Relay Selection Method and Device, and Electronic Device in Internet of Vehicles

Abstract

The present invention discloses a relay selection method, device and electronic device in a vehicle networking, which relates to the field of Internet of Things. The method includes: determining a selection range radius based on the position information of two vehicles to be networked, where the two vehicles to be networked include a communication sending vehicle and a communication receiving vehicle; obtaining all candidate relay nodes within the communication range indicated by the selection range radius to obtain a candidate relay set; calculating the social relationship strength between the communication sending vehicle and each candidate relay node to obtain a filtered candidate relay set; and selecting the candidate relay node with the lowest communication interruption probability in the filtered candidate relay set as the target relay node, so as to solve the technical problem in the related art that when the communication distance between communication objects exceeds the allowed maximum range, a suitable relay node cannot be selected, resulting in poor communication quality.

Description

Technical Field

[0001] The present invention relates to the field of Internet of Things, and in particular, to a relay selection method and device in vehicle-to-everything (V2X) and an electronic device. Background Art

[0002] Currently, with the development and popularization of 5G mobile communication technology, vehicle-to-everything (V2X) has developed accordingly. V2X belongs to a type of Internet of Things. Briefly speaking, in V2X, there is a local area network in the vehicle, vehicle-to-vehicle communication forms a vehicular network, and the vehicular network is connected to the Internet. Based on a unified protocol, data intercommunication among people, vehicles, roads, and clouds is realized, and finally functions such as intelligent transportation, intelligent vehicles, and intelligent driving are achieved.

[0003] The development of V2X plays a significant role in alleviating traffic congestion, improving traffic safety, and realizing intelligent transportation. However, with the continuous increase in vehicle nodes, vehicles have high requirements for the latency and quality of the communication network. In a complex road environment, the communication links in V2X are unstable. At the same time, due to the mobility of vehicles, the network topology structure changes dynamically greatly, which are all problems that need to be urgently solved in the current development of V2X.

[0004] Device-to-Device (D2D) technology has been applied to vehicle communication due to its advantages of low latency and high capacity. In related technologies, when D2D communication user pairs exceed the maximum range allowed for D2D communication, if they want to continue D2D communication, they need data forwarding by relay nodes to assist communication. And how to reasonably select relay nodes is the key to whether D2D communication can proceed normally and the quality of communication. In the prior art, vehicle D2D communication performs data transmission by multiplexing cellular network resources within a unit cell. However, this method not only has limitations on the communication range but also is not applicable to high-speed moving object targets. That is, in related technologies, when the communication distance between communication objects exceeds the allowed maximum range, a suitable relay node cannot be selected, resulting in poor communication quality. How to reduce the impact of vehicle mobility on D2D communication through a reasonable resource allocation algorithm, optimize D2D communication according to the characteristics of the vehicle environment, improve the D2D communication rate of vehicles, and ensure the quality of communication services.

[0005] Regarding the above problems, no effective solution has been proposed yet. Summary of the Invention

[0006] Embodiments of the present invention provide a relay selection method and device in vehicle-to-everything (V2X) and an electronic device, so as to at least solve the technical problem in related technologies that when the communication distance between communication objects exceeds the allowed maximum range, a suitable relay node cannot be selected, resulting in poor communication quality.

[0007] According to one aspect of the embodiments of the present invention, a relay selection method in a vehicle networking is provided, including: determining a selection range radius based on the position information of two vehicles to be networked, where the two vehicles to be networked include a communication sending vehicle and a communication receiving vehicle; obtaining all candidate relay nodes within the communication range indicated by the selection range radius to obtain a candidate relay set; calculating the social relationship strength between the communication sending vehicle and each candidate relay node, where the social relationship strength is used to screen the candidate relay nodes to obtain a filtered candidate relay set; selecting the candidate relay node with the minimum communication interruption probability in the filtered candidate relay set as the target relay node, where the target relay node serves as a relay networking node for direct node-to-node communication between the communication sending vehicle and the communication receiving vehicle.

[0008] Optionally, the step of determining a selection range radius based on the position information of two vehicles to be networked includes: combining the two vehicles to be networked into a communication vehicle pair; obtaining the positioning coordinates of each vehicle in the communication vehicle pair to obtain the position information; determining the direct connection distance between the communication vehicle pair based on the position information; selecting the midpoint position of the direct connection distance; and determining the selection range radius with any vehicle in the communication vehicle pair as the starting point and the midpoint position as the ending point.

[0009] Optionally, the step of calculating the social relationship strength between the communication sending vehicle and each candidate relay node includes: constructing an interest evaluation model, where the training input data of the interest evaluation model is: the identifiers of user i and user j in any user pair, a set of things, and the training output data of the interest evaluation model is: the interest parameters of user i and user j for each thing; obtaining the user information of the first vehicle user corresponding to the communication sending vehicle and the user information of the second vehicle user corresponding to each candidate relay node; evaluating the interest parameters of the first vehicle user for N things using the interest evaluation model based on the user information of the first vehicle user, and evaluating the interest parameters of the second vehicle user for the N things using the interest evaluation model based on the user information of the second vehicle user, where N is a positive integer greater than or equal to 1; comprehensively considering the interest parameters of the first vehicle user for N things and the interest parameters of the second vehicle user for N things to calculate the interest similarity between the communication sending vehicle and each candidate relay node; and determining the social relationship strength between the communication sending vehicle and each candidate relay node based on the interest similarity.

[0010] Optionally, after calculating the social relationship strength between the communication sending vehicle and each of the candidate relay nodes, the method further includes: obtaining a social evaluation threshold within a specified time period; retaining the candidate relay node corresponding to the social relationship strength when the social relationship strength is greater than or equal to the social evaluation threshold; and deleting the candidate relay node corresponding to the social relationship strength when the social relationship strength is less than the social evaluation threshold.

[0011] Optionally, the step of selecting the candidate relay node with the minimum communication interruption probability in the filtered candidate relay set as the target relay node includes: respectively calculating the first communication signal-to-noise ratio of each candidate relay node and the second communication signal-to-noise ratio of the communication receiving vehicle; combining the communication sending vehicle, a certain candidate relay node in the filtered candidate relay set, and the communication receiving vehicle into a communication direct connection group; based on the first communication signal-to-noise ratio and the second communication signal-to-noise ratio, calculating a first interruption probability value from the communication sending vehicle to the candidate relay node in each communication direct connection group, and calculating a second interruption probability value from the candidate relay node to the communication receiving vehicle; using a preset unsupervised learning algorithm to select the maximum probability value among the first interruption probability value and the second interruption probability value as the interruption probability value of the communication direct connection group; determining the interruption probability value corresponding to each communication direct connection group to obtain an interruption probability set; and taking the candidate relay node in the communication direct connection group corresponding to the minimum value in the interruption probability set as the target relay node.

[0012] Optionally, the step of respectively calculating the first communication signal-to-noise ratio of each candidate relay node and the second communication signal-to-noise ratio of the communication receiving vehicle includes: obtaining a first channel gain from the communication sending vehicle to the candidate relay node; controlling the communication sending vehicle to transmit data packets to each candidate relay node with a preset communication power, and combining the preset communication power and the first channel gain to detect the first received power of the candidate relay node; calculating the first communication signal-to-noise ratio of the candidate relay node based on the first received power and the Gaussian white noise power; obtaining a second channel gain from each candidate relay node to the communication receiving vehicle; controlling the candidate relay node to transmit data packets to the communication receiving vehicle with the first received power, and combining the first received power and the second channel gain to detect the second received power of the communication receiving vehicle; and calculating the second communication signal-to-noise ratio of the communication receiving vehicle based on the second received power and the Gaussian white noise power.

[0013] Optionally, the step of calculating the first communication signal-to-noise ratio of each of the candidate relay nodes and the second communication signal-to-noise ratio of the communication receiving vehicle further includes: defining each of the filtered candidate relay nodes as a learning state, and defining the data transmission between the communication sending vehicle and each of the candidate relay nodes as a learning action; respectively using the learning state and the learning action as the nodes and edges of an unsupervised learning algorithm, determining the ratio of the overall outage probability of all the candidate relay nodes to the communication outage probability of each candidate relay node; obtaining the learning rate and discount factor when using the preset unsupervised learning algorithm; combining the ratio, the learning rate, and the discount factor to update the maximum learning parameter matrix of the preset unsupervised learning algorithm, where the maximum learning parameter matrix is used to select the outage probability value.

[0014] According to another aspect of the embodiments of the present invention, there is also provided a relay selection device in a vehicle-to-everything network, including: a determination unit configured to determine a selection range radius based on the position information of two vehicles to be networked, where the two vehicles to be networked include: a communication sending vehicle and a communication receiving vehicle; an acquisition unit configured to acquire all candidate relay nodes within the communication range indicated by the selection range radius to obtain a candidate relay set; a calculation unit configured to calculate the social relationship strength between the communication sending vehicle and each of the candidate relay nodes, where the social relationship strength is used to filter the candidate relay nodes to obtain a filtered candidate relay set; a selection unit configured to select the candidate relay node with the minimum communication outage probability in the filtered candidate relay set as the target relay node, where the target relay node serves as the relay networking node for node direct communication between the communication sending vehicle and the communication receiving vehicle.

[0015] Optionally, the determination unit includes: a first combination subunit configured to combine the two vehicles to be networked into a communication vehicle pair; a first acquisition subunit configured to acquire the positioning coordinates of each vehicle in the communication vehicle pair to obtain the position information; a first determination subunit configured to determine the direct connection distance between the communication vehicle pair based on the position information; a first selection subunit configured to select the midpoint position of the direct connection distance; a second determination subunit configured to determine the selection range radius with any vehicle in the communication vehicle pair as the starting point and the midpoint position as the ending point.

[0016] Optionally, the computing unit includes: a first construction subunit configured to construct an interest evaluation model, wherein the training input data of the interest evaluation model is: the identifier of user i and the identifier of user j in any pair of users, and the set of things, and the training output data of the interest evaluation model is: the interest parameters of user i and user j for each thing; a second acquisition subunit configured to acquire the user information of the first vehicle user corresponding to the communication sending vehicle and the user information of the second vehicle user corresponding to each candidate relay node; a first evaluation subunit configured to, based on the user information of the first vehicle user, use the interest evaluation model to evaluate the interest parameters of the first vehicle user for N things, and based on the user information of the second vehicle user, use the interest evaluation model to evaluate the interest parameters of the second vehicle user for the N things, where N is a positive integer greater than or equal to 1; a first calculation subunit configured to comprehensively calculate the interest similarity between the communication sending vehicle and each candidate relay node based on the interest parameters of the first vehicle user for N things and the interest parameters of the second vehicle user for the N things; a third determination subunit configured to determine the social relationship strength between the communication sending vehicle and each candidate relay node based on the interest similarity.

[0017] Optionally, the computing unit further includes: a third acquisition subunit configured to acquire a social evaluation threshold within a specified time period; a first retention subunit configured to retain the candidate relay node corresponding to the social relationship strength when the social relationship strength is greater than or equal to the social evaluation threshold; a first deletion subunit configured to delete the candidate relay node corresponding to the social relationship strength when the social relationship strength is less than the social evaluation threshold.

[0018] Optionally, the selection unit includes: a second calculation subunit, configured to calculate the first communication signal-to-noise ratio of each candidate relay node and the second communication signal-to-noise ratio of the communication receiving vehicle respectively; a second combination subunit, configured to combine the communication sending vehicle, a certain candidate relay node in the filtered candidate relay set, and the communication receiving vehicle into a communication direct connection group; a third calculation subunit, configured to calculate, based on the first communication signal-to-noise ratio and the second communication signal-to-noise ratio, a first outage probability value from the communication sending vehicle to the candidate relay node in each communication direct connection group, and calculate a second outage probability value from the candidate relay node to the communication receiving vehicle; a second selection subunit, configured to select, by using a preset unsupervised learning algorithm, the maximum probability value among the first outage probability value and the second outage probability value as the outage probability value of the communication direct connection group; a fourth determination subunit, configured to determine the outage probability value corresponding to each communication direct connection group to obtain an outage probability set; a first acting subunit, configured to use the candidate relay node in the communication direct connection group corresponding to the minimum value in the outage probability set as the target relay node.

[0019] Optionally, the second calculation subunit includes: a first acquisition module, configured to acquire a first channel gain from the communication sending vehicle to the candidate relay node; a first detection module, configured to control the communication sending vehicle to transmit data packets to each candidate relay node at a preset communication power, and detect a first received power of the candidate relay node by combining the preset communication power and the first channel gain; a first calculation module, configured to calculate the first communication signal-to-noise ratio of the candidate relay node based on the first received power and Gaussian white noise power; a second acquisition module, configured to acquire a second channel gain from each candidate relay node to the communication receiving vehicle; a second detection module, configured to control the candidate relay node to transmit data packets to the communication receiving vehicle at the first received power, and detect a second received power of the communication receiving vehicle by combining the first received power and the second channel gain; a second calculation module, configured to calculate the second communication signal-to-noise ratio of the communication receiving vehicle based on the second received power and Gaussian white noise power.

[0020] Optionally, the selection unit further includes: a first definition subunit, configured to define each of the filtered candidate relay nodes as a learning state, and define the data transmission between the communication sending vehicle and each candidate relay node as a learning action; a fifth determination subunit, configured to determine, respectively, with the learning state and the learning action as the nodes and edges of an unsupervised learning algorithm, the ratio of the total outage probabilities of all the candidate relay nodes to the outage probability of each candidate relay node; a fourth acquisition subunit, configured to acquire the learning rate and the discount factor when using the preset unsupervised learning algorithm; a first update subunit, configured to update the maximum learning parameter matrix of the preset unsupervised learning algorithm in combination with the ratio, the learning rate, and the discount factor, where the maximum learning parameter matrix is used to select the outage probability value.

[0021] According to another aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium, which includes a stored computer program, where, when the computer program runs, it controls the device where the computer-readable storage medium is located to execute the relay selection method in the vehicle-to-everything network in any one of the above.

[0022] According to another aspect of the embodiments of the present invention, there is also provided an electronic device, including one or more processors and a memory, where the memory is used to store one or more programs, and where, when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the relay selection method in the vehicle-to-everything network in any one of the above.

[0023] In this application, the following steps are adopted. Based on the position information of two vehicles to be networked, the selection range radius is determined, where the two vehicles to be networked include: a communication sending vehicle and a communication receiving vehicle; all candidate relay nodes within the communication range indicated by the selection range radius are acquired to obtain a candidate relay set; the social relationship strength between the communication sending vehicle and each candidate relay node is calculated, where the social relationship strength is used to filter the candidate relay nodes to obtain a filtered candidate relay set; the candidate relay node with the minimum communication outage probability in the filtered candidate relay set is selected as the target relay node, where the target relay node serves as the relay networking node when the communication sending vehicle and the communication receiving vehicle perform node direct connection communication.

[0024] In this application, by calculating the social relationship strength between the communication - sending vehicle and each candidate relay node, when vehicle D2D relay communication is carried out, the node with the lowest communication interruption probability within its own range is selected as the relay node. The selected relay node is used to realize networking between two vehicles beyond the allowed communication distance. The relay screening process based on social relationships is more in line with the real vehicle environment scenario, fully considering the relay forwarding willingness while being able to improve communication security, thereby obtaining higher communication quality in the system, and further solving the technical problem in the related art that when the communication distance between communication objects exceeds the allowed maximum range, a suitable relay node cannot be selected, resulting in poor communication quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation to the present invention. In the drawings:

[0026] Figure 1 is a schematic diagram of vehicle D2D relay communication provided according to an embodiment of the present invention;

[0027] Figure 2 is a flowchart of an optional relay selection method in a vehicle - to - everything network provided according to an embodiment of the present invention;

[0028] Figure 3 is an iteration diagram of the Q - learning algorithm in a relay selection method in a vehicle - to - everything network provided according to an embodiment of the present invention;

[0029] Figure 4 is a schematic diagram of an optional relay selection device in a vehicle - to - everything network provided according to an embodiment of the present invention;

[0030] Figure 5 is a hardware structure block diagram of an electronic device (or mobile device) of a relay selection method in a vehicle - to - everything network according to an embodiment of the present invention DETAILED DESCRIPTION OF THE EMBODIMENTS

[0031] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0032] It should be noted that the terms "first", "second", etc. in the description, claims and the above drawings of the present invention are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present invention described herein can be implemented in an order different from those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0033] For the convenience of those skilled in the art to understand the present invention, the following explanations are made for some terms or nouns involved in each embodiment of the present invention:

[0034] The strength of the social relationship refers to the magnitude of the association relationship between a device and a relay node in the vehicle network.

[0035] The D2D communication technology, where D2D is short for Device to Device, refers to a communication method in which two peer user nodes directly communicate with each other. In a distributed network composed of D2D communication users, each user node can send and receive signals and can automatically forward messages.

[0036] The D2D communication technology used in this application enables two communication devices with a relatively short physical distance (such as two moving vehicles in the vehicle network of this application) to directly communicate without passing through a base station for forwarding. By reusing spectrum resources, it can improve spectrum efficiency and reduce the power consumption of mobile users, and can to a certain extent reduce the load on the base station and increase the system capacity. Compared with other direct-through technologies that do not rely on basic network facilities, D2D is more flexible and can be connected and resource-allocated under the control of the base station, or information can be exchanged when there is no network infrastructure.

[0037] It should be noted that the relay selection method and device in the vehicle network in this disclosure can be used in the field of the Internet of Things. In the case of selecting a relay node for vehicle communication, it can also be used in any field other than the field of the Internet of Things. In the case of selecting a relay node for vehicle communication, the application field of the relay selection method and device in the vehicle network in this disclosure is not limited.

[0038] It should be noted that the relevant information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this disclosure are all information and data authorized by users or fully authorized by all parties. For example, an interface is set up between this system and relevant users or institutions. Before obtaining relevant information, a request for acquisition needs to be sent to the aforementioned users or institutions through the interface, and after receiving the consent information feedback from the aforementioned users or institutions, the relevant information can be obtained.

[0039] The present invention can be applied to various vehicle networking systems / products, and can provide a reasonable relay selection scheme in vehicle networking. According to the calculated social relationship strength, when a vehicle performs D2D relay communication, it selects the node with the lowest communication interruption probability within its own range as the relay node (i.e., selects Relay). Through the relay screening process of social relationships, it makes the selection more in line with the actual environment where the vehicle is located. It can not only fully consider the relay forwarding willingness, but also improve communication security, thereby obtaining higher communication quality in the system.

[0040] Figure 1 is a schematic diagram of vehicle D2D relay communication provided according to an embodiment of the present invention, as Figure 1 shown in the schematic diagram of vehicle D2D relay communication. There are multiple relay nodes distributed on both sides of the road where the vehicle is traveling ( Figure 1 indicated by Relay in Figure 1 ), and base stations / signal towers can be built between long-distance relay base stations ( Figure 1 indicated by BS in

[0041] ). Communication is carried out between two vehicles ( Figure 1 including D2D_t and D2D_r). The distance between the vehicles is determined according to the positioning positions, and then a suitable relay node is selected as the intermediate communication node.

[0041] The following will describe this application in detail in combination with each embodiment.

[0042] Embodiment 1

[0043] According to an embodiment of the present invention, an embodiment of a relay selection method in vehicle networking is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0044] The relay selection method in the vehicle networking provided by the embodiment of the present invention makes the vehicle select the node with the lowest communication interruption probability within its own range as the relay node during the D2D relay communication process by calculating the strength of the social relationship. The relay screening process based on the social relationship makes it more conform to the actual environment scenario of the vehicle. It can not only fully consider the relay forwarding willingness, but also improve the communication security, so as to obtain a higher communication quality in the system. The present invention will be described below in combination with the preferred implementation steps.

[0045] Figure 2 It is a flowchart of an optional relay selection method in the vehicle networking provided by the embodiment of the present invention. As Figure 2 shown, the method includes the following steps:

[0046] Step S201, based on the location information of two vehicles to be networked, determine the selection range radius, where the two vehicles to be networked include: a communication sending vehicle and a communication receiving vehicle;

[0047] Step S202, obtain all candidate relay nodes within the communication range indicated by the selection range radius to obtain a candidate relay set;

[0048] Step S203, calculate the social relationship strength between the communication sending vehicle and each candidate relay node, where the social relationship strength is used to screen the candidate relay nodes to obtain a screened candidate relay set;

[0049] Step S204, select the candidate relay node with the lowest communication interruption probability in the screened candidate relay set as the target relay node, where the target relay node is the relay networking node for direct node-to-node communication between the communication sending vehicle and the communication receiving vehicle.

[0050] Through the above steps, based on the location information of two vehicles to be networked, determine the selection range radius, where the two vehicles to be networked include: a communication sending vehicle and a communication receiving vehicle; obtain all candidate relay nodes within the communication range indicated by the selection range radius to obtain a candidate relay set; calculate the social relationship strength between the communication sending vehicle and each candidate relay node, where the social relationship strength is used to screen the candidate relay nodes to obtain a screened candidate relay set; select the candidate relay node with the lowest communication interruption probability in the screened candidate relay set as the target relay node, where the target relay node is the relay networking node for direct node-to-node communication between the communication sending vehicle and the communication receiving vehicle.

[0051] In this application, according to the calculated social relationship strength, when the vehicle D2D relay communication is in progress, the node with the lowest communication interruption probability within its own range is selected as the relay node. The selected relay node is used to realize the networking between two vehicles beyond the allowable communication distance. Through the relay screening process of social relationships, it better conforms to the actual environment scenario of the vehicle. It can not only fully consider the relay forwarding willingness, but also improve the communication security, so as to obtain a higher communication quality in the system, and solve the technical problem in the related art that when the communication distance between communication objects exceeds the allowable maximum range, it is impossible to select a suitable relay node, resulting in poor communication quality.

[0052] The following will be described in detail in combination with the above-mentioned implementation steps.

[0053] Step S201: Based on the position information of two vehicles to be networked, determine the selection range radius. Among them, the two vehicles to be networked include: a communication sending vehicle and a communication receiving vehicle.

[0054] To realize the communication between two vehicles, first, based on the position information of the two vehicles to be networked, determine the selection range radius of the relay node. The vehicle position information can be the specific position information obtained through the positioning module on the vehicle (for example, GPS navigation module, Beidou navigation module, Bluetooth positioning module). The position information includes but is not limited to: the longitude of the vehicle's location, the latitude of the vehicle's location, the name of the place where the vehicle is located, the range place name of the vehicle's location, etc.

[0055] In the embodiment of the present invention, the step of determining the selection range radius based on the position information of two vehicles to be networked includes: combining the two vehicles to be networked into a communication vehicle pair; obtaining the positioning coordinates of each vehicle in the communication vehicle pair to obtain the position information; based on the position information, determine the direct connection distance between the communication vehicle pair; select the midpoint position of the direct connection distance; take any vehicle in the communication vehicle pair as the starting point and the midpoint position as the ending point to determine the selection range radius.

[0056] A communication vehicle pair refers to a set / system formed by combining two vehicles that need to communicate. To realize the communication between the communication vehicle pair, according to the obtained position information, the two vehicles are directly connected and the straight-line distance is measured, and the midpoint on this straight line is selected as the ending point of the radius to be selected. At the same time, the position where the vehicle is located is used as the starting point of the radius to be selected, and the line connecting the starting point and the ending point is used as the radius. With the ending point as the positioning point, the starting point is controlled to draw a circle around the radius, thereby determining a range to be selected, and obtaining all available relay nodes within the range to be selected.

[0057] For example, the selected vehicle D2D relay communication network includes a vehicle D2D user transmitter t, a vehicle D2D user receiver r, and N idle candidate relay users. The signal sent by the vehicle D2D user transmitter t is forwarded to the vehicle D2D user receiver r through the data of the selected relay user. In the vehicle D2D user pair (corresponding to the above-mentioned communication vehicle pair), the distance L between the D2D user pairs is determined according to the positioning position. It is stipulated that the range for the vehicle D2D user pair to detect the relay user is centered at the midpoint position between the two vehicle distances, with L max as the radius.

[0058] Step S202: Obtain all candidate relay nodes within the communication range indicated by the selected range radius to obtain a candidate relay set.

[0059] After obtaining the range radius, all relay nodes within this range are obtained as candidate relay nodes, thereby obtaining all candidate relay sets that can realize the communication between the above-mentioned communication vehicle pairs.

[0060] Step S203: Calculate the social relationship strength between the communication sending vehicle and each candidate relay node. Among them, the social relationship strength is used to screen candidate relay nodes to obtain a filtered candidate relay set.

[0061] In this embodiment, considering information such as the interests and social interactions between vehicles or other communication objects, the social relationship strength is determined to screen relay nodes.

[0062] In this embodiment, the steps of calculating the social relationship strength between the communication sending vehicle and each candidate relay node include: constructing an interest evaluation model. Among them, the training input data of the interest evaluation model is: the identification of user i and the identification of user j in any user pair, the set of things. The training output data of the interest evaluation model is: the interest parameters of user i and user j for each thing; obtain the user information of the first vehicle user corresponding to the communication sending vehicle and the user information of the second vehicle user corresponding to each candidate relay node; based on the user information of the first vehicle user, use the interest evaluation model to evaluate the interest parameters of the first vehicle user for N things, and based on the user information of the second vehicle user, use the interest evaluation model to evaluate the interest parameters of the second vehicle user for N things, where N is a positive integer greater than or equal to 1; comprehensively consider the interest parameters of the first vehicle user for N things and the interest parameters of the second vehicle user for N things, calculate the interest similarity between the communication sending vehicle and each candidate relay node; based on the interest similarity, determine the social relationship strength between the communication sending vehicle and each candidate relay node.

[0063] When calculating the social relationship strength, the constructed similarity model is used to represent the social relationship strength. The higher the similarity, the greater the social relationship strength.

[0064] Specifically, let the social relationship strength between user i and user j be w i,j , and the formula for the social relationship strength is as follows:

[0065]

[0066] where the vector I i = {θ i,1 , θ i,2 ,..., θ i,n} and I j = {θ j,1 , θ j,2 ,..., θ j,n} respectively represent the interest parameters / degrees of interest of user i and user j in all n things. Among them, the interest parameter / degree of interest is to evaluate the attention of each thing of the user (which can be determined by the attention duration and the number of attention times), and the interest parameter is evaluated through the attention degree.

[0067] By constructing an interest similarity model, the social relationship strength between vehicle users i and j can be directly obtained.

[0068] In the embodiment of the present invention, after calculating the social relationship strength between the communication sending vehicle and each candidate relay node, it further includes: obtaining a social evaluation threshold within a specified time period; retaining the candidate relay node corresponding to the social relationship strength when the social relationship strength is greater than or equal to the social evaluation threshold; and deleting the candidate relay node corresponding to the social relationship strength when the social relationship strength is less than the social evaluation threshold.

[0069] After obtaining the social relationship strength between the sending vehicle and each candidate relay node, all the obtained relay nodes are screened to obtain relay nodes that meet the predetermined conditions. For example, when the vehicle D2D user sender t explores the relay user pair, a social threshold W th is as follows:

[0070]

[0071] where represents the social relationship strength between the D2D user sender t (corresponding to the above-mentioned communication sending vehicle) and the relay user N k , is used to set and adjust the size of the social threshold w th . For the D2D user sender t, if , then the relay user N k is retained; if , then the relay user N k is deleted., after screening by the social threshold, the number of candidate relay users is reduced from N to N', so as to reduce the number of candidate relay users and obtain more eligible relay users.

[0072] Step S204: Select the candidate relay node with the minimum communication interruption probability in the screened candidate relay set as the target relay node, where the target relay node serves as the relay networking node for direct node communication between the communication sending vehicle and the communication receiving vehicle.

[0073] In the embodiment of the present invention, the step of selecting the candidate relay node with the minimum communication interruption probability in the screened candidate relay set as the target relay node includes: calculating the first communication signal-to-noise ratio of each candidate relay node and the second communication signal-to-noise ratio of the communication receiving vehicle respectively; combining the communication sending vehicle, a certain candidate relay node in the screened candidate relay set, and the communication receiving vehicle into a communication direct connection group. In the embodiment of the present invention, based on the first communication signal-to-noise ratio and the second communication signal-to-noise ratio, calculate the first interruption probability value from the communication sending vehicle to the candidate relay node in each communication direct connection group, and calculate the second interruption probability value from the candidate relay node to the communication receiving vehicle; adopt a preset unsupervised learning algorithm to select the maximum probability value among the first interruption probability value and the second interruption probability value as the interruption probability value of the communication direct connection group; determine the interruption probability value corresponding to each communication direct connection group to obtain an interruption probability set; use the candidate relay node in the communication direct connection group corresponding to the minimum value in the interruption probability set as the target relay node.

[0074] In the embodiment of the present invention, the step of calculating the first communication signal-to-noise ratio of each candidate relay node and the second communication signal-to-noise ratio of the communication receiving vehicle respectively includes: obtaining the first channel gain from the communication sending vehicle to the candidate relay node; controlling the communication sending vehicle to transmit data packets to each candidate relay node at a preset communication power, and combining the preset communication power and the first channel gain to detect the first received power of the candidate relay node; based on the first received power and the Gaussian white noise power, calculate the first communication signal-to-noise ratio of the candidate relay node; obtaining the second channel gain from each candidate relay node to the communication receiving vehicle; controlling the candidate relay node to transmit data packets to the communication receiving vehicle at the first received power, and combining the first received power and the second channel gain to detect the second received power of the communication receiving vehicle; based on the second received power and the Gaussian white noise power, calculate the second communication signal-to-noise ratio of the communication receiving vehicle.

[0075] For example, the communication sending vehicle / D2D user sending end t transmits data to the relay user at power P t The received power of the relay user (corresponding to the first received power of the candidate relay node mentioned above) can be expressed as:

[0076] P t,N’ =P t·H t,N’ ;

[0077] Among them, H t,N’ represents the channel gain from the D2D user transmitter t (corresponding to the above-mentioned communication transmitting vehicle) to the relay user N' (corresponding to the above-mentioned candidate relay node) (corresponding to the above-mentioned first channel gain).

[0078] Then the signal-to-noise ratio at the relay user N' (corresponding to the first communication signal-to-noise ratio of the above-mentioned candidate relay node) is:[[]]

[0079]

[0080] Among them, N 0 represents the Gaussian white noise power.

[0081] Similarly, the received power of the D2D user receiver r (corresponding to the second received power of the above-mentioned communication receiving vehicle) can be obtained as:[[]]

[0082] P N’,r = P t,N’ ·H N’,r ;

[0083] Among them, H N’,r represents the channel gain from the relay user N' to the D2D user receiver r (corresponding to the above-mentioned second channel gain).

[0084] The signal-to-noise ratio at the D2D user receiver r is:[[]]

[0085]

[0086] The outage probability of the D2D system is defined as the probability that the communication signal-to-noise ratio SNR is less than the signal-to-noise ratio threshold SNR th , which is expressed as:[[]]

[0087] P_out = P(SNR < SNR th );

[0088] Then the entire vehicle D2D relay-assisted communication with the goal of minimizing the outage probability can be expressed as:[[]]

[0089] min(P out ) = min(max(P t,N’ _out, P N’,r _out));

[0090] Among them, P t,N’ _out represents the outage probability from the D2D user transmitter t to the relay user N', and P N’,r _out represents the outage probability from the relay user N' to the D2D user receiver r. max(P t,N’ _out, PN’,r _out) represents selecting the maximum outage probability from two hops of a relay link (one hop from the user transmitter to the relay node and one hop from the relay node to the user receiver) (corresponding to selecting the maximum probability value from the above-mentioned first outage probability value and second outage probability value as the outage probability value of the communication direct connection group) to satisfy the communication of the entire link; min(max(P t,N’ _out, P N’,r _out)) represents selecting the link with the minimum outage probability from N relay links (corresponding to selecting the candidate relay node in the communication direct connection group corresponding to the minimum value in the outage probability set as the target relay node).

[0091] It should be noted that in this application, a preset unsupervised learning algorithm (Q-learning is used for illustration in this embodiment) is adopted, so that the system can update data by itself and select the most suitable communication relay node during the D2D relay communication process. Figure 3 is the iteration graph of the Q-learning algorithm in the relay selection method in the vehicle-to-everything network. The learner is defined as the vehicle D2D user pair transmitter t and receiver r, and the state is defined as the candidate relay users N' after social threshold screening (corresponding to Figure 3 the N' relay users in it). An action: at is used to evaluate from the learner to the state. For the state of each relay user, it is necessary to determine the reward value R when communicating with the user pair, and then use the Q-learning function to update to obtain the Q-value matrix, and select the highest one in the Q-value matrix as the relay node to complete the relay node screening. Among them, the action is defined as the vehicle D2D user transmitter t randomly selecting a relay user to forward data, and the reward value R is defined as the ratio of the total outage probability of exploring all candidate relays by the D2D user transmitter t to the communication outage probability of exploring any one node in the candidate relay users N', which is expressed as:

[0092]

[0093] Then the Q-learning model is:

[0094] Q(N', a) ← (1 - α)·Q(N', a) + α(R + γ·maxQ'(N', a));

[0095] Among them, α = [0, 1] represents the learning rate, γ represents the discount factor, and a represents the action executed by the D2D user transmitter t. Q(N', a) represents the initial Q-value matrix, and maxQ'(N', a) represents the maximum utility Q-value matrix selected after each Q-Learning.

[0096] Through the above embodiments, the social relationship strength between the communication sending vehicle and each candidate relay node is calculated, so that in the vehicle D2D relay communication process, an idle node / idle user with the lowest communication interruption probability within its own range is selected as the relay user. The relay screening process based on social relationships is more in line with the real vehicle environment scenario, fully considering the relay forwarding willingness while improving communication security, thereby obtaining higher communication quality in the system, and further solving the technical problem in the related art that when the communication distance between communication objects exceeds the allowed maximum range, a suitable relay node cannot be selected, resulting in poor communication quality.

[0097] The following describes the present invention in conjunction with another alternative embodiment.

[0098] Embodiment 2

[0099] This embodiment provides a relay selection device in a vehicle-to-everything network. Each implementation unit included in the selection device corresponds to each implementation step in Embodiment 1 above.

[0100] This application embodiment also provides a relay selection device in a vehicle-to-everything network. It should be noted that the relay selection device in the vehicle-to-everything network in this application embodiment can be used to execute the relay selection method in the vehicle-to-everything network provided in Embodiment 1 above. The following introduces the relay selection device in the vehicle-to-everything network provided in this application embodiment.

[0101] Figure 4 is a schematic diagram of an alternative relay selection device in a vehicle-to-everything network according to an embodiment of the present invention. As Figure 4 shown, the device includes: a determination unit 40, an acquisition unit 42, a calculation unit 44, and a selection unit 46. The device will be described in detail below.

[0102] The determination unit 40 is configured to determine a selection range radius based on the position information of two vehicles to be networked, where the two vehicles to be networked include: a communication sending vehicle and a communication receiving vehicle;

[0103] The acquisition unit 42 is configured to acquire all candidate relay nodes within the communication range indicated by the selection range radius to obtain a candidate relay set;

[0104] The calculation unit 44 is configured to calculate the social relationship strength between the communication sending vehicle and each candidate relay node, where the social relationship strength is used to screen the candidate relay nodes to obtain a filtered candidate relay set;

[0105] The selection unit 46 is configured to select the candidate relay node with the lowest communication interruption probability in the filtered candidate relay set as the target relay node, where the target relay node serves as a relay networking node for direct node communication between the communication sending vehicle and the communication receiving vehicle.

[0106] The control device for the client provided by the embodiment of the present application, through the determination unit 40, determines the selection range radius based on the position information of two vehicles to be networked, where the two vehicles to be networked include: a communication sending vehicle and a communication receiving vehicle; an acquisition unit 42 acquires all candidate relay nodes within the communication range indicated by the selection range radius to obtain a candidate relay set; a calculation unit 44 calculates the social relationship strength between the communication sending vehicle and each candidate relay node, where the social relationship strength is used to screen the candidate relay nodes to obtain a filtered candidate relay set; a selection unit 46 selects the candidate relay node with the lowest communication interruption probability in the filtered candidate relay set as the target relay node, where the target relay node serves as the relay networking node during node direct communication between the communication sending vehicle and the communication receiving vehicle.

[0107] In this embodiment, by calculating the social relationship strength between the communication sending vehicle and each candidate relay node, when the vehicle D2D relay communication is in progress, the node with the lowest communication interruption probability within its own range is selected as the relay node. The selected relay node is used to implement networking between two vehicles beyond the allowed communication distance. The relay screening process based on social relationships is more in line with the real vehicle environment scenario. While fully considering the relay forwarding willingness, it can improve communication security, thereby obtaining higher communication quality in the system. Furthermore, it solves the technical problem in the related art that when the communication distance between communication objects exceeds the allowed maximum range, it is impossible to select a suitable relay node, resulting in poor communication quality.

[0108] Optionally, the determination unit includes: a first combination subunit for combining the two vehicles to be networked into a communication vehicle pair; a first acquisition subunit for acquiring the positioning coordinates of each vehicle in the communication vehicle pair to obtain the position information; a first determination subunit for determining the direct connection distance between the communication vehicle pair based on the position information; a first selection subunit for selecting the midpoint position of the direct connection distance; a second determination subunit for determining the selection range radius with any vehicle in the communication vehicle pair as the starting point and the midpoint position as the ending point.

[0109] Optionally, the computing unit includes: a first construction subunit, configured to construct an interest evaluation model, wherein the training input data of the interest evaluation model is: the identifiers of user i and user j in any pair of users, the set of things, and the training output data of the interest evaluation model is: the interest parameters of user i and user j for each thing; a second acquisition subunit, configured to acquire the user information of the first vehicle user corresponding to the communication sending vehicle and the user information of the second vehicle user corresponding to each candidate relay node; a first evaluation subunit, configured to evaluate the interest parameters of the first vehicle user for N things by using the interest evaluation model based on the user information of the first vehicle user, and evaluate the interest parameters of the second vehicle user for the N things by using the interest evaluation model based on the user information of the second vehicle user, where N is a positive integer greater than or equal to 1; a first calculation subunit, configured to calculate the interest similarity between the communication sending vehicle and each candidate relay node by synthesizing the interest parameters of the first vehicle user for N things and the interest parameters of the second vehicle user for the N things; a third determination subunit, configured to determine the social relationship strength between the communication sending vehicle and each candidate relay node based on the interest similarity.

[0110] Optionally, the computing unit further includes: a third acquisition subunit, configured to acquire a social evaluation threshold within a specified time period; a first retention subunit, configured to retain the candidate relay node corresponding to the social relationship strength when the social relationship strength is greater than or equal to the social evaluation threshold; a first deletion subunit, configured to delete the candidate relay node corresponding to the social relationship strength when the social relationship strength is less than the social evaluation threshold.

[0111] Optionally, the selection unit includes: a second calculation subunit, configured to calculate the first communication signal-to-noise ratio of each candidate relay node and the second communication signal-to-noise ratio of the communication receiving vehicle respectively; a second combination subunit, configured to combine the communication sending vehicle, a certain candidate relay node in the filtered candidate relay set, and the communication receiving vehicle into a communication direct connection group; a third calculation subunit, configured to calculate, based on the first communication signal-to-noise ratio and the second communication signal-to-noise ratio, a first outage probability value from the communication sending vehicle to the candidate relay node in each communication direct connection group, and calculate a second outage probability value from the candidate relay node to the communication receiving vehicle; a second selection subunit, configured to select, by using a preset unsupervised learning algorithm, the maximum probability value among the first outage probability value and the second outage probability value as the outage probability value of the communication direct connection group; a fourth determination subunit, configured to determine the outage probability value corresponding to each communication direct connection group to obtain an outage probability set; a first acting subunit, configured to use the candidate relay node in the communication direct connection group corresponding to the minimum value in the outage probability set as the target relay node.

[0112] Optionally, the second calculation subunit includes: a first acquisition module, configured to acquire a first channel gain from the communication sending vehicle to the candidate relay node; a first detection module, configured to control the communication sending vehicle to transmit data packets to each candidate relay node at a preset communication power, and detect a first received power of the candidate relay node by combining the preset communication power and the first channel gain; a first calculation module, configured to calculate the first communication signal-to-noise ratio of the candidate relay node based on the first received power and Gaussian white noise power; a second acquisition module, configured to acquire a second channel gain from each candidate relay node to the communication receiving vehicle; a second detection module, configured to control the candidate relay node to transmit data packets to the communication receiving vehicle at the first received power, and detect a second received power of the communication receiving vehicle by combining the first received power and the second channel gain; a second calculation module, configured to calculate the second communication signal-to-noise ratio of the communication receiving vehicle based on the second received power and Gaussian white noise power.

[0113] Optionally, the selection unit further includes: a first definition subunit, configured to define each of the filtered candidate relay nodes as a learning state, and define the data transmission between the communication sending vehicle and each candidate relay node as a learning action; a fifth determination subunit, configured to determine, respectively, with the learning state and the learning action as nodes and edges of an unsupervised learning algorithm, the ratio of the total outage probability of all candidate relay nodes to the communication outage probability of each candidate relay node; a fourth acquisition subunit, configured to acquire a learning rate and a discount factor when using the preset unsupervised learning algorithm; a first update subunit, configured to update the maximum learning parameter matrix of the preset unsupervised learning algorithm in combination with the ratio, the learning rate, and the discount factor, where the maximum learning parameter matrix is used to select an outage probability value.

[0114] The above relay selection device in the vehicle-to-everything network may further include a processor and a memory. The above determination unit 40, acquisition unit 42, calculation unit 44, selection unit 46, etc. are all stored in the memory as program units, and the processor executes the above program units stored in the memory to implement corresponding functions.

[0115] The above processor includes a kernel, and the kernel retrieves the corresponding program units from the memory. The kernel can be set to one or more. Through the interest similarity model and Q-learning algorithm, when the vehicle D2D relay communication is in progress, a node with the lowest communication outage probability within its own range is selected as the relay node. The relay screening process through social relationships is more in line with the real vehicle environment scenario, fully considering the relay forwarding willingness while improving communication security, so as to obtain high-quality communication in the system.

[0116] The above memory may include non-permanent memory in a computer-readable medium, forms such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM), and the memory includes at least one storage chip.

[0117] According to another aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium, where the computer-readable storage medium includes a stored computer program, and when the computer program runs, it controls the device where the computer-readable storage medium is located to execute the relay selection method in the vehicle-to-everything network in any one of the above.

[0118] According to another aspect of the embodiments of the present invention, there is also provided an electronic device, including: a processor; and a memory, configured to store executable instructions of the processor; where the processor is configured to execute the relay selection method in the vehicle-to-everything network in any one of the above by executing the executable instructions.

[0119] Figure 5It is a hardware structure block diagram of an electronic device (or mobile device) for a relay selection method in an Internet of Vehicles according to an embodiment of the present invention. As Figure 5 shown, the electronic device may include one or more processors 502 (illustrated as 502a, 502b, ……, 502n in the figure) (the processor 502 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA), and a memory 504 for storing data. In addition, it may further include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, a keyboard, a power supply, and / or a camera. Those of ordinary skill in the art can understand that Figure 5 the structure shown is only schematic and does not limit the structure of the above-mentioned electronic device. For example, the electronic device may further include more or fewer components than Figure 5 shown, or have a different configuration from Figure 5 shown.

[0120] The serial numbers of the above-mentioned embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0121] In the above embodiments of the present invention, the descriptions of the respective embodiments have their own emphases. For parts not detailed in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0122] In several embodiments provided by the present application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only illustrative. For example, the division of units can be a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of units or modules can be in electrical or other forms.

[0123] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0124] In addition, in each embodiment of the present invention, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0125] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, read-only memories (ROMs), random access memories (RAMs), mobile hard disks, magnetic disks, or optical discs that can store program codes.

[0126] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A relay selection method in a vehicle networking, characterized in that, it includes: Based on the location information of two vehicles to be networked, determine the selection range radius, wherein the two vehicles to be networked include: a communication sending vehicle and a communication receiving vehicle; Obtain all candidate relay nodes within the communication range indicated by the selection range radius to obtain a candidate relay set; Calculate the social relationship strength between the communication sending vehicle and each candidate relay node, wherein the social relationship strength is used to screen the candidate relay nodes to obtain a filtered candidate relay set; The step of calculating the social relationship strength between the communication sending vehicle and each candidate relay node includes: constructing an interest evaluation model, wherein the training input data of the interest evaluation model is: the identifiers of user i and user j in any pair of users, a set of things, and the training output data of the interest evaluation model is: the interest parameters of user i and user j for each thing; obtain the user information of the first vehicle user corresponding to the communication sending vehicle and the user information of the second vehicle user corresponding to each candidate relay node; based on the user information of the first vehicle user, use the interest evaluation model to evaluate the interest parameters of the first vehicle user for N things, and based on the user information of the second vehicle user, use the interest evaluation model to evaluate the interest parameters of the second vehicle user for the N things, where N is a positive integer greater than or equal to 1; comprehensively consider the interest parameters of the first vehicle user for N things and the interest parameters of the second vehicle user for the N things, calculate the interest similarity between the communication sending vehicle and each candidate relay node; based on the interest similarity, determine the social relationship strength between the communication sending vehicle and each candidate relay node; Select the candidate relay node with the minimum communication interruption probability in the filtered candidate relay set as the target relay node, wherein the target relay node is used as the relay networking node for direct node communication between the communication sending vehicle and the communication receiving vehicle; The step of selecting the candidate relay node with the minimum communication interruption probability in the filtered candidate relay set as the target relay node includes: respectively calculate the first communication signal-to-noise ratio of each candidate relay node and the second communication signal-to-noise ratio of the communication receiving vehicle; combine the communication sending vehicle, a certain candidate relay node in the filtered candidate relay set, and the communication receiving vehicle into a communication direct connection group; based on the first communication signal-to-noise ratio and the second communication signal-to-noise ratio, calculate the first interruption probability value from the communication sending vehicle to the candidate relay node in each communication direct connection group, and calculate the second interruption probability value from the candidate relay node to the communication receiving vehicle; use a preset unsupervised learning algorithm to select the maximum probability value among the first interruption probability value and the second interruption probability value as the interruption probability value of the communication direct connection group; determine the interruption probability value corresponding to each communication direct connection group to obtain an interruption probability set; Define each of the filtered candidate relay nodes as being in a learning state, and define the data transmission between the communication sending vehicle and each candidate relay node as a learning action; respectively use the learning state and the learning action as the nodes and edges of an unsupervised learning algorithm, determine the ratio of the total outage probability of all candidate relay nodes to the communication outage probability of each candidate relay node, and use this ratio as the reward value of the preset unsupervised learning algorithm; obtain the learning rate and discount factor when using the preset unsupervised learning algorithm; combine the ratio, the learning rate, and the discount factor to update the maximum learning parameter matrix of the preset unsupervised learning algorithm, select the highest one in the maximum learning parameter matrix as the relay node, and complete the screening of the relay node, where the maximum learning parameter matrix is used to select the outage probability value.

2. The relay selection method according to claim 1, wherein, The step of determining the selection range radius based on the position information of two vehicles to be networked includes: Combine the two vehicles to be networked into a communication vehicle pair; Obtain the positioning coordinates of each vehicle in the communication vehicle pair to obtain the position information; Based on the position information, determine the direct connection distance between the communication vehicle pair; Select the midpoint position of the direct connection distance; Taking any vehicle in the communication vehicle pair as the starting point and the midpoint position as the end point, determine the selection range radius.

3. The relay selection method according to claim 1, wherein, After calculating the social relationship strength between the communication sending vehicle and each candidate relay node, it further includes: Obtain the social evaluation threshold within a specified time period; When the social relationship strength is greater than or equal to the social evaluation threshold, retain the candidate relay node corresponding to the social relationship strength; When the social relationship strength is less than the social evaluation threshold, delete the candidate relay node corresponding to the social relationship strength.

4. The relay selection method according to claim 1, wherein, The steps of respectively calculating the first communication signal-to-noise ratio of each candidate relay node and the second communication signal-to-noise ratio of the communication receiving vehicle include: Obtain the first channel gain from the communication sending vehicle to the candidate relay node; Control the communication sending vehicle to transmit data packets to each candidate relay node at a preset communication power, and combine the preset communication power and the first channel gain to detect the first received power of the candidate relay node; Based on the first received power and the Gaussian white noise power, calculate the first communication signal-to-noise ratio of the candidate relay node; Obtain the second channel gain from each candidate relay node to the communication receiving vehicle; Control the candidate relay node to transmit data packets to the communication receiving vehicle at the first received power, and combine the first received power and the second channel gain to detect the second received power of the communication receiving vehicle; Based on the second received power and the Gaussian white noise power, calculate the second communication signal-to-noise ratio of the communication receiving vehicle.

5. A relay selection device in a vehicle-to-everything network It is characterized in that including: a determination unit, configured to determine a selection range radius based on the location information of two vehicles to be networked, where the two vehicles to be networked include: a communication sending vehicle and a communication receiving vehicle; an acquisition unit, configured to acquire all candidate relay nodes within the communication range indicated by the selection range radius to obtain a candidate relay set; a calculation unit, configured to calculate the social relationship strength between the communication sending vehicle and each of the candidate relay nodes, where the social relationship strength is used to screen the candidate relay nodes to obtain a filtered candidate relay set; the calculation unit includes: a first construction subunit, configured to construct an interest evaluation model, where the training input data of the interest evaluation model is: the identifier of user i and the identifier of user j in any pair of users, and a set of things, and the training output data of the interest evaluation model is: the interest parameter of user i and user j for each thing; a second acquisition subunit, configured to acquire the user information of the first vehicle user corresponding to the communication sending vehicle and the user information of the second vehicle user corresponding to each of the candidate relay nodes; a first evaluation subunit, configured to evaluate the interest parameters of the first vehicle user for N things by using the interest evaluation model based on the user information of the first vehicle user, and evaluate the interest parameters of the second vehicle user for the N things by using the interest evaluation model based on the user information of the second vehicle user, where N is a positive integer greater than or equal to 1; a first calculation subunit, configured to comprehensively calculate the interest similarity between the communication sending vehicle and each of the candidate relay nodes based on the interest parameters of the first vehicle user for N things and the interest parameters of the second vehicle user for the N things; a third determination subunit, configured to determine the social relationship strength between the communication sending vehicle and each of the candidate relay nodes based on the interest similarity; a selection unit, configured to select the candidate relay node with the lowest communication interruption probability in the filtered candidate relay set as the target relay node, where the target relay node serves as the relay networking node for direct node-to-node communication between the communication sending vehicle and the communication receiving vehicle; The selection unit includes: a second calculation subunit, configured to calculate the first communication signal-to-noise ratio of each of the candidate relay nodes and the second communication signal-to-noise ratio of the communication receiving vehicle respectively; a second combination subunit, configured to combine the communication sending vehicle, a certain candidate relay node in the filtered candidate relay set, and the communication receiving vehicle into a communication direct connection group; a third calculation subunit, configured to calculate, based on the first communication signal-to-noise ratio and the second communication signal-to-noise ratio, a first outage probability value from the communication sending vehicle to the candidate relay node in each communication direct connection group, and calculate a second outage probability value from the candidate relay node to the communication receiving vehicle; a second selection subunit, configured to use a preset unsupervised learning algorithm to select the maximum probability value among the first outage probability value and the second outage probability value as the outage probability value of the communication direct connection group; a fourth determination subunit, configured to determine the outage probability value corresponding to each communication direct connection group to obtain an outage probability set; a first designation subunit, configured to designate the candidate relay node in the communication direct connection group corresponding to the minimum value in the outage probability set as the target relay node; The selection unit further includes: a first definition subunit, configured to define each of the filtered candidate relay nodes as a learning state, and define the data transmission between the communication sending vehicle and each candidate relay node as a learning action; a fifth determination subunit, configured to use the learning state and the learning action as nodes and edges of the unsupervised learning algorithm respectively, determine the ratio of the total outage probability of all candidate relay nodes to the communication outage probability of each candidate relay node, and use this ratio as the reward value of the preset unsupervised learning algorithm; a fourth acquisition subunit, configured to acquire the learning rate and discount factor when using the preset unsupervised learning algorithm; a first update subunit, configured to update the maximum learning parameter matrix of the preset unsupervised learning algorithm in combination with the ratio, the learning rate, and the discount factor, and select the highest one in the maximum learning parameter matrix as the relay node to complete the screening of the relay node, where the maximum learning parameter matrix is used to select the outage probability value.

6. A computer-readable storage medium, characterized in that, the computer-readable storage medium includes a stored computer program, wherein when the computer program runs, it controls the device where the computer-readable storage medium is located to execute the relay selection method in the vehicle-to-everything network according to any one of claims 1 to 4.

7. An electronic device, characterized in that, it includes one or more processors and a memory, and the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the relay selection method in the vehicle-to-everything network according to any one of claims 1 to 4.

Images