Congestion influence analysis method applying cloud computing

Abstract

The invention relates to a congestion impact analysis method applying cloud computing. The method comprises the following steps: analyzing an AI impact analysis model at a cloud computing network element end; an AI influence analysis model is adopted at a cloud computing network element end; according to various related road section information of the congestion road section in front of the target vehicle, the target vehicle is determined; and intelligently analyzing whether the congested road section in front of the target vehicle can cause the speed reduction of the target vehicle or not according to the current vehicle data of the target vehicle and the estimated arrival time of the target vehicle reaching the congested road section in front of the target vehicle at the driving speed of the current time. According to the invention, the AI influence analysis model can be adopted to carry out targeted intelligent analysis on whether the congestion road section in front of the target vehicle can cause the speed reduction of the target vehicle or not according to multiple basic data, so that valuable reference information is provided for the driver of the target vehicle to influence the congestion road section in front on the vehicle; the driver of the target vehicle can conveniently formulate a corresponding driving strategy, and the driver of the target vehicle is prevented from being anxious.

Description

Technical Field

[0001] This invention relates to the field of cloud computing, and more particularly to a method for analyzing the congestion impact of cloud computing. Background Technology

[0002] Cloud computing is not a completely new network technology, but rather a new concept of network application. The core concept of cloud computing is to provide fast and secure cloud computing services and data storage on websites, centered around the internet, allowing everyone who uses the internet to access the vast computing resources and data centers on the network. The fundamental meaning of cloud computing remains consistent: it possesses strong scalability and demand, providing users with a completely new experience. The core of cloud computing is the ability to coordinate numerous computing resources, thus enabling users to access virtually unlimited resources through the network, without time or space limitations.

[0003] Cloud computing has a wide range of applications, and there are many sub-application areas that need to be expanded. For example, when drivers encounter a congested road ahead, they are always anxious about whether the congestion will affect their future travel. Generally speaking, they are anxious about whether it will cause their vehicle to slow down. Obviously, there is a lack of mature analysis solutions in the current technology, which makes it impossible for drivers to decide whether they need to change their driving strategy based on the analysis results. Summary of the Invention

[0004] To address technical issues in related fields, this invention provides a congestion impact analysis method using cloud computing. By employing a customized AI impact analysis model based on a comprehensive selection of multiple fundamental data, it performs targeted intelligent analysis on whether a congested road section ahead will cause the target vehicle to slow down. This provides valuable reference information for the driver of the target vehicle regarding the impact of the congested road section ahead, facilitating the driver to formulate appropriate driving strategies and preventing the driver from experiencing anxiety.

[0005] According to the present invention, a method for congestion impact analysis using cloud computing is provided, the method comprising: The cloud computing network element collects various road segment information of the congested road segment ahead of the target vehicle. The various road segment information of the congested road segment ahead of the target vehicle includes the total number of congested vehicles, the area of ​​congested road surface, the length of congested road segment, and the vehicle speed of each historical time segment. Each historical time segment ends at the current time and the duration of each time segment is the same. The target vehicle's current speed, the length of the congested road section ahead of the target vehicle at the current time, and the average speed of each vehicle between the target vehicle's location and the congested road section ahead of the target vehicle are captured at the cloud computing network element terminal as various current vehicle data of the target vehicle. The BP neural network is trained multiple times at the cloud computing network element to obtain the BP neural network after multiple training actions. The BP neural network after multiple training actions is used as the output of the AI ​​impact analysis model. The number of training actions performed by the BP neural network is monotonically positively correlated with the road length of the congested road segment in front of the target vehicle at the current time. At the cloud computing network element level, an AI impact analysis model is used to intelligently analyze whether the congested road ahead will cause the target vehicle to slow down, based on various road segment information, current vehicle data, and the estimated arrival time of the target vehicle at its current speed. Among them, at the cloud computing network element end, the AI ​​impact analysis model is used to intelligently analyze whether the congested road section ahead of the target vehicle will cause the target vehicle to slow down, based on various road section related information, various current vehicle data of the target vehicle, and the estimated arrival time of the target vehicle at the congested road section ahead of the target vehicle at its current driving speed. This includes: intelligently analyzing and obtaining a speed reduction indicator indicating whether the congested road section ahead of the target vehicle will cause the target vehicle to slow down.

[0006] Therefore, it can be seen that the present invention has at least the following four important inventive points: First: At the cloud computing network element level, an AI impact analysis model is used to intelligently analyze whether the congested road ahead will cause the target vehicle to slow down, based on various road segment information, current vehicle data, and the estimated arrival time of the target vehicle at its current speed. This provides valuable reference information for the driver of the target vehicle regarding the impact of the congested road ahead, facilitating the driver to formulate corresponding driving strategies. Second: In order to perform intelligent analysis on whether the congested road section ahead of the target vehicle will cause the target vehicle to slow down, a customized AI impact analysis model is introduced. The AI ​​impact analysis model is a BP neural network after performing multiple training actions, and the number of training actions performed by the BP neural network is monotonically positively correlated with the road length of the target vehicle from the congested road section ahead of the target vehicle at the current moment. Third: In order to perform intelligent analysis on whether the congested road section ahead of the target vehicle will cause the target vehicle to slow down, a variety of comprehensive basic data are introduced. The various basic data include various road section related information of the congested road section ahead of the target vehicle, various current vehicle data of the target vehicle, and the estimated arrival time of the target vehicle at the congested road section ahead of the target vehicle at its current driving speed. Fourth: Specifically, the relevant information of the congested road segment ahead of the target vehicle includes the total number of congested vehicles, the area of ​​congested road surface, the length of congested road segment, and the vehicle speed for each historical time segment. The number of time segments selected for each historical time segment is positively correlated with the number of roads in the segment where the target vehicle is located. The current vehicle data of the target vehicle includes the vehicle's speed at the current moment, the road surface length from the congested road segment ahead of the target vehicle at the current moment, and the average speed of all vehicles between the target vehicle's location and the congested road segment ahead of the target vehicle at the current moment. Detailed Implementation

[0007] The following will provide a detailed description of embodiments of the congestion impact analysis method using cloud computing of the present invention.

[0008] <Embodiment 1 of the Invention> The congestion impact analysis method using cloud computing as shown in Embodiment 1 of the present invention specifically includes the following steps: The cloud computing network element collects various road segment information of the congested road segment ahead of the target vehicle. The various road segment information of the congested road segment ahead of the target vehicle includes the total number of congested vehicles, the area of ​​congested road surface, the length of congested road segment, and the vehicle speed of each historical time segment. Each historical time segment ends at the current time and the duration of each time segment is the same. Specifically, the relevant information of the congested road segment ahead of the target vehicle is collected at the cloud computing network element. The relevant information of the congested road segment ahead of the target vehicle includes the total number of congested vehicles, the area of ​​congested road surface, the length of congested road segment, and the vehicle speed of each historical time segment. The historical time segments are all based on the current time as the end time and the duration of each time segment is the same, including: the duration of each time segment is 15 minutes. The target vehicle's current speed, the length of the congested road section ahead of the target vehicle at the current time, and the average speed of each vehicle between the target vehicle's location and the congested road section ahead of the target vehicle are captured at the cloud computing network element terminal as various current vehicle data of the target vehicle. The BP neural network is trained multiple times at the cloud computing network element to obtain the BP neural network after multiple training actions. The BP neural network after multiple training actions is used as the output of the AI ​​impact analysis model. The number of training actions performed by the BP neural network is monotonically positively correlated with the road length of the congested road segment in front of the target vehicle at the current time. Specifically, the number of training actions executed by the BP neural network is monotonically positively correlated with the road length of the congested section in front of the target vehicle at the current moment, including: the longer the road length of the congested section in front of the target vehicle at the current moment, the more training actions the BP neural network executes. At the cloud computing network element level, an AI impact analysis model is used to intelligently analyze whether the congested road ahead will cause the target vehicle to slow down, based on various road segment information, current vehicle data, and the estimated arrival time of the target vehicle at its current speed. Among them, at the cloud computing network element end, the AI ​​impact analysis model is used to intelligently analyze whether the congested road section ahead of the target vehicle will cause the target vehicle to slow down based on various road section related information, various current vehicle data of the target vehicle, and the estimated arrival time of the target vehicle at the congested road section ahead of the target vehicle at its current driving speed. This includes: intelligently analyzing and obtaining a speed reduction indicator indicating whether the congested road section ahead of the target vehicle will cause the target vehicle to slow down. Specifically, the process involves collecting various road segment information related to the congested road segment ahead of the target vehicle at the cloud computing network element. This information includes the total number of congested vehicles, the area of ​​congested road surface, the length of congested road segment, and the vehicle speed for each historical time segment. Each historical time segment ends at the current time and has the same duration. This includes a positive correlation between the number of selected historical time segments and the number of roads in the road segment where the target vehicle is located.

[0009] <Embodiment 2 of the Invention> Compared to Embodiment 1 of the present invention, the congestion impact analysis method using cloud computing shown in Embodiment 2 of the present invention further includes the following steps: Receive a speed reduction indicator indicating whether the congested road ahead will cause the target vehicle to slow down, and wirelessly transmit the speed reduction indicator indicating whether the congested road ahead will cause the target vehicle to slow down back to the target vehicle's on-board terminal. The process of receiving a speed reduction indicator indicating whether a congested road section ahead of the target vehicle will cause the target vehicle to slow down, and wirelessly transmitting the speed reduction indicator indicating whether a congested road section ahead of the target vehicle will cause the target vehicle to slow down, includes: wirelessly transmitting the speed reduction indicator indicating whether a congested road section ahead of the target vehicle will cause the target vehicle to slow down to the target vehicle's onboard terminal based on a time-division duplex communication mechanism. Specifically, based on the time-division duplex communication mechanism, the deceleration indicator, which indicates whether the congested road section ahead of the target vehicle will cause the target vehicle to slow down, is wirelessly transmitted back to the target vehicle's on-board terminal, including the target vehicle's instrument panel and center console.

[0010] <Example 3 of the present invention> Compared to Embodiment 1 of the present invention, the congestion impact analysis method using cloud computing shown in Embodiment 3 of the present invention further includes the following steps: The system receives the target vehicle's location data wirelessly transmitted from the target vehicle's positioning device, determines the target vehicle's location based on the location data, and then determines the average speed of each vehicle between the target vehicle's location and the congested road section ahead of the target vehicle at the current moment. The process of receiving the target vehicle's location data wirelessly transmitted by the target vehicle's positioning device, determining the target vehicle's location based on the target vehicle's location data, and then determining the average driving speed of each vehicle between the target vehicle's location and the congested road section ahead of the target vehicle at the current moment includes: the target vehicle's location data being Beidou positioning data or Galileo positioning data.

[0011] Next, the specific steps of the congestion impact analysis method using cloud computing of the present invention will be further explained.

[0012] In the congestion impact analysis method of cloud computing according to any embodiment of the present invention: The BP neural network is trained multiple times at the cloud computing network element to obtain the BP neural network after multiple training actions. The BP neural network after multiple training actions is used as the output of the AI ​​impact analysis model. The number of training actions performed by the BP neural network is monotonically positively correlated with the road length of the congested road segment in front of the target vehicle at the current time. This includes: using a numerical transformation function to represent the numerical transformation relationship between the number of training actions performed by the BP neural network and the road length of the congested road segment in front of the target vehicle at the current time. Specifically, the MATLAB toolbox can be used to test and simulate the numerical transformation function implementation process; The numerical conversion relationship, in which the number of training actions performed by the BP neural network is monotonically positively correlated with the road length of the congested road segment in front of the target vehicle at the current moment, is represented by a numerical conversion function. In the numerical conversion function, the road length of the congested road segment in front of the target vehicle at the current moment is the input value of the numerical conversion function. Furthermore, the numerical conversion function used to represent the monotonically positive correlation between the number of training actions performed by the BP neural network and the road length of the congested road segment ahead of the target vehicle at the current time also includes: in the numerical conversion function, the number of training actions performed by the BP neural network that is monotonically positively correlated with the road length of the congested road segment ahead of the target vehicle at the current time is the output value of the numerical conversion function.

[0013] And in the congestion impact analysis method of cloud computing according to any embodiment of the present invention: At the cloud computing network element level, an AI impact analysis model is used to intelligently analyze whether the congested road segment ahead of the target vehicle will cause the target vehicle to slow down, based on various road segment information, current vehicle data, and the estimated arrival time of the target vehicle at its current speed. This includes inputting the various road segment information, current vehicle data, and estimated arrival time of the target vehicle at its current speed into the AI ​​impact analysis model in parallel.

[0014] Among them, the AI ​​impact analysis model used at the cloud computing network element end intelligently analyzes whether the congested road section ahead of the target vehicle will cause the target vehicle to slow down, based on various road section related information, various current vehicle data of the target vehicle, and the estimated arrival time of the target vehicle at its current speed to the congested road section ahead of the target vehicle. It also includes: running the AI ​​impact analysis model to obtain a speed reduction indicator output by the AI ​​impact analysis model indicating whether the congested road section ahead of the target vehicle will cause the target vehicle to slow down.

[0015] Furthermore, in the aforementioned congestion impact analysis method using cloud computing, the positive correlation between the number of selected historical time segments and the number of roads in the target vehicle's segment includes: using an information mapping formula to represent the information mapping relationship between the number of selected historical time segments and the number of roads in the target vehicle's segment; and in the information mapping formula, the number of roads in the target vehicle's segment is the input information, and the number of selected historical time segments positively correlated with the number of roads in the target vehicle's segment is the output information.

[0016] The congestion impact analysis method based on cloud computing of this invention addresses the technical problem in existing technologies where drivers of target vehicles experience anxiety due to their inability to predict whether ahead-facing congested road sections will affect their vehicles. By employing an AI impact analysis model, this method performs targeted intelligent analysis based on multiple fundamental data points to determine whether ahead-facing congested road sections will cause the target vehicle to slow down. This provides valuable reference information for the driver regarding the impact of ahead-facing congested road sections on their vehicle, facilitating the driver to formulate appropriate driving strategies and solving the aforementioned technical problem.

[0017] While specific embodiments of the invention have been described in detail, the breadth and scope of the invention should not be limited to the exemplary embodiments described above, but should be defined solely by the following claims and their equivalents. All modifications and alterations falling within the spirit of this invention are intended to be protected.

Claims

1. A congestion influence analysis method using cloud computing, characterized by, The method comprises: collecting, at the cloud computing network element, various road section related information of the front congested road section of the target vehicle, the various road section related information of the front congested road section of the target vehicle being various congested vehicle total amounts, various congested road surface areas, various congested road section lengths and various vehicle driving speeds corresponding to the front congested road section of the target vehicle in various historical time segments, the various historical time segments as a whole having the current time as the terminal time and each time segment having the same duration; capturing, at the cloud computing network element, the driving speed of the target vehicle at the current time, the road surface length of the front congested road section of the target vehicle at the current time and the average driving speed of each vehicle between the position of the target vehicle and the front congested road section of the target vehicle at the current time as various current vehicle data of the target vehicle; performing, at the cloud computing network element, multiple training actions on the BP neural network to obtain the BP neural network after performing the multiple training actions, and outputting the BP neural network after performing the multiple training actions as an AI influence analysis model, the number of training actions performed by the BP neural network being monotonically positively correlated with the road surface length of the front congested road section of the target vehicle at the current time; intelligently analyzing, at the cloud computing network element, whether the front congested road section of the target vehicle will cause the target vehicle to slow down according to the various road section related information of the front congested road section of the target vehicle, the various current vehicle data of the target vehicle and the estimated arrival time of the target vehicle to the front congested road section of the target vehicle at the driving speed of the target vehicle at the current time by using the AI influence analysis model; wherein intelligently analyzing, at the cloud computing network element, whether the front congested road section of the target vehicle will cause the target vehicle to slow down according to the various road section related information of the front congested road section of the target vehicle, the various current vehicle data of the target vehicle and the estimated arrival time of the target vehicle to the front congested road section of the target vehicle at the driving speed of the target vehicle at the current time by using the AI influence analysis model comprises intelligently analyzing to obtain a slowdown identifier indicating whether the front congested road section of the target vehicle will cause the target vehicle to slow down.

2. The congestion influence analysis method using cloud computing according to claim 1, wherein: collecting, at the cloud computing network element, various road section related information of the front congested road section of the target vehicle, the various road section related information of the front congested road section of the target vehicle being various congested vehicle total amounts, various congested road surface areas, various congested road section lengths and various vehicle driving speeds corresponding to the front congested road section of the target vehicle in various historical time segments, the various historical time segments as a whole having the current time as the terminal time and each time segment having the same duration comprises that the number of time segments of the selected various historical time segments is positively correlated with the number of road sections of the road section where the target vehicle is located. 3.The congestion impact analysis method using cloud computing of claim 2, wherein, The method further comprises: receiving the slowdown identifier indicating whether the front congested road section of the target vehicle will cause the target vehicle to slow down, and wirelessly returning the slowdown identifier indicating whether the front congested road section of the target vehicle will cause the target vehicle to slow down to the vehicle-mounted terminal of the target vehicle. The receiving the speed reduction identifier indicating whether the congested road section in front of the target vehicle will cause the target vehicle to reduce speed comprises: receiving the speed reduction identifier indicating whether the congested road section in front of the target vehicle will cause the target vehicle to reduce speed based on a time division duplex communication mechanism. 4.The congestion impact analysis method using cloud computing of claim 2, wherein, The method further comprises: receiving positioning data of the target vehicle wirelessly transmitted by a positioning device of the target vehicle, determining a position of the target vehicle based on the positioning data of the target vehicle, and further determining an average driving speed of each vehicle between the position of the target vehicle and the congested road section in front of the target vehicle at the current time; The receiving the positioning data of the target vehicle wirelessly transmitted by the positioning device of the target vehicle, determining the position of the target vehicle based on the positioning data of the target vehicle, and further determining the average driving speed of each vehicle between the position of the target vehicle and the congested road section in front of the target vehicle at the current time comprises: the positioning data of the target vehicle is Beidou positioning data or Galileo positioning data.

5. The congestion influence analysis method using cloud computing according to any one of claims 2-4, characterized in that: the cloud computing network element end executes a plurality of training actions on the BP neural network to obtain the BP neural network after the plurality of training actions are performed, and outputs the BP neural network after the plurality of training actions are performed as the AI influence analysis model, and the number of training actions performed by the BP neural network is monotonically positively correlated with the road length of the target vehicle from the target vehicle to the congested road section in front of the target vehicle at the current time, which comprises: using a numerical conversion function to represent the numerical conversion relationship of the monotonically positive correlation between the number of training actions performed by the BP neural network and the road length of the target vehicle from the target vehicle to the congested road section in front of the target vehicle at the current time.

6. The congestion influence analysis method using cloud computing according to claim 5, characterized in that: the numerical conversion function used to represent the numerical conversion relationship of the monotonically positive correlation between the number of training actions performed by the BP neural network and the road length of the target vehicle from the target vehicle to the congested road section in front of the target vehicle at the current time comprises: in the numerical conversion function, the road length of the target vehicle from the target vehicle to the congested road section in front of the target vehicle at the current time is the input value of the numerical conversion function.

7. The congestion influence analysis method using cloud computing according to claim 6, characterized in that: the numerical conversion function used to represent the numerical conversion relationship of the monotonically positive correlation between the number of training actions performed by the BP neural network and the road length of the target vehicle from the target vehicle to the congested road section in front of the target vehicle at the current time further comprises: in the numerical conversion function, the number of training actions performed by the BP neural network in the monotonically positive correlation with the road length of the target vehicle from the target vehicle to the congested road section in front of the target vehicle at the current time is the output value of the numerical conversion function.

8. The congestion influence analysis method using cloud computing according to any one of claims 2-4, characterized in that: The AI impact analysis model at the cloud computing network element end intelligently analyzes whether the front congestion road section of the target vehicle will cause the target vehicle to slow down according to the various road section related information of the front congestion road section of the target vehicle, the various current vehicle data of the target vehicle, and the estimated arrival time of the target vehicle reaching the front congestion road section of the target vehicle at the driving speed at the current time of the target vehicle, including: inputting the various road section related information of the front congestion road section of the target vehicle, the various current vehicle data of the target vehicle, and the estimated arrival time of the target vehicle reaching the front congestion road section of the target vehicle at the driving speed at the current time of the target vehicle into the AI impact analysis model in parallel.

9. The congestion impact analysis method using cloud computing according to claim 8, characterized in that: The AI impact analysis model at the cloud computing network element end intelligently analyzes whether the front congestion road section of the target vehicle will cause the target vehicle to slow down according to the various road section related information of the front congestion road section of the target vehicle, the various current vehicle data of the target vehicle, and the estimated arrival time of the target vehicle reaching the front congestion road section of the target vehicle at the driving speed at the current time of the target vehicle, further including: running the AI impact analysis model to obtain the slowdown identifier output by the AI impact analysis model, indicating whether the front congestion road section of the target vehicle will cause the target vehicle to slow down.