CN110958066B - Gain network acquisition method and device, storage medium and computer equipment - Google Patents
Gain network acquisition method and device, storage medium and computer equipment Download PDFInfo
- Publication number
- CN110958066B CN110958066B CN201911126788.XA CN201911126788A CN110958066B CN 110958066 B CN110958066 B CN 110958066B CN 201911126788 A CN201911126788 A CN 201911126788A CN 110958066 B CN110958066 B CN 110958066B
- Authority
- CN
- China
- Prior art keywords
- gain
- signal
- noise ratio
- loop
- agent
- 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.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/30—Monitoring; Testing of propagation channels
- H04B17/309—Measuring or estimating channel quality parameters
- H04B17/336—Signal-to-interference ratio [SIR] or carrier-to-interference ratio [CIR]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/30—Monitoring; Testing of propagation channels
- H04B17/309—Measuring or estimating channel quality parameters
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/08—Testing, supervising or monitoring using real traffic
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
- H04W4/46—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P] for vehicle-to-vehicle communication [V2V]
Abstract
The application relates to a gain network acquisition method, a gain network acquisition device, a computer readable storage medium and a computer device, wherein the method comprises the following steps: acquiring agents in an agent network, and determining the signal-to-noise ratio gain rate between the agents; constructing a signal-to-noise ratio gain model of the intelligent agent network according to the intelligent agents and the signal-to-noise ratio gain rate between the intelligent agents; obtaining a gain loop in the signal-to-noise ratio gain model; and determining a gain network in the intelligent agent network according to the gain loop. In the scheme provided by the application, any intelligent agent can increase the signal-to-noise ratio of the output signal of the intelligent agent through the gain network, and the signal-to-noise ratio of the signal is enhanced without adding an additional device, so that the utilization rate of the existing intelligent agent network is improved, and the resources are effectively saved.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method and an apparatus for acquiring a gain network, a computer-readable storage medium, and a computer device.
Background
With the development of computer technology, the application scenarios of the multi-intelligence technology in reality are increasing, for example, in the application fields of vehicle networking, vehicle road collaboration, automatic vehicle formation, and the like. However, when the signal-to-noise ratio of the signal output by a single agent in the multi-agent system does not reach the signal requirement, an additional amplifier is often required to increase the signal-to-noise ratio of the signal, which results in resource waste.
Disclosure of Invention
Based on this, it is necessary to provide a method and an apparatus for acquiring a gain network, a computer readable storage medium, and a computer device for solving the technical problem of resource waste in a multi-intelligence system.
A gain network acquisition method comprises the following steps:
acquiring agents in an agent network, and determining the signal-to-noise ratio gain rate between the agents;
constructing a signal-to-noise ratio gain model of the intelligent agent network according to the intelligent agents and the signal-to-noise ratio gain rate between the intelligent agents;
obtaining a gain loop in the signal-to-noise ratio gain model;
and determining a gain network in the intelligent agent network according to the gain loop.
An apparatus for obtaining a gain network, the apparatus comprising:
the intelligent agent acquisition module is used for acquiring intelligent agents in an intelligent agent network and determining the signal-to-noise ratio gain rate between the intelligent agents;
a gain model obtaining module, configured to construct a signal-to-noise ratio gain model of the agent network according to the agents and signal-to-noise ratio gain rates between the agents;
the gain loop determining module is used for acquiring a gain loop in the signal-to-noise ratio gain model;
and the gain network determining module is used for determining a gain network in the intelligent agent network according to the gain loop.
A computer-readable storage medium storing a computer program which, when executed by a processor, causes the processor to perform the steps of:
acquiring agents in an agent network, and determining the signal-to-noise ratio gain rate between the agents;
constructing a signal-to-noise ratio gain model of the intelligent agent network according to the intelligent agents and the signal-to-noise ratio gain rate between the intelligent agents;
obtaining a gain loop in the signal-to-noise ratio gain model;
and determining a gain network in the intelligent agent network according to the gain loop.
A computer device comprising a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of:
acquiring agents in an agent network, and determining the signal-to-noise ratio gain rate between the agents;
constructing a signal-to-noise ratio gain model of the intelligent agent network according to the intelligent agents and the signal-to-noise ratio gain rate between the intelligent agents;
obtaining a gain loop in the signal-to-noise ratio gain model;
and determining a gain network in the intelligent agent network according to the gain loop.
The method and the device for obtaining the gain network, the computer storage medium and the computer equipment obtain the intelligent agents in the intelligent agent network, determine the signal-to-noise ratio gain rate among the intelligent agents, construct the signal-to-noise ratio gain model of the intelligent agent network according to the intelligent agents and the signal-to-noise ratio gain rate among the intelligent agents, obtain the gain loop in the signal-to-noise ratio gain model, and determine the gain network in the intelligent agent network according to the gain loop. The signal-to-noise ratio gain model of the intelligent agent network is constructed through the intelligent agents in the intelligent agent network and the signal-to-noise ratio gain rate between the intelligent agents, so that a gain loop is screened out from the signal-to-noise ratio gain model, the gain network in the intelligent agent network is formed according to the gain loop, any one intelligent agent can increase the signal-to-noise ratio of an output signal of the intelligent agent through the gain network, additional devices are not needed to be added to enhance the signal-to-noise ratio of the signal, the utilization rate of the existing intelligent agent network is improved, and resources are effectively saved.
Drawings
FIG. 1 is a diagram of an exemplary implementation of a gain network acquisition method;
FIG. 2 is a flow diagram illustrating a method for acquiring a gain network according to one embodiment;
FIG. 3 is a flowchart illustrating steps in one embodiment for constructing a signal-to-noise ratio gain model for a network of agents based on agent and agent-to-noise ratio gain ratios;
FIG. 4 is a diagram of a signal-to-noise ratio gain model in one embodiment;
FIG. 5 is a flowchart illustrating the steps of obtaining a gain loop in the SNR gain model according to one embodiment;
FIG. 6 is a schematic flow chart of a method for acquiring a gain network in another embodiment;
FIG. 7 is a schematic view of an embodiment of a network of vehicles;
FIG. 8 is a diagram illustrating a loop in a signal-to-noise ratio gain model in one embodiment;
FIG. 9 is a block diagram showing an acquisition apparatus of a gain network according to another embodiment;
FIG. 10 is a block diagram that illustrates the architecture of a computing device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
Fig. 1 is a diagram of an application environment of a method for acquiring a gain network according to an embodiment. Referring to fig. 1, the gain network acquisition method is applied to a computer device. The computer device may be a terminal or a server. As shown in fig. 1, taking the computer device as a server 102 as an example, the server 102 acquires agents in an agent network and determines a signal-to-noise ratio gain rate between the agents; constructing a signal-to-noise ratio gain model of the intelligent agent network according to the intelligent agents and the signal-to-noise ratio gain rate between the intelligent agents; obtaining a gain loop in the signal-to-noise ratio gain model; and determining a gain network in the intelligent agent network according to the gain loop. After obtaining the gain network in the network of the intelligent agents, the server 102 may determine a target gain rate according to a ratio of the target signal-to-noise ratio to the original signal-to-noise ratio when the original signal-to-noise ratio of the output signal of a certain subsequent intelligent agent does not meet the requirement of the target signal-to-noise ratio, so as to screen a gain loop that meets the target gain rate from the gain network according to the target gain rate, and transmit the output signal of the intelligent agent through the gain loop, thereby achieving improvement of the signal-to-noise ratio of the output signal, enabling the signal-to-noise ratio of the output signal to meet the requirement of the target signal-to-noise ratio, and improving communication quality.
In one embodiment, as shown in fig. 2, a method for obtaining a gain network is provided. The embodiment is mainly illustrated by applying the method to the server 120 in fig. 1. Referring to fig. 2, the method for acquiring the gain network specifically includes the following steps:
step S202, acquiring agents in the agent network, and determining the signal-to-noise ratio gain rate between the agents.
The intelligent agent refers to an entity capable of performing information interaction with an application environment in the application environment, and the intelligent agent network refers to a network formed by a plurality of intelligent agents. For example, in an application environment of internet of vehicles, the network of agents refers to the internet of vehicles, and the agents in the network of agents refer to each vehicle in the internet of vehicles.
The signal-to-noise ratio gain rate refers to the amplification factor of the signal-to-noise ratio of an input signal and the signal-to-noise ratio of an output signal, and the signal-to-noise ratio gain rate between different agents refers to the amplification factor of the signal-to-noise ratio of a signal in the transmission process of two different agents; for example, when a signal with a signal-to-noise ratio a output from agent a is used as an input signal to agent B, an output signal with a signal-to-noise ratio of 1.2a output from agent B is obtained, and at this time, the signal-to-noise ratio gain ratio from agent a to agent B is 1.2. It should be understood that in practical applications, the signal-to-noise gain between any two different agents is different.
And S204, constructing a signal-to-noise ratio gain model of the intelligent agent network according to the intelligent agents and the signal-to-noise ratio gain ratio between the intelligent agents.
The signal-to-noise ratio gain model is a model of a loop formed by all intelligent agents in any combination, and in the signal-to-noise ratio gain model, when the intelligent agents forming the loop and the sequence among the intelligent agents are determined, the signal-to-noise ratio gain of the loop can be determined.
Specifically, after the agents in the agent network and the snr gain ratios between the agents are obtained, the agents may be regarded as nodes, the snr gain ratios between the agents are regarded as connection weights between the nodes, and then the nodes are connected to generate a directed graph, and the obtained directed graph is an snr gain model. Specifically, each agent may be numbered, and after the numbered agents are obtained, an snr gain rate matrix may be determined according to the number of each agent, where the snr gain rate matrix is R ═ R [ i, j ═ f]) i×j ，R[i,j]Is used to represent the signal-to-noise gain ratio of the signal from agent i to agent j, i.e. the signal with signal-to-noise ratio a from agent i is used as the input of agent j to obtain the signal-to-noise ratio R [ i, j ] of agent j]a ofAnd outputting a signal, and converting the signal-to-noise ratio gain matrix into a directed graph after the signal-to-noise ratio gain matrix is obtained, wherein the obtained directed graph is a signal-to-noise ratio gain model.
Step S206, a gain loop in the signal-to-noise ratio gain model is obtained.
The gain loop is a loop in which the signal-to-noise ratio of an obtained signal is higher than that of an original signal after the original signal output by any agent is transmitted through the loop.
The server traverses loops in the signal-to-noise ratio gain model after acquiring the signal-to-noise ratio gain model, calculates the signal-to-noise ratio gain ratio of each loop after acquiring all loops of the signal-to-noise ratio gain model, and determines the loop as the gain loop when the signal-to-noise ratio gain ratio of the loop is greater than 1, namely the original signal is transmitted through the loop and the signal-to-noise ratio of the acquired signal is higher than that of the original signal.
Further, in one embodiment, the snr gain model can be represented using a directed graph, and the gain loop can be found in the directed graph corresponding to the snr gain model by Bellman-Ford algorithm (Bellman-Ford). Specifically, the directed graph (i.e., the snr arbitrage model) is relaxed n-1 times in a loop, where n is the total number of agents, and all edges in the directed graph need to be relaxed each time. After n-1 relaxations are finished, if the directed graph (signal-to-noise ratio arbitrage model) can also be relaxed, a gain loop exists in the directed graph. It should be understood that relaxed means finding an edge in the directed graph that can reduce the sum of the weights of all edges on the path from the starting node to the current node, then this edge is the edge with negative weight, which forms the gain loop by finding all edges with negative weight on the negative loop.
And step S208, determining a gain network in the intelligent agent network according to the gain loop.
After all gain loops in the signal-to-noise ratio model are obtained, the gain loops are determined to be gain networks in the intelligent agent network. And subsequently, when the original signal-to-noise ratio of the output signal of an intelligent agent does not meet the requirement of the target signal-to-noise ratio, determining the target gain rate according to the ratio of the target signal-to-noise ratio and the original signal-to-noise ratio, so that a gain loop loaded with the target gain rate is screened from the gain network according to the target gain rate, and the output signal of the intelligent agent is transmitted through the gain loop, so that the signal-to-noise ratio of the output signal is improved, and the signal-to-noise ratio of the output signal meets the requirement of the target signal-to-noise ratio.
The method for acquiring the gain network acquires the intelligent agents in the intelligent agent network, determines the signal-to-noise ratio gain rate among the intelligent agents, constructs a signal-to-noise ratio gain model of the intelligent agent network according to the intelligent agents and the signal-to-noise ratio gain rate among the intelligent agents, acquires the gain loop in the signal-to-noise ratio gain model, and determines the gain network in the intelligent agent network according to the gain loop. The signal-to-noise ratio gain model of the intelligent agent network is constructed through the intelligent agents in the intelligent agent network and the signal-to-noise ratio gain rate between the intelligent agents, so that a gain loop is screened out from the signal-to-noise ratio gain model, the gain network in the intelligent agent network is formed according to the gain loop, any one intelligent agent can increase the signal-to-noise ratio of an output signal of the intelligent agent through the gain network, additional devices are not needed to increase the signal-to-noise ratio of the signal, the utilization rate of the existing intelligent agent network is improved, and resources are effectively saved.
In one embodiment, as shown in FIG. 3, the step of constructing a signal-to-noise ratio gain model of the network of agents based on the agents and the signal-to-noise ratio gain ratio between the agents includes:
step S302, determining the agents in the agent network as agent nodes.
Wherein the gain signal-to-noise ratio model may be a directed graph; after the agents in the agent network and the signal-to-noise ratio gain rates between the agents are obtained, agent nodes can be correspondingly generated according to the agents in the agent network, and the agent nodes are nodes in a directed graph.
And step S304, determining the connection weight among the nodes of the intelligent agents according to the signal-to-noise ratio gain rate among the intelligent agents.
The connection weight may include a direction and a weight value, where the weight value in the connection weight is used to indicate an amplification factor of a signal-to-noise ratio of a signal in a transmission process between two different nodes, a signal-to-noise ratio gain rate between the agents may be selected, or a negative logarithm of the signal-to-noise ratio gain rate between the agents may be selected, and the direction of the connection weight refers to a direction between the agents and is used to indicate which agent the output signal of the agent is input to. Specifically, for example, the connection weight of the agent nodes is taken as the signal-to-noise ratio gain rate, and after the agent nodes are obtained, the connection weight between the agent nodes corresponding to the agents can be directly determined according to the signal-to-noise ratio gain rate between the agents.
And S306, constructing a directed graph according to the intelligent agent nodes and the connection weights among the intelligent agent nodes.
After obtaining the intelligent agent nodes and the connection weights among the intelligent agent nodes, determining each intelligent agent node as the vertex of the directed graph, and determining the path among the intelligent agent nodes in the directed graph according to the direction and the weight in the connection weights among the intelligent agent nodes so as to obtain the directed graph.
And step S308, determining a signal-to-noise ratio gain model of the intelligent agent network according to the directed graph.
The obtained directed graph, namely a signal-to-noise ratio gain model corresponding to the intelligent agent network, is obtained from the signal-to-noise ratio gain model. In one embodiment, as shown in FIG. 4, FIG. 4 is a schematic diagram of a signal-to-noise ratio gain model in one embodiment. In the figure, the signal-to-noise ratio model comprises n intelligent agent nodes, the connection weight between the energy-saving agents can be directly valued as the signal-to-noise ratio gain rate R [ i, j ], and the R [ i, j ] is used for representing the signal-to-noise ratio gain rate of the signals from the intelligent agent i to the intelligent agent j. Specifically, because the connecting lines between the nodes in the directed graph are directional, the signal flow directions between any two agents are different, and the snr gain ratios between the two agents may be the same or different. Taking agent 1 and agent 2 in fig. 4 as an example, assuming that a signal with a signal-to-noise ratio output by agent 1 is used as first original information, after the first original signal is input into agent 2, the signal-to-noise ratio of the signal output by agent 2 is (R1, 2) × a, that is, the signal-to-noise ratio gain of the signals from agent 1 to agent 2 is R1, 2; the signal with signal-to-noise ratio a output by agent 2 is used as second original information, and after the second original signal is input into agent 1, the signal-to-noise ratio of the signal output by agent 1 is (R2, 1) x a, i.e. the signal-to-noise ratio gain of the signal from agent B to agent A is R2, 1, in which R1, 2 is not necessarily equal to R2, 1.
In one embodiment, as shown in fig. 5, the step of obtaining the gain loop in the signal-to-noise ratio gain model includes:
step S502, randomly determining a starting agent from the agent network.
Step S504, the intelligent agent node corresponding to the initial intelligent agent is taken as an initial node, and a loop taking the initial node as a starting point in the digraph is traversed.
After the signal-to-noise ratio gain model is obtained and the initial intelligent agent is randomly determined from the intelligent agent network, the intelligent agent node corresponding to the initial intelligent agent is determined as the initial node from the directed graph of the signal-to-noise ratio gain model, and therefore all loops taking the initial node as the starting point in the directed graph are traversed.
Specifically, as in the schematic diagram of the snr gain model shown in fig. 4, assuming that the starting agent is selected as agent 1, a loop in the directed graph corresponding to the snr gain model and starting from the agent node corresponding to agent 1 is traversed, such as loop "agent 1- > agent 2- > agent 1", loop "agent 1- > agent 3- > agent 1", loop "agent 1- > agent 2- > … … agent n- > agent 1", and so on.
Step S506, calculating the signal-to-noise ratio gain rate of each loop according to the connection weight between the intelligent agent nodes in each loop.
After obtaining loops which take the initial node as a starting point in the signal-to-noise ratio model, for each loop, calculating the signal-to-noise ratio gain of the loop according to the connection line weight of the nodes of the intelligent body in the loop; specifically, the flow direction of the signal between each intelligent agent node in the loop may be determined according to the sequence of the intelligent agents in the loop, and then the signal-to-noise ratio gain of each loop may be calculated according to the connection weight of each intelligent agent node.
For example, as shown in the schematic diagram of the snr gain model shown in fig. 4, where the connection weight between the agents takes the snr gain ratio between the agents, for the loop "agent 1- > agent 2- > agent 3- > agent 1", the order of the agents in the loop is: agent 1, agent 2, agent 3, agent 1, wherein the flow direction of signal between the agent node is: the output signal of agent 1 is input into agent 2, the output signal of agent 2 is input into agent 3, and the output signal of agent 3 is input into agent 1, therefore, the connection weight is determined one by one according to the flow direction of the signal between agent nodes: r1, 2, R2, 3, R3, 1, after obtaining the weight of the connection line, the obtained weight of the connection line is multiplied, and the signal-to-noise ratio gain of the loop is obtained.
Step S508, when the signal-to-noise ratio gain ratio of the loop is within the preset threshold range, determining the loop as a gain loop.
The preset threshold range is set according to actual conditions, for example, when the connection weight value of the directed graph is the signal-to-noise ratio gain rate between the intelligent agents, the preset threshold range is set to be a value range larger than 1; and when the connection line weight value of the directed graph is the negative logarithm of the signal-to-noise ratio gain rate between the intelligent agents, setting the preset threshold value range to be a value range smaller than 0.
For example, as shown in the schematic diagram of the snr gain model shown in fig. 4, where the connection weight between the agents is taken as the snr gain ratio between the agents, and for the loop "agent 1- > agent 2- > agent 3- > agent 1", when the value obtained by multiplying R [1,2], R [2,3] and R [3,1] is greater than 1, the snr of the signal obtained by the loop transmission of the original signal output from the agent 1 is greater than the snr of the original signal, and the loop is determined as the gain loop.
In one embodiment, the step of determining the connection weights between agent nodes based on the snr gain ratio between agents comprises: calculating the negative logarithm of the signal-to-noise ratio gain rate among the intelligent agents to obtain the connection weight among the nodes of the intelligent agents; the step of calculating the signal-to-noise ratio gain ratio of each loop according to the weight of the connecting line between each agent node in each loop comprises the following steps: determining the sequence of each agent node in the loop; determining target connection weights in the loop according to the sequence of each agent node; and calculating the sum of the negative logarithms corresponding to the target connecting line weight in the loop to obtain the signal-to-noise ratio gain rate of the loop.
Wherein, the weight of the connection line between the nodes of the agents can select the negative logarithm of the gain ratio of the signal to noise ratio between the corresponding agents. After the line weight among the intelligent agent nodes is determined as the negative logarithm of the signal-to-noise ratio gain rate among the intelligent agents, for each loop, the flow direction of signals among all the intelligent agent nodes in the loop can be determined according to the sequence of the intelligent agents in the loop, then the corresponding target line weight in the directed graph is determined according to the flow direction among all the intelligent agent nodes, finally, the negative logarithms of the signal-to-noise ratio gain rate corresponding to the target line weight are accumulated, the sum of the target line weight is calculated, and the loop signal-to-noise ratio gain is obtained. By selecting the negative logarithm of the signal-to-noise ratio gain rate between corresponding intelligent agents as the connection weight between intelligent agent nodes, the cumulative operation of the signal-to-noise ratio gain rate is converted into the cumulative operation of the negative logarithm of the signal-to-noise ratio gain rate, a signal-to-noise ratio gain model constructed by a directed graph is utilized, in addition, the process of searching for a gain network is converted into the process of searching for a negative loop from the directed graph corresponding to the signal-to-noise ratio gain model, and the difficulty and the calculated amount of obtaining the gain network are reduced.
Specifically, as shown in the schematic diagram of the snr gain model shown in fig. 4, the snr gain model includes n agent nodes, and the connection weight between the energy-saving agents can be directly set to an snr gain rate w (i, j) ═ lnR [ i, j ], where R [ i, j ] is used to represent the snr gain rates of signals from agent i to agent j. Assuming that the starting agent is selected to be agent 1, "agent 1- > agent 2- > agent 3- > agent 1", a loop of agents in which the order of agents is: agent 1, agent 2, agent 3, agent 1, wherein the flow direction of signal between the agent node is: the output signal of agent 1 is input into agent 2, the output signal of agent 2 is input into agent 3, and the output signal of agent 3 is input into agent 1, therefore, the connection weight is determined one by one according to the flow direction of the signal between agent nodes: -lnR 1,2, -lnR 2,3, -lnR 3,4, after obtaining the connection weight, accumulating the obtained connection weight to obtain the signal-to-noise ratio gain of the loop. When the values obtained by multiplying-lnR 1,2, -lnR 2,3 and-lnR 3,4 are smaller than 1, that is, the signal-to-noise ratio of the signal obtained by the original signal output from the agent 1 after being transmitted through the loop is larger than the signal-to-noise ratio of the original signal, the loop is determined as a gain loop.
In one embodiment, as shown in fig. 6, the method for acquiring the gain network includes:
step S602, acquiring agents in an agent network, and determining the signal-to-noise ratio gain rate between the agents;
step S604, determining the agents in the agent network as agent nodes;
step S606, calculating the negative logarithm of the signal-to-noise ratio gain rate among the agents to obtain the connection weight among the nodes of the agents;
step S608, constructing a directed graph according to the intelligent agent nodes and the connection weights among the intelligent agent nodes;
and step S610, determining a signal-to-noise ratio gain model of the intelligent agent network according to the directed graph.
Step S612, randomly determining a starting agent from the agent network;
step S614, taking the intelligent agent node corresponding to the initial intelligent agent as an initial node, and traversing a loop taking the initial node as a starting point in the digraph;
step S616, determining the loop direction of the loop and the sequence of each agent;
step 618, determining the target connection weight in the loop according to the direction of the loop and the sequence of each agent;
step S620, calculating the sum of the negative logarithms corresponding to the target connecting line weight in the loop to obtain the signal-to-noise ratio gain rate of the loop;
in step S622, when the snr gain of the loop is within the preset threshold range, the loop is determined as a gain loop.
And step S624, determining a gain network in the intelligent agent network according to the gain loop.
Specifically, the embodiment is further described by taking an example in which the intelligent agent network is a vehicle networking network and the intelligent agent is a vehicle in the vehicle networking network. As shown in fig. 7, fig. 7 is a schematic view of a car networking in one embodiment. The vehicle-mounted system of each vehicle is programmed with a signal-to-noise ratio detection module and a signal receiving module, the signal-to-noise ratio detection module is used for detecting the signal-to-noise ratio and the signal-to-noise ratio gain rate of received signals, and the signal receiving module is used for communication among vehicles. Specifically, the server obtains the internet of vehicles, and obtains the signal-to-noise ratio between vehicles in the internet of vehicles, taking fig. 7 as an example, assuming that the gain ratio of the signal-to-noise ratio between any two vehicles is 1.2, that is, a signal with a signal-to-noise ratio a is output by any one vehicle as an input of vehicle 1, and the signal-to-noise ratio of an output signal of vehicle 1 is 1.2 a.
After the signal-to-noise ratio gain rates of all vehicles and among all vehicles in the internet of vehicles are obtained, all vehicles are used as vertexes of the directed graph, the directed edge weight values among the corresponding vertexes are determined according to the negative logarithm of the signal-to-noise ratio gain rates of all vehicles, the connection line weights of the corresponding vertexes are obtained, then the directed graph is constructed according to all vertexes and the connection line weights among the vertexes, and the signal-to-noise ratio gain model corresponding to the internet of vehicles is obtained. After the signal-to-noise ratio gain model of the internet of vehicles is obtained, the server randomly selects any vehicle as a starting vehicle, and traverses a loop in which a vertex corresponding to the starting vehicle is taken as a starting point in a directed graph corresponding to the signal-to-noise ratio gain model. And for each loop, calculating the signal-to-noise ratio gain rate of the loop through the sequence of each vertex in the loop and the weight of a connecting line between each vertex, wherein when the signal-to-noise ratio gain rate of the loop is less than 1, the loop is a negative loop in a signal-to-noise ratio gain model, namely a gain network.
For example, as shown in fig. 8, fig. 8 is a schematic diagram of a loop in the snr gain model in an embodiment, where the link weight between vehicles can be directly taken as an snr gain rate w (i, j) ═ lnR [ i, j ], where R [ i, j ] is used to represent the snr gain rate of the signal from vehicle i to vehicle j. Assuming that the starting vehicle is selected as vehicle 1, "vehicle 1- > vehicle 2- > vehicle 4- > vehicle 6- > vehicle 5- > vehicle 3- > vehicle 1" in a loop, the order of the vehicles in the loop is: vehicle 1, vehicle 2, vehicle 4, vehicle 6, vehicle 5, vehicle 3, vehicle 1, wherein the flow direction of the signal between the corresponding vertices of the vehicle is: an output signal of the vehicle 1 is input into the vehicle 2, an output signal of the vehicle 2 is input into the vehicle 4, an output signal of the vehicle 4 is input into the vehicle 6, an output signal of the vehicle 6 is input into the vehicle 5, an output signal of the vehicle 5 is input into the vehicle 3, and an output signal of the vehicle 3 is input into the vehicle 1. Therefore, the link weights are determined one by one according to the flow direction of the signals between the corresponding vertexes of the vehicle: -ln R1, 2, -ln R2, 4, -ln R4, 6, -ln R6, 5, -ln R5, 3, -ln R3, 1, after obtaining connection weight, accumulating the obtained connection weight to obtain the signal-to-noise ratio gain of the loop. When the value obtained by multiplying-ln R1, 2, -ln R2, 4, -ln R4, 6, -ln R6, 5, -ln R5, 3 and-ln R3, 1 is less than 1, that is, the signal-to-noise ratio of the signal obtained by the loop transmission of the original signal output from the agent 1 is greater than the signal-to-noise ratio of the original signal, the loop is determined as a gain loop.
The method comprises the steps of traversing all loops in a signal-to-noise ratio gain model by carrying out the same calculation operation on any loop taking any vehicle as an initial vehicle in the signal-to-noise ratio gain model corresponding to the Internet of vehicles to obtain the signal-to-noise ratio gain rate corresponding to each loop, further obtaining all gain loops in the signal-to-noise ratio gain model, and finally forming a gain network through the gain loops.
In one embodiment, after the step of determining the gain network in the intelligent agent network according to the gain loop, the method further comprises: determining a target agent in an agent network; determining a target signal-to-noise ratio gain rate according to the signal-to-noise ratio of the original signal of the target intelligent agent and the signal-to-noise ratio of the target signal; determining a target gain loop from a gain network according to the target signal-to-noise ratio gain rate; the original signal of the target agent is transmitted through the target gain loop.
The target agent refers to an agent in an agent network, and the target signal-to-noise ratio refers to the signal-to-noise ratio requirement required by the subsequent service. It should be appreciated that the signal-to-noise ratio of the original signal of the target agent does not reach the signal-to-noise ratio required for subsequent transmission traffic or computation traffic.
After the gain network is obtained, when the signal-to-noise ratio of the original signal of the target agent does not meet the requirement of the target signal-to-noise ratio, the target gain rate can be determined according to the ratio of the signal-to-noise ratio of the original signal to the target signal-to-noise ratio, then a gain loop with the gain rate meeting the target gain rate is screened out from the gain network according to the target gain rate, and finally the original signal of the target agent is transmitted through the gain loop, so that the signal-to-noise ratio of the original signal is improved, the signal-to-noise ratio of the original signal meets the requirement of the target signal-to-noise ratio, an additional amplifier device is not needed, the utilization rate of the existing agent network is improved, and resources are effectively saved.
It should be understood that, although the steps in the above-described flowcharts are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of the steps in the above-described flowcharts may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or the stages is not necessarily sequential, but may be performed alternately or alternatingly with other steps or at least a portion of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 9, there is provided an obtaining apparatus 900 for a gain network, the apparatus comprising: agent acquisition module 902, gain model acquisition module 904, gain loop determination module 906, and gain network determination module 908, wherein:
an agent obtaining module 902, configured to obtain agents in an agent network and determine a signal-to-noise ratio gain ratio between the agents;
a gain model obtaining module 904, configured to construct a signal-to-noise ratio gain model of the agent network according to the agents and the signal-to-noise ratio gain ratio between the agents;
a gain loop determination module 906, configured to obtain a gain loop in the signal-to-noise ratio gain model;
and a gain network determining module 908 for determining a gain network in the agent network according to the gain loop.
In one embodiment, the gain model acquisition module includes:
an agent node acquisition unit, configured to determine an agent in an agent network as an agent node;
the connection weight acquisition unit is used for determining the connection weight among the nodes of the intelligent agents according to the signal-to-noise ratio gain rate among the intelligent agents;
the directed graph constructing unit is used for constructing a directed graph according to the intelligent agent nodes and the connection weights among the intelligent agent nodes;
and the gain model acquisition unit is used for determining a signal-to-noise ratio gain model of the intelligent network according to the directed graph.
In one embodiment, the gain loop determination module includes:
an originating agent determining unit for randomly determining an originating agent from the agent network;
a loop determining unit, configured to take an agent node corresponding to an agent as an initial node, and traverse a loop in the digraph with the initial node as a starting point;
the gain ratio calculation unit is used for calculating the signal-to-noise ratio gain ratio of each loop according to the connection weight among the intelligent agent nodes in each loop;
and the gain loop determining unit is used for determining the loop as the gain loop when the signal-to-noise ratio gain rate of the loop is within the range of the preset threshold value.
In one embodiment, the connection weight obtaining unit is configured to calculate a negative logarithm of a signal-to-noise ratio gain ratio between the agents to obtain a connection weight between nodes of the agents; a gain ratio calculation unit for determining the loop direction of the loop and the order of the agents; determining target connection weights in the loop according to the direction of the loop and the sequence of each agent; and calculating the sum of the negative logarithms corresponding to the target connecting line weight in the loop to obtain the signal-to-noise ratio gain rate of the loop.
In one embodiment, the apparatus for obtaining a gain network further comprises a gain network determining module, configured to determine a target agent in the network of agents; determining a target signal-to-noise ratio gain rate according to the signal-to-noise ratio of the original signal of the target intelligent agent and the signal-to-noise ratio of the target signal; determining a target gain loop from the gain network according to the target signal-to-noise ratio gain rate; the original signal of the target agent is transmitted through the target gain loop.
FIG. 10 is a diagram that illustrates an internal structure of the computer device in one embodiment. The computer device may specifically be the server 120 in fig. 1. As shown in fig. 10, the computer apparatus includes a processor, a memory, a network interface, an input device, and a display screen connected through a system bus. Wherein the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program that, when executed by the processor, causes the processor to implement the method of acquiring the gain network. The internal memory may also have a computer program stored therein, which, when executed by the processor, causes the processor to perform the method for acquiring the gain network. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 10 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, the gain network obtaining apparatus provided in the present application may be implemented in a form of a computer program, and the computer program may be run on a computer device as shown in fig. 10. The memory of the computer device may store therein the various program modules that make up the acquisition means of the gain network, such as agent acquisition module 902, gain model acquisition module 904, gain loop determination module 906, and gain network determination module 908 shown in fig. 9. The computer program constituted by the respective program modules causes the processor to execute the steps in the acquisition method of the gain network of the respective embodiments of the present application described in the present specification.
For example, the computer device shown in fig. 10 may execute step 202 through the agent obtaining module 902 in the obtaining means of the gain network shown in fig. 9. The computer device may perform step 204 by gain model acquisition module 904. The computer device may perform step 206 by the gain loop determination module 906. The computer device may perform step 208 by gain network determination module 908.
In an embodiment, a computer device is provided, comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of the above gain network acquisition method. Here, the steps of the gain network acquisition method may be steps in the gain network acquisition methods of the above embodiments.
In one embodiment, a computer-readable storage medium is provided, in which a computer program is stored, which, when being executed by a processor, causes the processor to carry out the steps of the above-mentioned gain network acquisition method. Here, the steps of the gain network acquisition method may be steps in the gain network acquisition methods of the above embodiments.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by a computer program, which may be stored in a non-volatile computer readable storage medium, and when executed, may include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (12)
1. A gain network acquisition method comprises the following steps:
acquiring agents in an agent network, and determining the signal-to-noise ratio gain rate between the agents;
constructing a signal-to-noise ratio gain model of the agent network according to the agents and the signal-to-noise ratio gain ratio between the agents;
obtaining a gain loop in the signal-to-noise ratio gain model;
determining a gain network in the agent network according to the gain loop;
the step of constructing a signal-to-noise ratio gain model of the agent network according to the agents and the signal-to-noise ratio gain ratio between the agents comprises:
determining agents in the agent network as agent nodes;
determining the connection weight among the intelligent agent nodes according to the signal-to-noise ratio gain rate among the intelligent agents;
constructing a directed graph according to the intelligent agent nodes and the connection weights among the intelligent agent nodes;
determining a signal-to-noise ratio gain model of the intelligent agent network according to the directed graph;
the step of obtaining the gain loop in the signal-to-noise ratio gain model includes:
randomly determining a starting agent from the agent network;
taking an agent node corresponding to the starting agent as a starting node, and traversing a loop taking the starting node as a starting point in the directed graph;
calculating the signal-to-noise ratio gain rate of each loop according to the connection weight between the intelligent agent nodes in each loop;
and when the signal-to-noise ratio gain rate of the loop is within a preset threshold range, determining the loop as a gain loop.
2. The method of claim 1, wherein said step of constructing a signal-to-noise ratio gain model of said network of agents based on said agents and their signal-to-noise ratio gain ratios further comprises:
numbering the intelligent agent to obtain the number of the intelligent agent;
determining a signal-to-noise ratio gain rate matrix according to the number of the agents and the signal-to-noise ratio gain rate between the agents;
and converting the signal-to-noise ratio gain rate matrix into a directed graph, and determining the directed graph as a signal-to-noise ratio gain model of the intelligent agent network.
3. The method of claim 1, wherein the step of obtaining the gain loop in the snr gain model further comprises:
traversing loops in the signal-to-noise ratio gain model to obtain all loops in the signal-to-noise ratio gain model;
calculating the signal-to-noise ratio gain rate of each loop;
and when the signal-to-noise ratio gain ratio of the loop is greater than 1, determining the loop as a gain loop in the signal-to-noise ratio gain model.
4. The method of claim 1, wherein said step of determining a link weight between nodes of said agents based on a signal-to-noise ratio gain ratio between said agents comprises:
calculating the negative logarithm of the signal-to-noise ratio gain ratio between the intelligent agents to obtain the connection weight between the nodes of the intelligent agents;
the step of calculating the signal-to-noise ratio gain rate of each loop according to the connection weight between the agent nodes in each loop comprises:
determining an order of each of the agent nodes in the loop;
determining a target link weight in the loop according to the sequence of each agent node;
and calculating the sum of the negative logarithms corresponding to the target connecting line weight in the loop to obtain the signal-to-noise ratio gain rate of the loop.
5. The method of claim 1, wherein the step of determining a gain network in the intelligent agent network based on the gain loop is followed by:
determining a target agent in the agent network;
determining a target signal-to-noise ratio gain rate according to the signal-to-noise ratio of the original signal of the target agent and the signal-to-noise ratio of the target signal;
determining a target gain loop from the gain network according to the target signal-to-noise ratio gain rate;
transmitting the original signal of the target agent through the target gain loop.
6. An apparatus for obtaining a gain network, the apparatus comprising:
the intelligent agent acquisition module is used for acquiring intelligent agents in an intelligent agent network and determining the signal-to-noise ratio gain rate between the intelligent agents;
the gain model acquisition module is used for constructing a signal-to-noise ratio gain model of the intelligent agent network according to the intelligent agents and the signal-to-noise ratio gain rate between the intelligent agents;
the gain loop determining module is used for acquiring a gain loop in the signal-to-noise ratio gain model;
a gain network determination module for determining a gain network in the intelligent agent network according to the gain loop;
the gain model obtaining module comprises:
an agent node acquisition unit for determining agents in an agent network as agent nodes;
the connection weight acquisition unit is used for determining the connection weight among the nodes of the intelligent agents according to the signal-to-noise ratio gain rate among the intelligent agents;
the directed graph constructing unit is used for constructing a directed graph according to the intelligent agent nodes and the connection weights among the intelligent agent nodes;
the gain model acquisition unit is used for determining a signal-to-noise ratio gain model of the intelligent agent network according to the directed graph;
the gain loop determination module comprises:
an originating agent determining unit for randomly determining an originating agent from the agent network;
a loop determining unit, configured to take an agent node corresponding to an agent as an initial node, and traverse a loop in the digraph with the initial node as a starting point;
the gain ratio calculation unit is used for calculating the signal-to-noise ratio gain ratio of each loop according to the connection weight among the intelligent agent nodes in each loop;
and the gain loop determining unit is used for determining the loop as the gain loop when the signal-to-noise ratio gain rate of the loop is within the range of the preset threshold value.
7. The apparatus of claim 6, wherein the gain model obtaining module is further configured to number the agent to obtain a number of the agent; determining a signal-to-noise ratio gain rate matrix according to the number of the agents and the signal-to-noise ratio gain rate between the agents; and converting the signal-to-noise ratio gain rate matrix into a directed graph, and determining the directed graph as a signal-to-noise ratio gain model of the intelligent agent network.
8. The apparatus of claim 6, wherein the gain loop determining module is further configured to traverse loops in the snr gain model to obtain all loops in the snr gain model; calculating the signal-to-noise ratio gain rate of each loop; and when the signal-to-noise ratio gain ratio of the loop is greater than 1, determining the loop as a gain loop in the signal-to-noise ratio gain model.
9. The apparatus of claim 6, wherein the connection weight obtaining unit is further configured to calculate a negative logarithm of the snr gain ratio between the agents to obtain the connection weight between the agent nodes;
the gain ratio calculation unit is further configured to determine an order of each of the agent nodes in the loop; determining a target link weight in the loop according to the sequence of each agent node; and calculating the sum of the negative logarithms corresponding to the target connecting line weight in the loop to obtain the signal-to-noise ratio gain rate of the loop.
10. The apparatus of claim 6, wherein the apparatus is further configured to determine a target agent in the network of agents; determining a target signal-to-noise ratio gain rate according to the signal-to-noise ratio of the target agent original signal and the signal-to-noise ratio of a target signal; determining a target gain loop from the gain network according to the target signal-to-noise ratio gain rate; transmitting the original signal of the target agent through the target gain loop.
11. A computer-readable storage medium, storing a computer program which, when executed by a processor, causes the processor to carry out the steps of the method according to any one of claims 1 to 5.
12. A computer device comprising a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of the method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911126788.XA CN110958066B (en) | 2019-11-18 | 2019-11-18 | Gain network acquisition method and device, storage medium and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911126788.XA CN110958066B (en) | 2019-11-18 | 2019-11-18 | Gain network acquisition method and device, storage medium and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110958066A CN110958066A (en) | 2020-04-03 |
| CN110958066B true CN110958066B (en) | 2022-09-09 |
Family
ID=69977600
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911126788.XA Active CN110958066B (en) | 2019-11-18 | 2019-11-18 | Gain network acquisition method and device, storage medium and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110958066B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113192330B (en) * | 2021-04-26 | 2022-05-31 | 上海德衡数据科技有限公司 | Multi-agent-based vehicle management method, management system, device and medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103347290A (en) * | 2013-06-20 | 2013-10-09 | 重庆邮电大学 | Method for selecting relay of vehicular ad-hoc network based on game theory |
| CN106788708A (en) * | 2016-12-22 | 2017-05-31 | 云南电网有限责任公司 | The OSNR computational methods of OTN networks |
| CN108401492A (en) * | 2017-09-28 | 2018-08-14 | 深圳前海达闼云端智能科技有限公司 | A kind of route selection method, device and server based on mixing resource |
| CN109328439A (en) * | 2016-11-28 | 2019-02-12 | 华为技术有限公司 | Base station, transmitter communication equipment and the relay communications equipment communicated for honeycomb and D2D |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2706708B1 (en) * | 2011-05-24 | 2015-09-16 | Huawei Technologies Co., Ltd. | Method and apparatus for path selection |
| WO2017132629A1 (en) * | 2016-01-27 | 2017-08-03 | Ping Liang | Cellular wireless communication systems enhanced by intelligent self-organizing wireless distributed active antennas |
-
2019
- 2019-11-18 CN CN201911126788.XA patent/CN110958066B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103347290A (en) * | 2013-06-20 | 2013-10-09 | 重庆邮电大学 | Method for selecting relay of vehicular ad-hoc network based on game theory |
| CN109328439A (en) * | 2016-11-28 | 2019-02-12 | 华为技术有限公司 | Base station, transmitter communication equipment and the relay communications equipment communicated for honeycomb and D2D |
| CN106788708A (en) * | 2016-12-22 | 2017-05-31 | 云南电网有限责任公司 | The OSNR computational methods of OTN networks |
| CN108401492A (en) * | 2017-09-28 | 2018-08-14 | 深圳前海达闼云端智能科技有限公司 | A kind of route selection method, device and server based on mixing resource |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110958066A (en) | 2020-04-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108133619B (en) | Parking lot parking prediction method and device, storage medium and terminal equipment | |
| Liu et al. | LSOT: A lightweight self-organized trust model in VANETs | |
| DE102012213799A1 (en) | Method and system for transmitting information in wireless vehicle networks | |
| Kasana et al. | Location error resilient geographical routing for vehicular ad‐hoc networks | |
| CN112929845B (en) | Vehicle networking node trust evaluation method and system based on block chain | |
| CN110446204B (en) | Trust value calculation method suitable for Internet of vehicles network vehicle node | |
| CN108491971B (en) | Optimal path planning method of three-dimensional map based on travel plan | |
| CN113687875B (en) | Method and device for unloading vehicle tasks in Internet of vehicles | |
| CN110958066B (en) | Gain network acquisition method and device, storage medium and computer equipment | |
| Zhang et al. | Latency prediction for delay-sensitive v2x applications in mobile cloud/edge computing systems | |
| CN110753332A (en) | Data processing method and device based on Bluetooth SIG MESH and terminal to be unlocked | |
| Nguyen et al. | Impact of communication erasure channels on control performance of connected and automated vehicles | |
| CN114579683A (en) | Map network updating method and device, computer equipment and storage medium | |
| CN112035490B (en) | Electric vehicle information monitoring method, device and system based on cloud platform | |
| CN108877210B (en) | Real-time road condition data production method and vehicle-mounted terminal | |
| CN111586160B (en) | Data processing method, device, data processing equipment and storage medium | |
| CN114548572A (en) | Method, device, equipment and medium for predicting urban road network traffic state | |
| CN113543065A (en) | Communication resource allocation method based on reinforcement learning and related equipment thereof | |
| CN110621005B (en) | Vehicle networking privacy protection method based on crowdsourcing application | |
| CN110427816B (en) | Object detection method, device, computer equipment and storage medium | |
| CN114154930A (en) | Method and device for determining logistics distribution network, terminal equipment and storage medium | |
| RU2685030C2 (en) | Method of estimating efficiency of data exchange of communication system | |
| Nikolov et al. | MABASR—A Robust Wireless Interface Selection Policy for Heterogeneous Vehicular Networks | |
| CN114912759A (en) | Vehicle interaction data processing method and device, computer equipment and storage medium | |
| CN110619403A (en) | Car pooling method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40022006 Country of ref document: HK |
|
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |