architecture also allows for multiple packet queues in the upper layers above the MAC layer.

The application relates to the technical field of network transmission optimization, and discloses a data packet and multi-channel pipeline cooperative transmission optimization method, which comprises the following steps: obtaining a data flow core feature descriptor vector through hierarchical feature extraction and principal component analysis dimension reduction; generating a structured logical data packet set by using information entropy weighted clustering and scale balance adjustment strategies; obtaining a channel pipeline capability matrix by monitoring the real-time state of a multi-channel physical layer and a link layer; establishing a packet channel mapping scheme by using an online learning dynamic distribution and time slot scheduling algorithm; realizing data transmission through a multi-thread concurrent transmission and cross-channel pipeline synchronization control mechanism; recovering an ordered data delivery sequence by using a hash table index packet classification and priority-driven reorganization strategy at a receiving end; and finally continuously optimizing system operation parameters through PID feedback control and an online parameter updating mechanism. The application can realize efficient and reliable transmission of data in a multi-channel environment, reduce transmission delay, and improve system throughput.

Some embodiments relate to systems and methods for low latency control. A communication system can include an application operating on the first device. The application is configured to: 1. classify a first packet provided to the first device as being for reception by a second low latency device, or 2. classify the first packet as being for use in a low latency operation. The application is configured to provide the first packet to a first queue associated with a low latency path.

The invention discloses a universal data analysis method and system, terminal equipment and a storage medium, and relates to the technical field of data analysis. The method comprises the following steps: constructing a first analysis configuration file; the first analysis configuration file comprises a data classification configuration file and a plurality of candidate analysis structure configuration files; the data classification configuration file is used for indicating a mapping relationship between the data packet identifier and the data packet type name; receiving an original data packet sent by the server, and obtaining a data packet identifier of the original data packet; performing data packet classification processing according to the data packet identifier and the data classification configuration file, and determining the data type name of the original data packet; determining a target analytic structure configuration file from the plurality of candidate analytic structure configuration files according to the data type name; performing data analysis processing on the original data packet according to the target analysis structure configuration file to obtain a data analysis result; and displaying a data analysis result on a visual interface. The data analysis efficiency in the communication process can be improved.

The invention provides a tuple structure and hardware acceleration neural network data packet classification method and system, and the method comprises the steps: reconstructing a data packet classification problem into a high-dimensional multi-class classification problem, and generating a unique tuple index for each data packet through a rule priority mechanism; constructing a semi-structured model based on the unique tuple index; the semi-structured model comprises a neural network classification model and a tuple space search structure; and performing classification on the CPU-GPU hybrid streaming framework, predicting a tuple index by the GPU based on a neural network classification model, calling a tuple space search structure by the CPU based on the index to perform accurate search, and outputting a data packet classification result. According to the method, complete coverage of a large-scale rule set is achieved through a single model, rule copying is not needed, the model complexity is remarkably reduced through TSS middleware, the hardware potential is fully released through CPU-GPU assembly line collaborative design, and therefore the classification throughput and stability are remarkably improved.

A method for processing packets, the method comprising receiving a packet by a data processing unit (DPU), making a first determination that there is no exact match flow entry in a hardware switch pipeline in the DPU for the packet, in response to the first determination, classifying, in the DPU, the packet as a data packet, in response to the classifying of the packet: identifying, using a software data plane in the DPU, a forwarding information base (FIB) entry to be used to transmit the packet towards its intended destination, identifying, using the software data plane, a flow associated with the packet, initiating, using the software data plane, programming of an exact match flow entry in the hardware switch pipeline, and initiating, using the software data plane, transmission of the packet towards its intended destination using the FIB entry and the hardware switch pipeline.

The application discloses a data universal analysis method and system, a terminal device and a storage medium, and relates to the technical field of data analysis. The method comprises the following steps: constructing a first analysis configuration file; the first analysis configuration file comprises a data classification configuration file and a plurality of candidate analysis structure configuration files; the data classification configuration file is used for indicating the mapping relationship between the data packet identifier and the data packet type name; receiving the original data packet sent by a server, and obtaining the data packet identifier of the original data packet; performing data packet classification processing according to the data packet identifier and the data classification configuration file, and determining the data type name of the original data packet; determining the target analysis structure configuration file from the plurality of candidate analysis structure configuration files according to the data type name; performing data analysis processing on the original data packet according to the target analysis structure configuration file, and obtaining a data analysis result; and displaying the data analysis result on a visual interface. The data analysis efficiency in the communication process can be improved.

The application discloses a FPGA packet classification method and system based on a heterogeneous hybrid path, and the method comprises the following steps: receiving a network data packet, extracting metadata and temporarily storing the network data packet; constructing a key value according to the metadata of the network data packet, performing fast path lookup and processing based on the constructed key value K through a cuckoo hash to obtain a fast path result, activating a slow path matching and learning to perform rule matching through a ternary content-addressable memory to obtain a slow path result if the fast path is not hit; aligning and arbitrating the fast path result and the slow path result to obtain a final action, and sending the temporarily stored network data packet to a downstream or discarding the temporarily stored network data packet. The application aims to solve the problems of large resource consumption, high power consumption, inability of a hash table to handle conflicts, easy packet loss in rule updating and disorder in multi-path processing in the existing packet classification technology, and realizes FPGA packet classification with high performance, low power consumption, high flexibility and support for lossless hot updating.

The invention discloses a queue scheduling method and device, electronic equipment and a storage medium. Comprising the following steps: receiving a to-be-transmitted data packet corresponding to a target power system, and determining a data packet classification identifier of the to-be-transmitted data packet; determining target queue scheduling information corresponding to the to-be-transmitted data packet based on the data packet classification identifier and queue scheduling configuration information, the queue scheduling configuration information including static queue scheduling configuration information and dynamic queue scheduling configuration information, the dynamic queue scheduling configuration information comprises dynamic queue scheduling information updated based on power grid state change data of the target power system, and the target queue scheduling information comprises flow queue scheduling information, user queue scheduling information and port queue scheduling information; and executing multi-level queue scheduling through a preset scheduling algorithm based on each item of information in the target queue scheduling information, so as to transmit the to-be-transmitted data packet to a target data receiving end. The target queue scheduling information is dynamically determined, so that the accuracy and the adaptability of queue scheduling are improved.