CN117579535B - Transmission path planning method, device, system and medium - Google Patents
Transmission path planning method, device, system and medium Download PDFInfo
- Publication number
- CN117579535B CN117579535B CN202410051851.2A CN202410051851A CN117579535B CN 117579535 B CN117579535 B CN 117579535B CN 202410051851 A CN202410051851 A CN 202410051851A CN 117579535 B CN117579535 B CN 117579535B
- Authority
- CN
- China
- Prior art keywords
- transmission
- confidence
- transmission path
- path
- information
- 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
- 230000005540 biological transmission Effects 0.000 title claims abstract description 466
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000011156 evaluation Methods 0.000 claims abstract description 29
- 238000013528 artificial neural network Methods 0.000 claims description 56
- 238000012549 training Methods 0.000 claims description 39
- 230000000694 effects Effects 0.000 abstract description 2
- 238000004891 communication Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The invention discloses a transmission path planning method, a device, a system and a medium, which relate to the technical field of data transmission, and are characterized in that transmission path information between vehicles and other vehicles is acquired based on running state information by acquiring the running state information, a transmission path with higher success rate of data transmission between the vehicles is determined according to the transmission path information of the vehicles needing to carry out data transmission and the vehicles needing to carry out data reception, the effect of reducing time delay is achieved to a certain extent, the transmission path information is input into a confidence evaluation network model, the confidence of the transmission is output, the transmission is obtained, the vehicles are helped to make efficient transmission decisions, the transmission performance of the vehicles is improved, the target transmission path is determined according to the confidence of the transmission and the transmission purpose, the pertinence and the efficiency of the data transmission are improved, and the transmission time delay can be greatly reduced on the basis of guaranteeing the transmission success rate.
Description
Technical Field
The present invention relates to the field of data transmission technologies, and in particular, to a transmission path planning method, apparatus, system, and medium.
Background
The vehicle-mounted image transmission system is generally applied to occasions requiring on-site image transmission, such as police, fire protection, rescue and the like, and is used for helping a user to know on-site conditions in real time and make corresponding decisions.
However, in an actual application scene, when the vehicles exist in a scene with larger traffic, the image transmission machine among the vehicles is easy to have a situation of high transmission delay and failure of data transmission among the vehicles.
Disclosure of Invention
The invention mainly aims to provide a transmission path planning method, a transmission path planning device, a transmission path planning system and a transmission path planning medium, and aims to solve the technical problem that data transmission between vehicles is failed due to high transmission delay in the data transmission process of the vehicles.
In order to achieve the above object, the present invention provides a transmission path planning method, which is applied to a vehicle, the transmission path planning method including the steps of:
acquiring running state information, and acquiring transmission path information between the vehicle and other vehicles based on the running state information;
inputting the transmission path information into a confidence evaluation network model, and outputting to obtain transmission confidence;
and determining a target transmission path according to the transmission confidence and the transmission purpose.
Optionally, before the step of acquiring the driving state information, the transmission path planning method further includes:
acquiring a preset training set, wherein the preset training set comprises a history transmission path and a history transmission confidence corresponding to the history transmission path;
training a preset neural network by using the preset training set until the target loss value in the preset neural network is smaller than the preset loss value, and obtaining the confidence evaluation network model.
Optionally, the step of training the preset neural network by using the preset training set includes:
inputting the historical transmission path and the historical transmission confidence into a backbone neural network of the preset neural network to obtain high-level characteristics;
inputting the high-level features, the historical transmission paths and the historical transmission confidence into a confidence query module of the preset neural network to obtain confidence feature data of the historical transmission confidence;
inputting the confidence coefficient characteristic data into a confidence coefficient regression head of the preset neural network to obtain preset confidence coefficient information, and determining the target loss value based on the confidence coefficient characteristic data and the preset confidence coefficient information.
Optionally, the step of acquiring the driving state information, acquiring transmission path information between the vehicle and other vehicles based on the driving state information includes:
acquiring self-running state information and other running state information of other vehicles, and determining self-running paths and other running paths of other vehicles based on the running state information and the other running state information;
and acquiring path distances between the path points on the self-running path and the path points on other running paths at the same moment, and determining the transmission path information based on the transmission path corresponding to the path distance and the moment to which the transmission path belongs when the path distance is determined to be smaller than a preset transmission distance.
Optionally, the step of inputting the transmission path information into a confidence evaluation network model and outputting to obtain the transmission confidence includes:
and inputting the transmission path information into the confidence evaluation network model, and outputting the transmission confidence of each transmission path at the corresponding moment.
Optionally, in the case that the transmission destination is a divergent transmission, the step of determining a target transmission path according to the transmission confidence and the transmission destination includes:
determining a corresponding transmission path to be confirmed in the transmission path information according to a path point of the self-running path at the current moment;
and selecting the transmission path to be confirmed with the highest transmission confidence from the transmission paths to be confirmed, and determining the transmission path to be confirmed as the target transmission path.
Optionally, in the case that the transmission destination is a directional transmission, the step of determining a target transmission path according to the transmission confidence and the transmission destination includes:
determining other travel paths of any path point in the transmission path information as to-be-confirmed transmission paths of the path points on the travel path of the target vehicle for directional transmission;
and selecting the transmission path to be confirmed with the highest transmission confidence from the transmission paths to be confirmed, and determining the transmission path to be confirmed as the target transmission path of the target vehicle.
The invention also provides a transmission path planning device, which comprises:
the information acquisition module is used for acquiring running state information and acquiring transmission path information between the vehicle and other vehicles based on the running state information;
the information prediction module is used for inputting the transmission path information into a confidence evaluation network model and outputting to obtain transmission confidence;
and the path determining module is used for determining a target transmission path according to the transmission confidence and the transmission purpose.
In addition, in order to achieve the above object, the present invention also provides a transmission path planning system including a memory, a processor, and a computer processing program stored on the memory and executable on the processor, which when executed by the processor, implements the steps of the transmission path planning method as described above.
In addition, in order to achieve the above object, the present invention also provides a computer-readable storage medium having stored thereon a computer processing program which, when executed by a processor, implements the steps of the transmission path planning method as described above.
The invention provides a transmission path planning method, a device, a system and a medium, which are used for acquiring transmission path information between vehicles and other vehicles based on running state information by acquiring the running state information, determining a transmission path with higher data transmission success rate between the vehicles according to the vehicles needing to carry out data transmission and the transmission path information of the vehicles needing to carry out data reception, playing a role in reducing time delay to a certain extent, inputting the transmission path information into a confidence evaluation network model, outputting to obtain transmission confidence, helping the vehicles to make efficient transmission decisions, improving the transmission performance of the vehicles, determining a target transmission path according to the transmission confidence and the transmission purpose, improving the pertinence and the efficiency of data transmission, and greatly reducing the transmission time delay on the basis of ensuring the transmission success rate.
Drawings
FIG. 1 is a schematic diagram of a terminal structure of a hardware operating environment according to an embodiment of the present invention;
fig. 2 is a flowchart of a transmission path planning method according to a first embodiment of the present invention;
fig. 3 is a flowchart of a second embodiment of a transmission path planning method according to the present invention;
fig. 4 is a flowchart of a third embodiment of a transmission path planning method according to the present invention;
fig. 5 is a schematic block diagram of a transmission path planning apparatus according to the present invention.
The implementation, functional features and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
As shown in fig. 1, fig. 1 is a schematic diagram of a terminal structure of a hardware running environment according to an embodiment of the present invention.
The implementation terminal of the present invention is a transmission path planning system, as shown in fig. 1, where the transmission path planning system may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, a communication bus 1002. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1005 may be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.
Optionally, the transmission path planning system may further include an RF (Radio Frequency) circuit, a sensor, a WiFi module, and the like. Among them, sensors such as light sensor, motion sensor and others are not described herein.
Those skilled in the art will appreciate that the transmission path planning system structure shown in fig. 1 does not constitute a limitation of the transmission path planning system and may include more or fewer components than shown, or may combine certain components, or may have a different arrangement of components.
As shown in fig. 1, an operating system, a network communication module, a user interface module, and a computer processing program may be included in the memory 1005, which is a type of computer storage medium.
In the transmission path planning system shown in fig. 1, the network interface 1004 is mainly used for connecting to a background server and performing data communication with the background server; the user interface 1003 is mainly used for connecting a client (user side) and performing data communication with the client; and the processor 1001 may be configured to call a computer processing program stored in the memory 1005 and perform the following operations:
acquiring running state information, and acquiring transmission path information between the vehicle and other vehicles based on the running state information;
inputting the transmission path information into a confidence evaluation network model, and outputting to obtain transmission confidence;
and determining a target transmission path according to the transmission confidence and the transmission purpose.
Further, the processor 1001 may call a computer processing program stored in the memory 1005, and further perform the following operations:
before the step of acquiring the driving state information, acquiring a preset training set, wherein the preset training set comprises a history transmission path and a history transmission confidence degree corresponding to the history transmission path;
training a preset neural network by using the preset training set until the target loss value in the preset neural network is smaller than the preset loss value, and obtaining the confidence evaluation network model.
Further, the processor 1001 may call a computer processing program stored in the memory 1005, and further perform the following operations:
the step of training the preset neural network by using the preset training set comprises the following steps: inputting the historical transmission path and the historical transmission confidence into a backbone neural network of the preset neural network to obtain high-level characteristics;
inputting the high-level features, the historical transmission paths and the historical transmission confidence into a confidence query module of the preset neural network to obtain confidence feature data of the historical transmission confidence;
inputting the confidence coefficient characteristic data into a confidence coefficient regression head of the preset neural network to obtain preset confidence coefficient information, and determining the target loss value based on the confidence coefficient characteristic data and the preset confidence coefficient information.
Further, the processor 1001 may call a computer processing program stored in the memory 1005, and further perform the following operations:
the step of acquiring travel state information, acquiring transmission path information with other vehicles based on the travel state information, includes: acquiring self-running state information and other running state information of other vehicles, and determining self-running paths and other running paths of other vehicles based on the running state information and the other running state information;
and acquiring path distances between the path points on the self-running path and the path points on other running paths at the same moment, and determining the transmission path information based on the transmission path corresponding to the path distance and the moment to which the transmission path belongs when the path distance is determined to be smaller than a preset transmission distance.
Further, the processor 1001 may call a computer processing program stored in the memory 1005, and further perform the following operations:
inputting the transmission path information into a confidence evaluation network model, and outputting to obtain the transmission confidence, wherein the method comprises the following steps of:
and inputting the transmission path information into the confidence evaluation network model, and outputting the transmission confidence of each transmission path at the corresponding moment.
Further, the processor 1001 may call a computer processing program stored in the memory 1005, and further perform the following operations:
and determining a target transmission path according to the transmission confidence and the transmission purpose, wherein the method comprises the following steps of:
determining a corresponding transmission path to be confirmed in the transmission path information according to a path point of the self-running path at the current moment;
and selecting the transmission path to be confirmed with the highest transmission confidence from the transmission paths to be confirmed, and determining the transmission path to be confirmed as the target transmission path.
Further, the processor 1001 may call a computer processing program stored in the memory 1005, and further perform the following operations:
and determining a target transmission path according to the transmission confidence and the transmission purpose, wherein the method comprises the following steps of:
determining other travel paths of any path point in the transmission path information as to-be-confirmed transmission paths of the path points on the travel path of the target vehicle for directional transmission;
and selecting the transmission path to be confirmed with the highest transmission confidence from the transmission paths to be confirmed, and determining the transmission path to be confirmed as the target transmission path of the target vehicle.
Referring to fig. 2, in a first embodiment of the present invention, the transmission path planning method includes:
step S10, acquiring traveling state information, and acquiring transmission path information with other vehicles based on the traveling state information.
In the course of starting data transmission from a vehicle to another vehicle, it is first necessary to acquire travel state information of a vehicle to be data-transmitted (hereinafter referred to as a first vehicle) and a vehicle to be data-received (hereinafter referred to as a second vehicle), wherein the travel state information of the first vehicle is acquired from a database of the first vehicle itself, and the travel state information of the second vehicle is transmitted from the second vehicle to the first vehicle.
After the first vehicle acquires the self running state information and the running state information of the second vehicle, the first vehicle directly determines the transmission path information of the data between the first vehicle and the second vehicle according to the self running state information and the running state information of the second vehicle, and the path with low transmission efficiency is removed from the determined transmission path information, so that the efficiency of data transmission between the vehicles is improved, and the situations of high transmission delay and transmission failure in data transmission through the path with low transmission efficiency are avoided.
Optionally, before the step of acquiring the driving state information in step S10, the transmission path planning method further includes:
step S101, a preset training set is obtained, wherein the preset training set comprises a history transmission path and a history transmission confidence coefficient corresponding to the history transmission path;
and step S102, training a preset neural network by using the preset training set until the target loss value in the preset neural network is smaller than the preset loss value, so as to obtain the confidence evaluation network model.
And calculating a target loss value of the preset neural network according to the historical transmission confidence coefficient corresponding to the historical transmission path and the historical transmission path, and outputting the preset neural network as a confidence coefficient evaluation network model when the target loss value is smaller than the preset loss value.
Optionally, the step of training the preset neural network using the preset training set in step S102 includes:
and step S103, inputting the historical transmission path and the historical transmission confidence into a backbone neural network of the preset neural network to obtain high-level characteristics.
In this embodiment, a standard transducer network composed of stacked standard transducer blocks is used as a backbone neural network, and a model in the natural voice field realizes architectural unification, which is beneficial to multi-mode joint training of confidence.
In the training stage of the preset neural network, the backbone neural network receives as input a combination of the input historical transmission paths and the historical transmission confidence coefficients, and learns to obtain high-level features (i.e., confidence coefficient details) of each historical transmission confidence coefficient, specifically referring to the following formula 1:
-equation 1
Wherein H represents a high-level feature, and Backbone represents a Backbone neural network, []Representing the operation of the splicing operation,representing a history transmission path->The high-level features encode the features of each historical transmission confidence and the correlation between all the historical transmission paths and the corresponding historical transmission confidence through a self-attention mechanism, so that the consistency relationship between the correctly matched historical transmission paths and the historical transmission confidence can be maintained.
Step S104, inputting the high-level features, the historical transmission paths and the historical transmission confidence into a confidence query module of the preset neural network to obtain confidence feature data of the historical transmission confidence.
It should be noted that, the confidence query module introduced in this embodiment is only used in the training process of the preset neural network, so as to avoid bringing additional overhead to the downstream task.
Specifically, given the high-level features H of each historical transmission confidence, if a simple prediction header (one layer of MLP) is directly used to predict the confidence of the historical transmission path, it may result in a burden of extracting features unrelated to the downstream task to be given to the backbone neural network, thereby limiting the performance of the backbone neural network in the downstream task.
Therefore, in order to avoid the above situation, the present embodiment introduces a confidence query module to undertake the extraction of features related to only the borrowing task, so that the backbone neural network can focus and learn the general high-level features easy to transfer. In order to ensure the simplicity of the preset neural network, the confidence query module in the embodiment includes standard transducer modules, but the number of transducer modules is less than that of transducer modules in the backbone neural network.
Specifically, the confidence coefficient query module receives, as input, a high-level feature H output by the backbone neural network and features related to the borrowing task, that is, a history transmission path related to the borrowing task and a history transmission confidence coefficient corresponding to the history transmission path, and outputs confidence coefficient feature data for obtaining the history transmission confidence coefficient, specifically referring to the following formula 2:
-equation 2
Wherein PIM represents a location query model, Z represents confidence feature data,representing a history of the transmission paths,representing historical transmission confidence.
Step S105, inputting the confidence characteristic data into a confidence regression head of the preset neural network to obtain preset confidence information, and determining the target loss value based on the confidence characteristic data and the preset confidence information.
The top end of the preset neural network in this embodiment is a confidence coefficient regression head for predicting the confidence coefficient information of the historical transmission path through the confidence coefficient feature data, where the confidence coefficient regression head is only composed of one full-connection layer, receives the confidence coefficient feature data Z output by the confidence coefficient query module as input, and outputs the predicted confidence coefficient information of the historical transmission path, specifically referring to the following formula 3:
-equation 3
Where FC represents the confidence regression header and O represents the predictive confidence information.
And determining a target loss value of the preset neural network according to the confidence characteristic data Z and the predicted confidence information O, and taking the preset neural network as a confidence evaluation network model when the target loss value is detected to be smaller than the preset loss value.
Optionally, the step of acquiring the driving state information in step S10, acquiring the transmission path information with other vehicles based on the driving state information, includes:
step S106, acquiring self-running state information and other running state information of other vehicles, and determining self-running paths and other running paths of other vehicles based on the running state information and the other running state information.
Since the travel state information is the travel position of the vehicle at each time, the first vehicle can determine the own travel route of the first vehicle and the other travel routes of the second vehicle on the basis of the travel state information of the first vehicle and the travel state information of the second vehicle (i.e., the other vehicles).
Step S107, obtaining a path distance between a path point on the own driving path and a path point on another driving path at the same time, and determining the transmission path information based on a transmission path corresponding to the path distance and a time to which the transmission path belongs when determining that the path distance is smaller than a preset transmission distance.
Because the data is transmitted at one moment, in order to ensure that the data at one moment can be transmitted smoothly, at the moment, the path point of the self-running path of the first vehicle and the path point of the running path of the second vehicle at the same moment are acquired, the two path points are connected to form a connecting path, then the path distance of the connecting path is determined, and the transmission efficiency of the data transmission of the first vehicle based on the path distance is judged. The path distance is the connection path.
In the example, the judgment is that the path distance is compared with the preset transmission distance, if the comparison results in that the path distance is smaller than the preset transmission distance, the path distance is judged to have the characteristic of high transmission efficiency, and the path distance and the time to which the path distance belongs are determined to be transmission path information; if the comparison result shows that the path distance is larger than the preset transmission distance, the transmission efficiency of the path distance is lower, and the data transmission based on the path distance is considered to have the disadvantage of low transmission efficiency, and the path distance is deleted, so that the path distance with low transmission efficiency is removed, and the situations of large calculated amount and more invalid data in the process of transmitting the path distance with low transmission efficiency into the subsequent steps for calculating the transmission confidence are avoided.
And step S20, inputting the transmission path information into a confidence evaluation network model, and outputting to obtain the transmission confidence.
The transmission path information calculated in step S10 is input to a confidence evaluation network model for predicting transmission paths (i.e., connection paths), and the transmission confidence of each transmission path is output, thereby obtaining the reliability of data transmission on each transmission path.
Optionally, the step of inputting the transmission path information into a confidence evaluation network model in step S20 and outputting the obtained transmission confidence includes:
step S201, inputting the transmission path information into the confidence evaluation network model, and outputting the transmission confidence of each transmission path at the corresponding time.
Inputting the calculated path distance and the moment corresponding to the path distance in the transmission path information into a confidence evaluation network model, so as to obtain the transmission confidence of the data transmission of the path distance at the corresponding moment.
And step S30, determining a target transmission path according to the transmission confidence and the transmission purpose.
The target transmission path of the first vehicle for transmitting data to the second vehicle, which is selected according to the transmission confidence and the transmission purpose, is the transmission path with the highest transmission efficiency, so that the low timeliness of data transmission can be ensured to the greatest extent by transmitting data based on the determined target transmission path.
In this embodiment, the transmission path information between the vehicle and other vehicles is acquired based on the driving state information, and the transmission path information of the vehicle to be subjected to data transmission and the vehicle to be subjected to data reception is determined, so that the transmission path with higher success rate of data transmission between the vehicles is determined, the effect of reducing the time delay is achieved to a certain extent, the transmission path information is input into the confidence evaluation network model, the transmission confidence is output, the vehicle is helped to make an efficient transmission decision, the transmission performance of the vehicle is improved, the target transmission path is determined according to the transmission confidence and the transmission purpose, the pertinence and the efficiency of the data transmission are improved, and the transmission time delay can be greatly reduced on the basis of guaranteeing the transmission success rate.
Further, based on the first embodiment of the transmission path planning method of the present invention, a second embodiment of the transmission path planning method of the present invention is provided.
Referring to fig. 3, in a second embodiment of the transmission path planning method of the present invention, the step of determining the target transmission path in the step S30 according to the transmission confidence and the transmission destination includes:
step S301, determining a corresponding transmission path to be confirmed in the transmission path information according to a path point of the current time on the own running path.
Step S302, selecting a transmission path to be confirmed with highest transmission confidence from the transmission paths to be confirmed, and determining the transmission path to be confirmed as the target transmission path.
Specifically, in this embodiment, the determining a target transmission path is determined based on the transmission purpose, where the transmission purpose is to perform data transmission on each second vehicle, that is, divergent transmission, a first vehicle will include a path point on its own running path according to the current time and the path point where the current time is located in the running path in the running process, after determining the path distance with the current time as the transmission path to be confirmed in the transmission path information, directly selecting the transmission path to be confirmed with the highest transmission confidence in the transmission path to be confirmed as the target transmission path, and transmitting the output to the second vehicle corresponding to the target transmission path through the target transmission path.
Assuming that the current time is the time a, the path point of the first vehicle on the self-running path at the time a is the path point c, the path point is extracted from the transmission path information, the transmission paths to be confirmed at the time a are (c, b), (c, d) and (c, a), and the transmission paths to be confirmed with the highest transmission confidence are selected from the transmission confidence corresponding to the transmission paths (c, b), (c, d) and (c, a), and the transmission paths to be confirmed (c, b) are confirmed as target transmission paths.
The transmission path (c, b) to be confirmed is used, wherein "c" is a path point on the own travel path to which the first vehicle belongs, and "b" is a path point on the travel path to which the second vehicle belongs, and the two path points are connected to form one transmission path.
In this embodiment, by determining a corresponding transmission path to be confirmed in the transmission path information according to a path point where the current time is located on the own travel path, selecting a transmission path to be confirmed with the highest transmission confidence in each transmission path to be confirmed, and determining the transmission path to be confirmed as a target transmission path, the low time ductility of divergent transmission is achieved.
Further, based on the first embodiment of the transmission path planning method of the present invention described above, a third embodiment of the transmission path planning method of the present invention is proposed.
Referring to fig. 4, in a third embodiment of the transmission path planning method of the present invention, the step of determining the target transmission path in step S30 according to the transmission confidence and the transmission destination includes:
step S303, determining other travel paths of any one of the path points as the transmission path to be confirmed of the path point on the travel path of the target vehicle for directional transmission in the transmission path information;
step S304, selecting a transmission path to be confirmed with highest transmission confidence from the transmission paths to be confirmed, and determining the transmission path to be confirmed as the target transmission path of the target vehicle.
Specifically, in this embodiment, the determination target transmission path is determined based on the transmission destination, where the transmission destination is to perform data transmission on a specific second vehicle, that is, directional transmission, a transmission path of a path point where a travel path where any path point is located is extracted from transmission path information, where the travel path is a travel path of the specific second vehicle (that is, a target vehicle), and after the transmission path is determined as a transmission path to be confirmed, a transmission path to be confirmed with the highest transmission confidence is selected directly according to the transmission confidence corresponding to each transmission path to be confirmed, and the transmission path to be confirmed is determined as the target transmission path.
In this embodiment, the transmission path information is used to determine that the other travel path to which any one of the path points belongs is the transmission path to be confirmed of the path point on the travel path of the target vehicle for directional transmission, and the transmission path to be confirmed with the highest transmission confidence is selected from the transmission paths to be confirmed, and is determined to be the target transmission path with the target vehicle, so that the low timeliness of the directional transmission is realized.
Referring to fig. 5, the present invention provides a transmission path planning apparatus including:
an information acquisition module 10 for acquiring travel state information, based on which transmission path information with other vehicles is acquired;
the information prediction module 20 is configured to input the transmission path information into a confidence evaluation network model, and output the transmission confidence;
the path determining module 30 is configured to determine a target transmission path according to the transmission confidence and the transmission purpose.
Further, the vehicle transmission path device described above further includes:
the model training module 40 is configured to obtain a preset training set, where the preset training set includes a history transmission path and a history transmission confidence corresponding to the history transmission path;
training a preset neural network by using the preset training set until the target loss value in the preset neural network is smaller than the preset loss value, and obtaining the confidence evaluation network model.
Further, the model training module 40 is further configured to:
inputting the historical transmission path and the historical transmission confidence into a backbone neural network of the preset neural network to obtain high-level characteristics;
inputting the high-level features, the historical transmission paths and the historical transmission confidence into a confidence query module of the preset neural network to obtain confidence feature data of the historical transmission confidence;
inputting the confidence characteristic data into a confidence regression head of the preset neural network to obtain preset confidence information;
and determining the target loss value based on the confidence characteristic data and the preset confidence information.
Further, the information acquisition module 10 is further configured to:
acquiring self-running state information and other running state information of other vehicles, and determining self-running paths and other running paths of other vehicles based on the running state information and the other running state information;
and acquiring path distances between the path points on the self-running path and the path points on other running paths at the same moment, and determining the transmission path information based on the transmission path corresponding to the path distance and the moment to which the transmission path belongs when the path distance is determined to be smaller than a preset transmission distance.
Further, the information prediction module 20 is further configured to:
and inputting the transmission path information into the confidence evaluation network model, and outputting the transmission confidence of each transmission path at the corresponding moment.
Further, the path determining module 30 is further configured to:
determining a corresponding transmission path to be confirmed in the transmission path information according to a path point of the self-running path at the current moment;
and selecting the transmission path to be confirmed with the highest transmission confidence from the transmission paths to be confirmed, and determining the transmission path to be confirmed as the target transmission path.
Further, the path determining module 30 is further configured to:
determining other travel paths of any path point in the transmission path information as to-be-confirmed transmission paths of the path points on the travel path of the target vehicle for directional transmission;
and selecting the transmission path to be confirmed with the highest transmission confidence from the transmission paths to be confirmed, and determining the transmission path to be confirmed as the target transmission path of the target vehicle.
The invention also provides a transmission path planning system which comprises a memory, a processor and a computer processing program stored in the memory and capable of running on the processor, wherein the computer processing program is executed by the processor to realize the steps of the transmission path planning method.
The present invention also proposes a computer-readable storage medium having stored thereon a computer-processing program which, when executed by a processor, implements the steps of the transmission path planning method as described above.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) as described above, comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (8)
1. A transmission path planning method, characterized in that the transmission path planning method is applied to a vehicle, the transmission path planning method comprising the steps of:
acquiring running state information, and acquiring transmission path information between the vehicle and other vehicles based on the running state information;
inputting the transmission path information into a confidence evaluation network model, and outputting to obtain transmission confidence;
determining a target transmission path according to the transmission confidence and the transmission purpose;
before the step of acquiring the driving state information, the transmission path planning method further includes:
acquiring a preset training set, wherein the preset training set comprises a history transmission path and a history transmission confidence corresponding to the history transmission path;
training a preset neural network by using the preset training set until a target loss value in the preset neural network is smaller than a preset loss value, so as to obtain the confidence evaluation network model;
the step of training the preset neural network by using the preset training set includes:
inputting the historical transmission path and the historical transmission confidence into a backbone neural network of the preset neural network to obtain high-level characteristics;
inputting the high-level features, the historical transmission paths and the historical transmission confidence into a confidence query module of the preset neural network to obtain confidence feature data of the historical transmission confidence;
inputting the confidence coefficient characteristic data into a confidence coefficient regression head of the preset neural network to obtain preset confidence coefficient information, and determining the target loss value based on the confidence coefficient characteristic data and the preset confidence coefficient information.
2. The transmission path planning method according to claim 1, wherein the step of acquiring travel state information, acquiring transmission path information with other vehicles based on the travel state information, comprises:
acquiring self-running state information and other running state information of other vehicles, and determining self-running paths and other running paths of other vehicles based on the running state information and the other running state information;
and acquiring path distances between the path points on the self-running path and the path points on other running paths at the same moment, and determining the transmission path information based on the transmission path corresponding to the path distance and the moment to which the transmission path belongs when the path distance is determined to be smaller than a preset transmission distance.
3. The transmission path planning method according to claim 2, wherein the step of inputting the transmission path information into a confidence evaluation network model and outputting the obtained transmission confidence comprises:
and inputting the transmission path information into the confidence evaluation network model, and outputting the transmission confidence of each transmission path at the corresponding moment.
4. The transmission path planning method according to claim 3, wherein in the case where the transmission destination is a divergent transmission, the step of determining a target transmission path based on the transmission confidence and the transmission destination comprises:
determining a corresponding transmission path to be confirmed in the transmission path information according to a path point of the self-running path at the current moment;
and selecting the transmission path to be confirmed with the highest transmission confidence from the transmission paths to be confirmed, and determining the transmission path to be confirmed as the target transmission path.
5. The transmission path planning method according to claim 3, wherein in the case where the transmission destination is a directional transmission, the step of determining a target transmission path based on the transmission confidence and the transmission destination comprises:
determining other travel paths of any path point in the transmission path information as to-be-confirmed transmission paths of the path points on the travel path of the target vehicle for directional transmission;
and selecting the transmission path to be confirmed with the highest transmission confidence from the transmission paths to be confirmed, and determining the transmission path to be confirmed as the target transmission path of the target vehicle.
6. A transmission path planning apparatus, characterized by comprising:
the information acquisition module is used for acquiring running state information and acquiring transmission path information between the vehicle and other vehicles based on the running state information;
the information prediction module is used for inputting the transmission path information into a confidence evaluation network model and outputting to obtain transmission confidence;
the path determining module is used for determining a target transmission path according to the transmission confidence and the transmission purpose;
the transmission path planning apparatus further includes:
the model training module is used for acquiring a preset training set, wherein the preset training set comprises a history transmission path and a history transmission confidence coefficient corresponding to the history transmission path;
training a preset neural network by using the preset training set until a target loss value in the preset neural network is smaller than a preset loss value, so as to obtain the confidence evaluation network model;
the model training module is further used for inputting the historical transmission path and the historical transmission confidence into a backbone neural network of the preset neural network to obtain high-level characteristics;
inputting the high-level features, the historical transmission paths and the historical transmission confidence into a confidence query module of the preset neural network to obtain confidence feature data of the historical transmission confidence;
inputting the confidence characteristic data into a confidence regression head of the preset neural network to obtain preset confidence information;
and determining the target loss value based on the confidence characteristic data and the preset confidence information.
7. A transmission path planning system comprising a memory, a processor and a computer processing program stored on the memory and executable on the processor, the computer processing program when executed by the processor implementing the steps of the transmission path planning method according to any one of claims 1 to 5.
8. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer-processing program which, when executed by a processor, implements the steps of the transmission path planning method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410051851.2A CN117579535B (en) | 2024-01-15 | 2024-01-15 | Transmission path planning method, device, system and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410051851.2A CN117579535B (en) | 2024-01-15 | 2024-01-15 | Transmission path planning method, device, system and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117579535A CN117579535A (en) | 2024-02-20 |
| CN117579535B true CN117579535B (en) | 2024-04-09 |
Family
ID=89864615
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410051851.2A Active CN117579535B (en) | 2024-01-15 | 2024-01-15 | Transmission path planning method, device, system and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117579535B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102916889A (en) * | 2012-09-29 | 2013-02-06 | 西安电子科技大学 | Instant route selection based on multi-path communication time and credibility in VANET (Vehicular Ad-Hoc Network) |
| CN103596238A (en) * | 2012-08-14 | 2014-02-19 | 广州联瑞数码科技有限公司 | A route calculating method and apparatus for a V2V communication network |
| CN105722176A (en) * | 2016-01-29 | 2016-06-29 | 同济大学 | Connection method of Internet of Vehicles massive heterogeneous network with infrastructure in city scene |
| CN106535282A (en) * | 2016-12-19 | 2017-03-22 | 南通大学 | QoS sensing routing protocol based on genetic algorithm in vehicular ad-hoc Network |
| CN108597246A (en) * | 2017-12-11 | 2018-09-28 | 武汉大学 | A method of Path selection real time problems are solved to avoid local congestion |
| CN110493749A (en) * | 2019-08-02 | 2019-11-22 | 重庆邮电大学 | A kind of car networking greedy routing method based on track search |
| WO2020094534A1 (en) * | 2018-11-06 | 2020-05-14 | Robert Bosch Gmbh | Method for training an artificial neural network, artificial neural network, use of an artificial neural network, corresponding computer program, machine-readable storage medium and corresponding device |
| CN111683351A (en) * | 2020-06-09 | 2020-09-18 | 重庆邮电大学 | Three-dimensional vehicle-mounted self-organizing network routing method based on packet receiving probability |
| CN113497761A (en) * | 2020-03-20 | 2021-10-12 | 罗伯特·博世有限公司 | Vehicle-mounted device, communication system and data transmission method |
| CN113747400A (en) * | 2021-07-28 | 2021-12-03 | 东风柳州汽车有限公司 | Vehicle-to-vehicle communication transmission optimization method, device, equipment and storage medium |
| KR20230046968A (en) * | 2021-09-30 | 2023-04-06 | 한국전자통신연구원 | Method and apparatus for routing of vehicles through mobile wireless network |
| CN116112892A (en) * | 2021-11-10 | 2023-05-12 | 中国移动通信集团江苏有限公司 | Data transmission method and device for vehicle ad hoc network |
| CN116847428A (en) * | 2023-07-20 | 2023-10-03 | 东风柳州汽车有限公司 | Data transmission path adjustment method, device, storage medium and apparatus |
-
2024
- 2024-01-15 CN CN202410051851.2A patent/CN117579535B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103596238A (en) * | 2012-08-14 | 2014-02-19 | 广州联瑞数码科技有限公司 | A route calculating method and apparatus for a V2V communication network |
| CN102916889A (en) * | 2012-09-29 | 2013-02-06 | 西安电子科技大学 | Instant route selection based on multi-path communication time and credibility in VANET (Vehicular Ad-Hoc Network) |
| CN105722176A (en) * | 2016-01-29 | 2016-06-29 | 同济大学 | Connection method of Internet of Vehicles massive heterogeneous network with infrastructure in city scene |
| CN106535282A (en) * | 2016-12-19 | 2017-03-22 | 南通大学 | QoS sensing routing protocol based on genetic algorithm in vehicular ad-hoc Network |
| CN108597246A (en) * | 2017-12-11 | 2018-09-28 | 武汉大学 | A method of Path selection real time problems are solved to avoid local congestion |
| WO2020094534A1 (en) * | 2018-11-06 | 2020-05-14 | Robert Bosch Gmbh | Method for training an artificial neural network, artificial neural network, use of an artificial neural network, corresponding computer program, machine-readable storage medium and corresponding device |
| CN110493749A (en) * | 2019-08-02 | 2019-11-22 | 重庆邮电大学 | A kind of car networking greedy routing method based on track search |
| CN113497761A (en) * | 2020-03-20 | 2021-10-12 | 罗伯特·博世有限公司 | Vehicle-mounted device, communication system and data transmission method |
| CN111683351A (en) * | 2020-06-09 | 2020-09-18 | 重庆邮电大学 | Three-dimensional vehicle-mounted self-organizing network routing method based on packet receiving probability |
| CN113747400A (en) * | 2021-07-28 | 2021-12-03 | 东风柳州汽车有限公司 | Vehicle-to-vehicle communication transmission optimization method, device, equipment and storage medium |
| KR20230046968A (en) * | 2021-09-30 | 2023-04-06 | 한국전자통신연구원 | Method and apparatus for routing of vehicles through mobile wireless network |
| CN116112892A (en) * | 2021-11-10 | 2023-05-12 | 中国移动通信集团江苏有限公司 | Data transmission method and device for vehicle ad hoc network |
| CN116847428A (en) * | 2023-07-20 | 2023-10-03 | 东风柳州汽车有限公司 | Data transmission path adjustment method, device, storage medium and apparatus |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117579535A (en) | 2024-02-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10620635B2 (en) | Moving object movement system and movement path selection method | |
| JP5027920B2 (en) | Method, apparatus and computer program for social route planner | |
| KR101772970B1 (en) | Method for providing vehicle information and terminal device applying the same | |
| US20090248292A1 (en) | Route guidance device, route guidance method, and route guidance processing program | |
| US10578446B2 (en) | Route search apparatus, route search method and computer-readable storage medium storing program | |
| CN111006678A (en) | Route search device and computer-readable storage medium | |
| CN113532459A (en) | Predictive navigation route planning method and system | |
| JP6110608B2 (en) | Route search system, portable terminal, and route guidance method | |
| CN117579535B (en) | Transmission path planning method, device, system and medium | |
| CN103471598A (en) | Method for tracing moving target and moving device for tracing moving target | |
| WO2010032282A1 (en) | Server device, mobile terminal, intersection guide system, and intersection guide method | |
| US11378412B2 (en) | Device and method for outputting navigation information, and vehicle | |
| KR20050015978A (en) | Information processing center, information processing method and infotmation providing system | |
| US9097550B2 (en) | Navigation device, server, navigation method and program | |
| JP4900316B2 (en) | Route search device | |
| CN113923775B (en) | Method, device, equipment and storage medium for evaluating quality of positioning information | |
| CN107525511B (en) | Navigation device with automatic mirroring function and automatic mirroring method using the same | |
| KR101649988B1 (en) | Apparatus and method for providing na vigation function in portable terminal | |
| JPH10267683A (en) | Navigation device | |
| JP2016156770A (en) | Route guidance system, method, and program | |
| JP3797204B2 (en) | Car navigation system | |
| JP2017181667A (en) | Voice recognition apparatus and voice recognition method | |
| JP7468315B2 (en) | SERVER DEVICE, TERMINAL DEVICE, PROGRAM, VEHICLE, AND SYSTEM OPERATION METHOD | |
| CN112197785B (en) | Travel route generation method, travel route generation device, mobile carrier, and storage medium | |
| US20230152119A1 (en) | System for guiding evacuation at a time of a disaster, method for guiding evacuation at a time of a disaster, and non-transitory computer-readable medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |