CN116996397A - Network packet loss optimization method and device, storage medium and electronic equipment - Google Patents
Network packet loss optimization method and device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN116996397A CN116996397A CN202311263633.7A CN202311263633A CN116996397A CN 116996397 A CN116996397 A CN 116996397A CN 202311263633 A CN202311263633 A CN 202311263633A CN 116996397 A CN116996397 A CN 116996397A
- Authority
- CN
- China
- Prior art keywords
- network
- data
- packet loss
- predicted
- network packet
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000005457 optimization Methods 0.000 title claims abstract description 27
- 238000003860 storage Methods 0.000 title claims abstract description 22
- 238000003062 neural network model Methods 0.000 claims abstract description 71
- 230000005540 biological transmission Effects 0.000 claims abstract description 40
- 238000010586 diagram Methods 0.000 claims description 32
- 230000015654 memory Effects 0.000 claims description 24
- 238000004590 computer program Methods 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 16
- 238000013528 artificial neural network Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 abstract description 12
- 238000012545 processing Methods 0.000 description 19
- 230000006870 function Effects 0.000 description 12
- 238000006243 chemical reaction Methods 0.000 description 9
- 230000006872 improvement Effects 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 6
- 239000004973 liquid crystal related substance Substances 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 210000005036 nerve Anatomy 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000001537 neural effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 229920001296 polysiloxane Polymers 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 239000010979 ruby Substances 0.000 description 1
- 229910001750 ruby Inorganic materials 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/147—Network analysis or design for predicting network behaviour
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/16—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0823—Errors, e.g. transmission errors
- H04L43/0829—Packet loss
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/02—Topology update or discovery
- H04L45/08—Learning-based routing, e.g. using neural networks or artificial intelligence
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/12—Shortest path evaluation
- H04L45/123—Evaluation of link metrics
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Environmental & Geological Engineering (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The specification discloses a method, a device, a storage medium and electronic equipment for optimizing network packet loss. In the network packet loss optimization process, the graph neural network model to be trained can be trained through the sample data and the real network packet loss data corresponding to the sample data, and then the trained graph neural network model can be deployed into the multi-mode network, so that the optimal routing path can be determined according to the predicted network packet loss data under each preset routing path output by the trained graph neural network model and the actual network packet loss data of the multi-mode network under the current routing path, and the packet loss rate of the multi-mode network in the data transmission process can be reduced.
Description
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to a method and apparatus for optimizing network packet loss, a storage medium, and an electronic device.
Background
Nowadays, with the development of technology, the demands of people for network service quality are continuously improved, and the multi-mode network can dynamically allocate network resources based on the actual demands of the existing service, so that the development of the modern society and the progress of the human society are promoted.
In practice, the existing multi-mode network cannot realize a low network packet loss rate, where network packet loss refers to a situation that, during the transmission of network data, a data packet is discarded because of various reasons, the data packet is not transmitted to an application program yet. However, the situation that the network packet loss rate is high is faced in the process of data transmission through the multi-mode network at present, but the network packet loss rate optimization method of the multi-mode network at present cannot well optimize the network packet loss rate of the multi-mode network in the process of data transmission, which may cause some situations to occur in the process of data transmission through the multi-mode network.
Therefore, how to flexibly and efficiently optimize the network packet loss rate of the multi-mode network becomes a current urgent problem to be solved.
Disclosure of Invention
The present disclosure provides a method, an apparatus, a storage medium, and an electronic device for optimizing network packet loss, so as to partially solve the foregoing problems in the prior art.
The technical scheme adopted in the specification is as follows:
the specification provides a method for optimizing network packet loss, which comprises the following steps:
acquiring sample data, wherein the sample data at least comprises modal information data used for representing service types of services which can be processed of all equipment nodes in each network link diagram related under a multi-modal network, service flow information data used for representing flow use conditions and flow direction conditions of all equipment nodes in each network link diagram related under the multi-modal network, network bandwidth information data used for representing all equipment nodes in each network link diagram related under the multi-modal network and network topology information data used for representing network structures of all network link diagrams related under the multi-modal network, wherein the network link diagram is used for representing network connection relations between equipment nodes corresponding to user equipment and equipment nodes corresponding to a switch, and the multi-modal network is used for optimizing transmission strategies of data of all network links according to the service types of all network links;
Inputting the sample data into a graph neural network model to be trained to obtain predicted network packet loss data for the multi-modal network, wherein the predicted network packet loss data is used for representing predicted data loss conditions when data transmission of each device is realized through the multi-modal network;
training the graph neural network model by taking the deviation between the minimum predicted network packet loss data and the real network packet loss data corresponding to the sample data as an optimization target;
and deploying the trained graph neural network model into the multi-mode network to determine an optimal routing path based on the predicted network packet loss data under each preset routing path output by the trained graph neural network model and the actual network packet loss data under the current routing path used by the multi-mode network for currently transmitting data, and transmitting data according to the optimal routing path, wherein the routing path is formed by network links.
Optionally, the graph neural network corresponding to the graph neural network model to be trained is constructed according to network topology information data in the sample data.
Optionally, inputting the sample data to a graph neural network model to be trained to obtain predicted network packet loss data for the multi-modal network, which specifically includes:
Inputting the sample data into a graph neural network model to be trained, and determining predicted network packet loss data of each device aiming at the multi-mode network;
and determining the predicted network packet loss data aiming at the multi-mode network according to the predicted network packet loss data of each device.
Optionally, determining the optimal routing path based on the predicted network packet loss data under each preset routing path output by the trained graph neural network model and the actual network packet loss data under the current routing path used by the current transmission data of the multi-mode network specifically includes:
determining the predicted network packet loss data of each device under each preset routing path based on the trained graph neural network model;
for each preset routing path, carrying out weighted average on the predicted network packet loss data of each device under the preset routing path, and determining the data obtained after weighted average as the predicted network packet loss data under the preset routing path;
and determining a route path corresponding to the least network packet loss data in the predicted network packet loss data under each preset route path and the actual network packet loss data under the current route path used by the current transmission data of the multi-mode network as an optimal route path.
The present specification provides a device for optimizing network packet loss, including:
an obtaining module, configured to obtain sample data, where the sample data includes at least modality information data for indicating a service type of a service that can be processed by each device node in each network link graph involved in a multi-modal network, service flow information data for indicating a flow usage situation and a flow direction situation of each device node in each network link graph involved in the multi-modal network, network bandwidth information data for indicating each device node in each network link graph involved in the multi-modal network, and network topology information data for indicating a network structure of each network link graph involved in the multi-modal network, where the network link graph is used to indicate a network connection relationship between a device node corresponding to a user device and a device node corresponding to a switch, and the multi-modal network is used to optimize a transmission policy of data of each network link according to the service type of each network link;
the input module is used for inputting the sample data into a graph neural network model to be trained so as to obtain predicted network packet loss data aiming at the multi-mode network, wherein the predicted network packet loss data is used for representing predicted data loss conditions when data transmission of each device is realized through the multi-mode network;
The training module is used for training the graph neural network model by taking the deviation between the minimum predicted network packet loss data and the real network packet loss data corresponding to the sample data as an optimization target;
the determining module is used for deploying the trained graph neural network model into the multi-mode network so as to determine an optimal routing path based on the predicted network packet loss data under each preset routing path output by the trained graph neural network model and the actual network packet loss data under the current routing path used by the current transmission data of the multi-mode network, and transmitting data according to the optimal routing path, wherein the routing path is formed by network links.
Optionally, the graph neural network corresponding to the graph neural network model to be trained is constructed according to network topology information data in the sample data.
Optionally, the input module is specifically configured to input the sample data to a graph neural network model to be trained, and determine predicted network packet loss data of each device for the multi-modal network; and determining the predicted network packet loss data aiming at the multi-mode network according to the predicted network packet loss data of each device.
Optionally, the determining module is specifically configured to determine, based on the trained graph neural network model, predicted network packet loss data of each device under each preset routing path; for each preset routing path, carrying out weighted average on the predicted network packet loss data of each device under the preset routing path, and determining the data obtained after weighted average as the predicted network packet loss data under the preset routing path; and determining a route path corresponding to the least network packet loss data in the predicted network packet loss data under each preset route path and the actual network packet loss data under the current route path used by the current transmission data of the multi-mode network as an optimal route path.
The present specification provides a computer readable storage medium storing a computer program which when executed by a processor implements the method of network packet loss optimization described above.
The present specification provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method of network packet loss optimization described above when executing the program.
The above-mentioned at least one technical scheme that this specification adopted can reach following beneficial effect:
the method for optimizing network packet loss provided in the present specification obtains sample data, where the sample data includes at least modality information data for representing service types of services that can be handled by each device node in each network link graph involved in a multi-modal network, traffic flow information data for representing traffic usage and traffic flow conditions of each device node in each network link graph involved in the multi-modal network, network bandwidth information data for representing each device node in each network link graph involved in the multi-modal network, and network topology information data for representing network structures of each network link graph involved in the multi-modal network, where the network link graph is used to represent network connection relationships between device nodes corresponding to user devices and device nodes corresponding to switches, the multi-modal network is used for optimizing the transmission strategy of the data of each network link according to the service type of each network link, inputting the sample data into a graph neural network model to be trained to obtain predicted network packet loss data for the multi-modal network, wherein the predicted network packet loss data is used for representing the predicted data loss condition when the data transmission of each device is realized through the multi-modal network, taking the deviation between the predicted network packet loss data and the real network packet loss data corresponding to the sample data as an optimization target, training the graph neural network model, deploying the trained graph neural network model into the multi-modal network to obtain the predicted network packet loss data under each preset routing path output based on the trained graph neural network model, and determining an optimal routing path according to actual network packet loss data under a current routing path used by the current transmission data of the multi-mode network, and transmitting data according to the optimal routing path, wherein the routing path is formed by network links.
According to the method, in the network packet loss optimization process, the graph neural network model to be trained can be trained through the sample data and the real network packet loss data corresponding to the sample data, and then the trained graph neural network model can be deployed into the multi-mode network, so that the optimal routing path can be determined according to the predicted network packet loss data under each preset routing path and the actual network packet loss data of the multi-mode network under the current routing path, which are output by the trained graph neural network model, so that the packet loss rate of the multi-mode network in the data transmission process can be reduced.
Drawings
The accompanying drawings, which are included to provide a further understanding of the specification, illustrate and explain the exemplary embodiments of the present specification and their description, are not intended to limit the specification unduly. In the drawings:
fig. 1 is a flow chart of a method for optimizing network packet loss provided in the present specification;
fig. 2 is a schematic diagram of a training data set for network packet loss optimization provided in the present specification;
FIG. 3 is a schematic diagram of the structure of a neural network model of the type provided in the present specification;
Fig. 4 is a schematic diagram of logic for network packet loss optimization provided in the present specification;
fig. 5 is a schematic diagram of a network packet loss optimization device structure provided in the present specification;
fig. 6 is a schematic structural diagram of the electronic device corresponding to fig. 1 provided in the present specification.
Detailed Description
For the purposes of making the objects, technical solutions and advantages of the present specification more apparent, the technical solutions of the present specification will be clearly and completely described below with reference to specific embodiments of the present specification and corresponding drawings. It will be apparent that the described embodiments are only some, but not all, of the embodiments of the present specification. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are intended to be within the scope of the present disclosure.
The following describes in detail the technical solutions provided by the embodiments of the present specification with reference to the accompanying drawings.
Fig. 1 is a flow chart of a method for optimizing network packet loss, provided in the present specification, including the following steps:
s101: sample data is obtained, wherein the sample data at least comprises modal information data used for representing service types of services which can be processed of all equipment nodes in each network link diagram related under the multi-modal network, service flow information data used for representing traffic use conditions and traffic flow direction conditions of all equipment nodes in each network link diagram related under the multi-modal network, network bandwidth information data used for representing all equipment nodes in each network link diagram related under the multi-modal network and network topology information data used for representing network structures of all network link diagrams related under the multi-modal network, wherein the network link diagram is used for representing network connection relations between equipment nodes corresponding to user equipment and equipment nodes corresponding to a switch, and the multi-modal network is used for optimizing transmission strategies of data of all network links according to the service types of all network links.
S102: and inputting the sample data into a graph neural network model to be trained to obtain predicted network packet loss data for the multi-mode network, wherein the predicted network packet loss data is used for representing predicted data loss conditions when data transmission of each device is realized through the multi-mode network.
The execution body of the network packet loss optimization method in the present specification may be a terminal device such as a desktop computer or a notebook computer, or may be a server, and the method of network packet loss optimization in the embodiment of the present specification will be described below by taking the terminal device as an example of the execution body.
In the present description, the terminal device first acquires sample data.
The sample data herein refers to data collected by the terminal device every predetermined time period, where the sample data includes at least modal information data for indicating a service type of a service that can be handled by each device node in each network link graph related in the multi-modal network, traffic flow information data for indicating a traffic usage situation and a traffic flow situation of each device node in each network link graph related in the multi-modal network, network bandwidth information data for indicating each device node in each network link graph related in the multi-modal network, and network topology information data for indicating a network structure of each network link graph related in the multi-modal network, where the network link graph is used to indicate a network connection relationship between a device node corresponding to the user device and a device node corresponding to the switch, and the multi-modal network herein may be used to optimize a transmission policy of data of each network link according to the service type of each network link.
The above-mentioned modal information data may specifically be, when the service that can be processed by each device node in each network link diagram related under the multi-modal network is a cloud computing service, the service type corresponding to the service is a cloud computing service type, and at this time, the modal information data may be data for representing "cloud computing service type".
The network topology information data may specifically be that when the user equipment involved in the multi-mode network is an A1 device, an A2 device, a B1 device, and a B2 device, and the switches involved in the multi-mode network are an a switch and a B switch, then the network links may include the following eight network links: the network links formed by the connection of the A1 device and the a switch, the network links formed by the connection of the A2 device and the a switch, the network links formed by the connection of the B1 device and the a switch, the network links formed by the connection of the A1 device and the B switch, the network links formed by the connection of the A2 device and the B switch, and the network links formed by the connection of the B1 device and the B switch correspond to respective network link graphs respectively, and the integrated graph can be a graph obtained by integrating the network link graphs of the eight network links, which can be network topology information data describing the network structure of each network link graph involved in the multi-mode network.
In addition, the terminal device can also obtain the real network packet loss data corresponding to the sample data.
The sample data and the real network packet loss data corresponding to the sample data can form a training data set for subsequent training of the graph neural network model to be trained.
Fig. 2 is a schematic diagram of a training data set for network packet loss optimization provided in the present specification.
As shown in fig. 2, the training dataset includes network topology information data of the multi-modal network, characteristic information of the multi-modal network (the characteristic information includes the modal information data of the multi-modal network, the network bandwidth information data of the multi-modal network), and network traffic information of the multi-modal network (the network traffic information includes the traffic information data of the multi-modal network).
Once the sample data and the real network packet loss data corresponding to the sample data are obtained, the terminal device can input the sample data into a graph neural network model to be trained so as to obtain predicted network packet loss data for the multi-mode network, wherein the predicted network packet loss data are used for representing predicted data loss conditions when data transmission of each device is realized through the multi-mode network. The graph neural network corresponding to the graph neural network model to be trained is constructed according to the network topology information data in the sample data.
Fig. 3 is a schematic diagram of a structure of a neural network model provided in the present specification.
As shown in fig. 3, the graph neural network model mainly includes four network layers: a network link message processing layer, an encoding layer in the feedforward neural network, a network routing path message processing layer, a decoding layer in the feedforward neural network.
Specifically, the first layer is a network link message processing layer, status sensing is performed on network links in the multi-mode network through long-term memory (Long Short Term Memory, LSTM), the layer takes characteristic information characteristic vectors in the multi-mode network as input, then dependency relations between network links and routing topology are grabbed through LSTM nerve units in the hidden layer, and then packet loss information of the links in the network is calculated and updated, wherein LSTM is a special recurrent nerve network.
The second layer is a coding layer in the feedforward neural network, the output of the LSTM neural unit is reconstructed and abstract features are extracted, the layer is a supervised learning process, training can be completed only by knowing the label of the data, namely, the layer completes feature extraction and reconstruction of the input data under the supervised condition (the second layer corresponds to a downsampling module).
The third layer is a network route path message processing layer, the state sensing is carried out on the route paths in the multi-mode network through the LSTM, the layer takes the characteristic information characteristic vectors in the multi-mode network as input, then the dependency relationship between the network paths and the route topology is grabbed through the LSTM nerve units in the hidden layer, and then the packet loss information of the paths in the network is calculated and updated (the connection mode between the second layer and the third layer can be residual connection, and the connection mode between the subsequent third layer and the fourth layer can be residual connection).
The fourth layer is a decoding layer in the feedforward neural network, and obtains the output of the LSTM neural unit, namely, the hidden variable of the hidden layer is reconstructed and restored to the initial input dimension, and the hidden structure of the decoding layer is utilized to read and restore the packet loss information, so as to obtain the network packet loss prediction data (the fourth layer corresponds to an up-sampling module).
And then, outputting the network packet loss prediction data.
Specifically, the processing mode of the first layer (i.e., the network link message processing layer) and the processing mode of the third layer (i.e., the network routing path message processing layer) may include three stages of message conversion, message update and message readout.
In the first layer, the relevant data of the whole network link may be determined by first determining the relevant data of the whole network link according to the sample data in the message conversion stage of the first layer, and then converted into the data representation of the network node and the adjacent edge in the network topology according to the relevant data of the whole network link, and output to other nodes in the network topology.
The output data after message conversion corresponding to the message conversion stage of the first layer can be usedThe formula may be expressed as follows:
in the above-mentioned method, the step of,for a device node in the network topology +.>Adjacent node of->，/>For equipment nodesStatus of (2) and device node->The status of the device node herein may specifically include traffic flow information data for expressing traffic usage and traffic flow conditions of the device node in the multi-mode network, network bandwidth information data of the device node in the multi-mode network, and connection data for expressing connection conditions between the device node and other device nodes or between the device node and the switch, E (n, m) being an edge of the device node n and an edge of the device node m,and T is the preset iteration number, and T is the current iteration number, wherein the T is the preset message conversion function.
In the first layer message updating stage, the output data after message conversion according to the first layer message conversion stageAnd +.>Device node->Update the status of (1) to determine +.>Output data as a message update phase of a first layer，/>The specific determination formula is as follows:
wherein, the liquid crystal display device comprises a liquid crystal display device,for the number of iterations->Is->The state of the device node n at the number of iterations,updating the function for a preset message, +.>Is output data after message conversion in the message conversion stage of the first layer, and T is preset iteration times.
Then, in the message reading phase of the first layer, the output data according to the message updating phase of the first layerDetermining the output data of the first layer in the message reading phase (i.e. the output data of the first layer), the output data of the first layer in the message reading phase is +.>Indicating (I)>The specific determination formula is as follows:
wherein, the liquid crystal display device comprises a liquid crystal display device,for the number of iterations->Feature vectors representing map data corresponding to the network topology of a computing network->Reading out a function for a predetermined message, +.>Is->The state of the device node n at the iteration number.
The same applies to the processing manner of the third layer (i.e., the network routing path message processing layer), except that "through determining the relevant data of the whole network link according to the sample data" in the processing manner of the first layer (i.e., the network link message processing layer) is replaced by "through determining the relevant data of the whole routing path according to the sample data", so that the description is omitted herein. It should be noted that the third layer (i.e. the network routing path message processing layer) is finally determined Refers to predicted network packet loss data for a multi-mode network.
S103: and training the graph neural network model by taking the deviation between the minimum predicted network packet loss data and the real network packet loss data corresponding to the sample data as an optimization target.
S104: and deploying the trained graph neural network model into the multi-mode network to determine an optimal routing path based on the predicted network packet loss data under each preset routing path output by the trained graph neural network model and the actual network packet loss data under the current routing path used by the multi-mode network for currently transmitting data, and transmitting data according to the optimal routing path, wherein the routing path is formed by network links.
After the predicted network packet loss data for the multi-mode network is determined, the terminal device can minimize the deviation between the predicted network packet loss data and the real network packet loss data corresponding to the sample data as an optimization target, train the graph neural network model, and deploy the trained graph neural network model into the multi-mode network so as to determine an optimal routing path based on the predicted network packet loss data under each preset routing path output by the trained graph neural network model and the actual network packet loss data under the current routing path used by the current transmission data of the multi-mode network, and perform data transmission according to the optimal routing path, wherein the routing path is formed by network links.
The determination of the optimal routing path may specifically be: the terminal equipment firstly determines the predicted network packet loss data of each device under each preset routing path based on the trained graph neural network model, then carries out weighted average on the predicted network packet loss data of each device under the preset routing path aiming at each preset routing path, determines the data obtained after weighted average as the predicted network packet loss data under the preset routing path, and determines the routing path corresponding to the least network packet loss data in the predicted network packet loss data under each preset routing path and the actual network packet loss data under the current routing path used by the current transmission data of the multi-mode network as the optimal routing path.
Fig. 4 is a schematic diagram of logic for network packet loss optimization provided in the present specification.
As shown in fig. 4, first, the terminal device may acquire sample data, and then may construct a graph neural network model to be trained, and train the graph neural network model based on the sample data and real network packet loss data corresponding to the sample data.
Once the training of the graph neural network model is completed, the terminal device may deploy the graph neural network model into the multi-modal network, so as to determine an optimal routing path based on the predicted network packet loss data under the preset routing path output by the trained graph neural network model and the actual network packet loss data under the current routing path of the multi-modal network (specifically, in each preset routing path, the predicted network packet loss data of the routing path is determined by the above-mentioned weighted average mode first, then the minimum value in the predicted network packet loss data of each preset routing path is determined, the terminal device compares the minimum value with the actual network packet loss data under the current routing path, and if the minimum value is determined to be smaller than the actual network packet loss data under the current routing path, the control layer of the multi-modal network switches the current routing path into the preset routing path corresponding to the minimum value, and if the minimum value is determined to be not smaller than the actual network packet loss data under the current routing path, the current routing path is maintained by the multi-modal network.
According to the method, in the network packet loss optimization process, the graph neural network model to be trained can be trained through the sample data and the real network packet loss data corresponding to the sample data, and then the trained graph neural network model can be deployed into the multi-mode network, so that the optimal routing path can be determined according to the predicted network packet loss data under each preset routing path and the actual network packet loss data of the multi-mode network under the current routing path, which are output by the trained graph neural network model, so that the packet loss rate of the multi-mode network in the data transmission process can be reduced.
The foregoing is a method implemented by one or more of the embodiments of the present disclosure, and based on the same concept, the present disclosure further provides a corresponding network packet loss optimization device, as shown in fig. 5.
Fig. 5 is a schematic diagram of a network packet loss optimization device provided in the present specification, including:
an obtaining module 501, configured to obtain sample data, where the sample data includes at least modality information data for indicating a service type of a service that can be processed by each device node in each network link graph involved in a multi-modal network, service flow information data for indicating a flow usage situation and a flow direction situation of each device node in each network link graph involved in the multi-modal network, network bandwidth information data for indicating each device node in each network link graph involved in the multi-modal network, and network topology information data for indicating a network structure of each network link graph involved in the multi-modal network, where the network link graph is used to indicate a network connection relationship between a device node corresponding to a user device and a device node corresponding to a switch, and the multi-modal network is used to optimize a transmission policy of data of each network link according to the service type of each network link;
The input module 502 is configured to input the sample data to a neural network model to be trained, so as to obtain predicted network packet loss data for the multi-modal network, where the predicted network packet loss data is used to represent predicted data loss conditions when data transmission of each device is implemented through the multi-modal network;
a training module 503, configured to train the graph neural network model with a deviation between the minimum predicted network packet loss data and the real network packet loss data corresponding to the sample data as an optimization target;
the determining module 504 is configured to deploy a trained graph neural network model into the multi-modal network, so as to determine an optimal routing path based on predicted network packet loss data under each preset routing path output by the trained graph neural network model and actual network packet loss data under a current routing path used by the multi-modal network for current data transmission, and perform data transmission according to the optimal routing path, where the routing path is formed by network links.
Optionally, the graph neural network corresponding to the graph neural network model to be trained is constructed according to network topology information data in the sample data.
Optionally, the input module 502 is specifically configured to input the sample data to a graph neural network model to be trained, and determine predicted network packet loss data of each device for the multi-modal network; and determining the predicted network packet loss data aiming at the multi-mode network according to the predicted network packet loss data of each device.
Optionally, the determining module 504 is specifically configured to determine, based on the trained neural network model, predicted network packet loss data of each device under each preset routing path; for each preset routing path, carrying out weighted average on the predicted network packet loss data of each device under the preset routing path, and determining the data obtained after weighted average as the predicted network packet loss data under the preset routing path; and determining a route path corresponding to the least network packet loss data in the predicted network packet loss data under each preset route path and the actual network packet loss data under the current route path used by the current transmission data of the multi-mode network as an optimal route path.
The present specification also provides a computer readable storage medium storing a computer program operable to perform a method of network packet loss optimization as provided in fig. 1 above.
The present specification also provides a schematic structural diagram of an electronic device corresponding to fig. 1 shown in fig. 6. At the hardware level, as shown in fig. 6, the electronic device includes a processor, an internal bus, a network interface, a memory, and a nonvolatile storage, and may of course include hardware required by other services. The processor reads the corresponding computer program from the nonvolatile memory into the memory and then runs the computer program to realize the network packet loss optimization method described in the above figure 1.
Of course, other implementations, such as logic devices or combinations of hardware and software, are not excluded from the present description, that is, the execution subject of the following processing flows is not limited to each logic unit, but may be hardware or logic devices.
In the 90 s of the 20 th century, improvements to one technology could clearly be distinguished as improvements in hardware (e.g., improvements to circuit structures such as diodes, transistors, switches, etc.) or software (improvements to the process flow). However, with the development of technology, many improvements of the current method flows can be regarded as direct improvements of hardware circuit structures. Designers almost always obtain corresponding hardware circuit structures by programming improved method flows into hardware circuits. Therefore, an improvement of a method flow cannot be said to be realized by a hardware entity module. For example, a programmable logic device (Programmable Logic Device, PLD) (e.g., field programmable gate array (Field Programmable Gate Array, FPGA)) is an integrated circuit whose logic function is determined by the programming of the device by a user. A designer programs to "integrate" a digital system onto a PLD without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Moreover, nowadays, instead of manually manufacturing integrated circuit chips, such programming is mostly implemented by using "logic compiler" software, which is similar to the software compiler used in program development and writing, and the original code before the compiling is also written in a specific programming language, which is called hardware description language (Hardware Description Language, HDL), but not just one of the hdds, but a plurality of kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), lava, lola, myHDL, PALASM, RHDL (Ruby Hardware Description Language), etc., VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog are currently most commonly used. It will also be apparent to those skilled in the art that a hardware circuit implementing the logic method flow can be readily obtained by merely slightly programming the method flow into an integrated circuit using several of the hardware description languages described above.
The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer readable medium storing computer readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable logic controllers, and embedded microcontrollers, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, atmel AT91SAM, microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic of the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller in a pure computer readable program code, it is well possible to implement the same functionality by logically programming the method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc. Such a controller may thus be regarded as a kind of hardware component, and means for performing various functions included therein may also be regarded as structures within the hardware component. Or even means for achieving the various functions may be regarded as either software modules implementing the methods or structures within hardware components.
The system, apparatus, module or unit set forth in the above embodiments may be implemented in particular by a computer chip or entity, or by a product having a certain function. One typical implementation is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being functionally divided into various units, respectively. Of course, the functions of each element may be implemented in one or more software and/or hardware elements when implemented in the present specification.
It will be appreciated by those skilled in the art that embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, the present specification may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present description can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
The present description is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the specification. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
It will be appreciated by those skilled in the art that embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, the present specification may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present description can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
The description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.
The foregoing is merely exemplary of the present disclosure and is not intended to limit the disclosure. Various modifications and alterations to this specification will become apparent to those skilled in the art. Any modifications, equivalent substitutions, improvements, or the like, which are within the spirit and principles of the present description, are intended to be included within the scope of the claims of the present description.
Claims (10)
1. A method for optimizing network packet loss, comprising:
acquiring sample data, wherein the sample data at least comprises modal information data used for representing service types of services which can be processed of all equipment nodes in each network link diagram related under a multi-modal network, service flow information data used for representing flow use conditions and flow direction conditions of all equipment nodes in each network link diagram related under the multi-modal network, network bandwidth information data used for representing all equipment nodes in each network link diagram related under the multi-modal network and network topology information data used for representing network structures of all network link diagrams related under the multi-modal network, wherein the network link diagram is used for representing network connection relations between equipment nodes corresponding to user equipment and equipment nodes corresponding to a switch, and the multi-modal network is used for optimizing transmission strategies of data of all network links according to the service types of all network links;
inputting the sample data into a graph neural network model to be trained to obtain predicted network packet loss data for the multi-modal network, wherein the predicted network packet loss data is used for representing predicted data loss conditions when data transmission of each device is realized through the multi-modal network;
Training the graph neural network model by taking the deviation between the minimum predicted network packet loss data and the real network packet loss data corresponding to the sample data as an optimization target;
and deploying the trained graph neural network model into the multi-mode network to determine an optimal routing path based on the predicted network packet loss data under each preset routing path output by the trained graph neural network model and the actual network packet loss data under the current routing path used by the multi-mode network for currently transmitting data, and transmitting data according to the optimal routing path, wherein the routing path is formed by network links.
2. The method of claim 1, wherein the graph neural network corresponding to the graph neural network model to be trained is constructed from network topology information data in the sample data.
3. The method of claim 1, wherein inputting the sample data to a graph neural network model to be trained to obtain predicted network packet loss data for the multi-modal network, comprises:
inputting the sample data into a graph neural network model to be trained, and determining predicted network packet loss data of each device aiming at the multi-mode network;
And determining the predicted network packet loss data aiming at the multi-mode network according to the predicted network packet loss data of each device.
4. The method of claim 1, wherein determining the optimal routing path based on the predicted network packet loss data under each preset routing path output by the trained graph neural network model and the actual network packet loss data under the current routing path used by the current transmission data of the multi-modal network specifically comprises:
determining the predicted network packet loss data of each device under each preset routing path based on the trained graph neural network model;
for each preset routing path, carrying out weighted average on the predicted network packet loss data of each device under the preset routing path, and determining the data obtained after weighted average as the predicted network packet loss data under the preset routing path;
and determining a route path corresponding to the least network packet loss data in the predicted network packet loss data under each preset route path and the actual network packet loss data under the current route path used by the current transmission data of the multi-mode network as an optimal route path.
5. A device for optimizing network packet loss, comprising:
An obtaining module, configured to obtain sample data, where the sample data includes at least modality information data for indicating a service type of a service that can be processed by each device node in each network link graph involved in a multi-modal network, service flow information data for indicating a flow usage situation and a flow direction situation of each device node in each network link graph involved in the multi-modal network, network bandwidth information data for indicating each device node in each network link graph involved in the multi-modal network, and network topology information data for indicating a network structure of each network link graph involved in the multi-modal network, where the network link graph is used to indicate a network connection relationship between a device node corresponding to a user device and a device node corresponding to a switch, and the multi-modal network is used to optimize a transmission policy of data of each network link according to the service type of each network link;
the input module is used for inputting the sample data into a graph neural network model to be trained so as to obtain predicted network packet loss data aiming at the multi-mode network, wherein the predicted network packet loss data is used for representing predicted data loss conditions when data transmission of each device is realized through the multi-mode network;
The training module is used for training the graph neural network model by taking the deviation between the minimum predicted network packet loss data and the real network packet loss data corresponding to the sample data as an optimization target;
the determining module is used for deploying the trained graph neural network model into the multi-mode network so as to determine an optimal routing path based on the predicted network packet loss data under each preset routing path output by the trained graph neural network model and the actual network packet loss data under the current routing path used by the current transmission data of the multi-mode network, and transmitting data according to the optimal routing path, wherein the routing path is formed by network links.
6. The apparatus of claim 5, wherein the neural network corresponding to the neural network model to be trained is constructed from network topology information data in the sample data.
7. The apparatus of claim 5, wherein the input module is specifically configured to input the sample data to a neural network model to be trained, determine predicted network packet loss data for each device of the multi-modal network; and determining the predicted network packet loss data aiming at the multi-mode network according to the predicted network packet loss data of each device.
8. The apparatus of claim 5, wherein the determining module is specifically configured to determine, based on the trained graph neural network model, predicted network packet loss data for each device under each preset routing path; for each preset routing path, carrying out weighted average on the predicted network packet loss data of each device under the preset routing path, and determining the data obtained after weighted average as the predicted network packet loss data under the preset routing path; and determining a route path corresponding to the least network packet loss data in the predicted network packet loss data under each preset route path and the actual network packet loss data under the current route path used by the current transmission data of the multi-mode network as an optimal route path.
9. A computer readable storage medium, characterized in that the storage medium stores a computer program which, when executed by a processor, implements the method of any of the preceding claims 1-4.
10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method of any of the preceding claims 1-4 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311263633.7A CN116996397B (en) | 2023-09-27 | 2023-09-27 | Network packet loss optimization method and device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311263633.7A CN116996397B (en) | 2023-09-27 | 2023-09-27 | Network packet loss optimization method and device, storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116996397A true CN116996397A (en) | 2023-11-03 |
| CN116996397B CN116996397B (en) | 2024-01-09 |
Family
ID=88530703
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311263633.7A Active CN116996397B (en) | 2023-09-27 | 2023-09-27 | Network packet loss optimization method and device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116996397B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108809839A (en) * | 2018-07-17 | 2018-11-13 | 湖南理工学院 | Wireless Mesh backbone network network flow control methods and device |
| EP3407267A1 (en) * | 2017-05-25 | 2018-11-28 | Hitachi, Ltd. | Deep learning network architecture optimization for uncertainty estimation in regression |
| CN111652351A (en) * | 2020-05-09 | 2020-09-11 | 济南浪潮高新科技投资发展有限公司 | Deployment method, device and medium of neural network model |
| CN113158543A (en) * | 2021-02-02 | 2021-07-23 | 浙江工商大学 | Intelligent prediction method for software defined network performance |
| CN113285831A (en) * | 2021-05-24 | 2021-08-20 | 广州大学 | Network behavior knowledge intelligent learning method and device, computer equipment and storage medium |
| CN113395207A (en) * | 2021-06-15 | 2021-09-14 | 北京工业大学 | Deep reinforcement learning-based route optimization framework and method under SDN framework |
| CN113938415A (en) * | 2021-09-09 | 2022-01-14 | 华中科技大学 | Network route forwarding method and system based on link state estimation |
| CN115314407A (en) * | 2022-08-03 | 2022-11-08 | 东南大学 | Network flow based online game QoE detection method |
| WO2023036042A1 (en) * | 2021-09-07 | 2023-03-16 | 华为技术有限公司 | Method, apparatus and system for determining network optimization policy |
| CN116152591A (en) * | 2022-11-25 | 2023-05-23 | 中山大学 | Model training method, infrared small target detection method and device and electronic equipment |
| CN116527567A (en) * | 2023-06-30 | 2023-08-01 | 南京信息工程大学 | Intelligent network path optimization method and system based on deep reinforcement learning |
-
2023
- 2023-09-27 CN CN202311263633.7A patent/CN116996397B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3407267A1 (en) * | 2017-05-25 | 2018-11-28 | Hitachi, Ltd. | Deep learning network architecture optimization for uncertainty estimation in regression |
| CN108809839A (en) * | 2018-07-17 | 2018-11-13 | 湖南理工学院 | Wireless Mesh backbone network network flow control methods and device |
| CN111652351A (en) * | 2020-05-09 | 2020-09-11 | 济南浪潮高新科技投资发展有限公司 | Deployment method, device and medium of neural network model |
| CN113158543A (en) * | 2021-02-02 | 2021-07-23 | 浙江工商大学 | Intelligent prediction method for software defined network performance |
| CN113285831A (en) * | 2021-05-24 | 2021-08-20 | 广州大学 | Network behavior knowledge intelligent learning method and device, computer equipment and storage medium |
| CN113395207A (en) * | 2021-06-15 | 2021-09-14 | 北京工业大学 | Deep reinforcement learning-based route optimization framework and method under SDN framework |
| WO2023036042A1 (en) * | 2021-09-07 | 2023-03-16 | 华为技术有限公司 | Method, apparatus and system for determining network optimization policy |
| CN113938415A (en) * | 2021-09-09 | 2022-01-14 | 华中科技大学 | Network route forwarding method and system based on link state estimation |
| CN115314407A (en) * | 2022-08-03 | 2022-11-08 | 东南大学 | Network flow based online game QoE detection method |
| CN116152591A (en) * | 2022-11-25 | 2023-05-23 | 中山大学 | Model training method, infrared small target detection method and device and electronic equipment |
| CN116527567A (en) * | 2023-06-30 | 2023-08-01 | 南京信息工程大学 | Intelligent network path optimization method and system based on deep reinforcement learning |
Non-Patent Citations (2)
| Title |
|---|
| 李奇越;周娜娜;柳传嘉;王建平;孙伟;: "基于强化学习的M2M通信上行链路节能优化算法", 合肥工业大学学报(自然科学版), no. 07 * |
| 李建平;王晓凯;: "基于模糊神经网络的无线传感器网络可靠性评估", 计算机应用, no. 2 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116996397B (en) | 2024-01-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111930486B (en) | Task selection data processing method, device, equipment and storage medium | |
| CN115981870B (en) | Data processing method and device, storage medium and electronic equipment | |
| CN116167461A (en) | Model training method and device, storage medium and electronic equipment | |
| CN117828360A (en) | Model training method, model training device, model code generating device, storage medium and storage medium | |
| CN116578877B (en) | Method and device for model training and risk identification of secondary optimization marking | |
| CN116185596B (en) | Method and device for improving task execution efficiency of wide-area multi-cluster distributed system | |
| CN116347623B (en) | Task scheduling method and device, storage medium and electronic equipment | |
| CN116091895B (en) | Model training method and device oriented to multitask knowledge fusion | |
| CN116996397B (en) | Network packet loss optimization method and device, storage medium and electronic equipment | |
| CN115543945B (en) | Model compression method and device, storage medium and electronic equipment | |
| CN116167431A (en) | Service processing method and device based on hybrid precision model acceleration | |
| CN116341642A (en) | Data processing method and device, storage medium and electronic equipment | |
| CN115017915B (en) | Model training and task execution method and device | |
| CN117348999B (en) | Service execution system and service execution method | |
| CN117201334B (en) | Multi-mode network traffic prediction method and device | |
| CN116484768B (en) | System dynamics model construction method and device | |
| CN116434787B (en) | Voice emotion recognition method and device, storage medium and electronic equipment | |
| CN116340004A (en) | Task execution method and device, storage medium and electronic equipment | |
| CN115862675B (en) | Emotion recognition method, device, equipment and storage medium | |
| CN115545938B (en) | Method, device, storage medium and equipment for executing risk identification service | |
| CN116501852B (en) | Controllable dialogue model training method and device, storage medium and electronic equipment | |
| CN117350351B (en) | Training method of user response prediction system, user response prediction method and device | |
| CN117194992B (en) | Model training and task execution method and device, storage medium and equipment | |
| CN117034926A (en) | Model training method and device for multi-field text classification model | |
| CN116822936A (en) | Business wind control method and device, storage medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |