Direct connection state real-time big data judgment method

Abstract

The invention relates to a direct connection state real-time big data judgment method. Comprising the following steps: acquiring various associated data of a target automobile, various associated data of a set traffic light intersection, data of each road section corresponding to each road section between the target automobile and the set traffic light intersection, and multiple associated information of each traffic light corresponding to each road section; and intelligently judging whether the target automobile can directly pass to a set traffic light intersection at the current driving speed by green light or not based on the basic data. The direct connection state real-time big data judgment method is stable in operation and intelligent in design. The artificial intelligence model designed for the customized structure of the target automobile can be adopted, and whether the target automobile can directly pass through the set traffic light intersection at the current driving speed or not can be intelligently judged in real time according to each piece of basic data, so that valuable reference information is provided for a driving strategy of a driver of the target automobile.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of big data, and more particularly, to a straight-through state real-time big data judgment method. BACKGROUND

[0002] Big data is almost impossible to be processed by most database management systems, and must be processed by software running in parallel on tens, hundreds or even thousands of servers, such as computer clusters. The definition of big data depends on the ability of the organization holding the data set and the ability of the software it usually uses to process and analyze data. For some organizations, the first time they face a data set of hundreds of GB may make them need to rethink the options for data management. For other organizations, the data set may need to reach tens or hundreds of TB before they are disturbed.

[0003] Applying big data to the auxiliary driving of a car is a design trend selected by current car manufacturers when manufacturing cars, and is one of the selling points that can outperform other car manufacturers. However, due to the complexity of the road section and the variability of the car driving environment, the car driver cannot predict whether the car can reach the set traffic light intersection with a green light at the current speed when driving the car, that is, the car driver cannot predict that the car will stop at the first traffic light intersection in front at the current speed, which makes the car driver unable to adjust his driving strategy and further improve the intelligent level of the car, affecting the driving experience of the car driver. SUMMARY

[0004] In order to solve the technical problems in the related field, the present application provides a straight-through state real-time big data judgment method, which adopts an artificial intelligence model customized for the structure design of a target car, and intelligently judges in real time whether the target car can reach the set traffic light intersection with a green light at the current driving speed according to the various associated data of the target car, the various associated data of the set traffic light intersection, and the various road section data corresponding to each road section between the target car and the set traffic light intersection and the various associated information of the traffic lights corresponding to each road section, thereby providing valuable reference information for the driving strategy of the driver of the target car.

[0005] According to the present application, a straight-through state real-time big data judgment method is provided, which comprises: obtaining positioning data of a target car and positioning data of a set traffic light intersection, and analyzing the various road section data corresponding to each road section between the positioning data of the target car and the positioning data of the set traffic light intersection, wherein the road section data corresponding to each road section includes the length, the maximum speed limit, the current congestion identifier, the number of lanes, the average lane width, the number of intersection road sections, and the number of surrounding permanent residents of the road section. based on the current driving speed of the target automobile, the positioning data of the target automobile, the respective road segment data corresponding to each road segment between the positioning data of the target automobile and the positioning data of the set red-light intersection, the respective red light setting duration corresponding to each red-light intersection between the positioning data of the target automobile and the positioning data of the set red-light intersection, the respective current light type code, the respective current light remaining duration and the respective green light setting duration of each red light, the AI intelligent judgment model corresponding to the target automobile is used to intelligently judge whether the target automobile can pass through the set red-light intersection with a green light at the current driving speed. Among them, the AI intelligent judgment model corresponding to the target automobile outputs a pass-through identifier indicating whether the target automobile can pass through the set red-light intersection with a green light at the current driving speed. Among them, the AI intelligent judgment model corresponding to the target automobile is a Hofit neural network after multiple training operations, and the number of training operations of the Hofit neural network is monotonically positively correlated with the maximum speed of the target automobile. Among them, the positioning data of the target automobile and the positioning data of the set red-light intersection are obtained, and the respective road segment data corresponding to each road segment between the positioning data of the target automobile and the positioning data of the set red-light intersection is analyzed. The road segment data corresponding to each road segment is the length, maximum speed limit, current congestion identifier, lane number, average lane width, intersection number and surrounding resident number of the road segment, including: the surrounding resident number of each road segment is the cumulative value of the respective resident number of each resident building along the road segment.

[0006] Therefore, the present application has at least the following three beneficial technical effects: Technical effect A: According to the correlation data of the target automobile, the correlation data of the set red-light intersection, the respective road segment data corresponding to each road segment between the target automobile and the set red-light intersection, and the respective red light correlation information of each road segment, the real-time intelligent judgment of whether the target automobile can pass through the set red-light intersection with a green light at the current driving speed is provided. The driving strategy of the driver of the target automobile provides valuable reference information; Technical effect B: The AI intelligent judgment model corresponding to the target automobile is introduced to perform real-time intelligent judgment of whether the target automobile can pass through the set red-light intersection with a green light at the current driving speed. The AI intelligent judgment model corresponding to the target automobile is a Hofit neural network after multiple training operations, and the number of training operations of the Hofit neural network is monotonically positively correlated with the maximum speed of the target automobile. Technical effect C: introduce the current driving speed of the target automobile, the positioning data of the target automobile, each part of the road section data corresponding to each road section between the positioning data of the target automobile and the positioning data of the set red light intersection, each part of the red light setting duration corresponding to each red light intersection between the positioning data of the target automobile and the positioning data of the set red light intersection, each part of the current light type code, each part of the current light remaining duration and each part of the green light setting duration, for performing real-time intelligent judgment of whether the target automobile can pass through the set red light intersection with one green light at the current driving speed. The road section data corresponding to each road section is the length, maximum speed limit, current congestion identifier, lane number, average lane width, intersection road section number and surrounding resident number of the road section, so as to complete the targeted selection of each basic data for real-time intelligent judgment.

[0007] The straight-through state real-time big data judgment method of the application is stable in operation and intelligent in design. Since the artificial intelligence model customized for the target automobile can be used, according to the various associated data of the target automobile, the various associated data of the set red light intersection and the various road section data corresponding to each road section between the target automobile and the set red light intersection and the various associated information of the red light corresponding to each road section, the real-time intelligent judgment of whether the target automobile can pass through the set red light intersection with one green light at the current driving speed is performed, thereby providing valuable reference information for the driving strategy of the driver of the target automobile. DETAILED DESCRIPTION

[0008] The embodiments of the straight-through state real-time big data judgment method of the application will be described in detail below.

[0009] <Embodiment one of the application> The straight-through state real-time big data judgment method shown in embodiment one of the application specifically includes the following steps: Obtain the positioning data of the target automobile and the positioning data of the set red light intersection, analyze each part of the road section data corresponding to each road section between the positioning data of the target automobile and the positioning data of the set red light intersection, and each road section data corresponding to each road section is the length, maximum speed limit, current congestion identifier, lane number, average lane width, intersection road section number and surrounding resident number of the road section; Specifically, the positioning data of the target automobile and the positioning data of the set traffic light intersection are acquired, and each section data corresponding to each section between the positioning data of the target automobile and the positioning data of the set traffic light intersection is parsed, and the section data corresponding to each section is the length of the section, the maximum speed limit, the current congestion identifier, the number of lanes, the average lane width, the number of intersecting sections, and the number of surrounding permanent residents, including: determining each section between the positioning data of the target automobile and the positioning data of the set traffic light intersection based on the current driving route of the target automobile; Based on the current driving speed of the target automobile, the positioning data of the target automobile, the positioning data of the set traffic light intersection, the section data corresponding to each section between the positioning data of the target automobile and the positioning data of the set traffic light intersection, the red light setting duration corresponding to each traffic light intersection between the positioning data of the target automobile and the positioning data of the set traffic light intersection, the current light type code, the current light remaining duration, and the green light setting duration, the AI intelligent judgment model corresponding to the target automobile is used to intelligently judge whether the target automobile can pass through the set traffic light intersection with a green light at the current driving speed. Specifically, the traffic light device has three different light body types, red, green and yellow. Generally, the setting light duration of the yellow light is fixed, usually 2-3 seconds, while the setting light duration of the red light and the setting light duration of the green light can be adjusted. At the same time, the red light, the green light and the yellow light correspond to different light type codes respectively, and when the current light type is red light, the current light remaining duration is the remaining duration of the red light in the light state. The AI intelligent judgment model corresponding to the target automobile outputs a pass-through identifier indicating whether the target automobile can pass through the set traffic light intersection with a green light at the current driving speed. The AI intelligent judgment model corresponding to the target automobile is a Hopfield neural network after multiple training operations, and the number of training operations of the Hopfield neural network is monotonically positively correlated with the maximum speed of the target automobile. The positioning data of the target automobile and the positioning data of the set traffic light intersection are acquired, and each section data corresponding to each section between the positioning data of the target automobile and the positioning data of the set traffic light intersection is parsed, and the section data corresponding to each section is the length of the section, the maximum speed limit, the current congestion identifier, the number of lanes, the average lane width, the number of intersecting sections, and the number of surrounding permanent residents, including: the number of surrounding permanent residents of each section is the cumulative value of the number of permanent residents corresponding to each resident building along the section. The AI intelligent judgment model corresponding to the target automobile is a Hopfield neural network after multiple training operations, and the number of training operations of the Hopfield neural network is monotonously positively correlated with the highest speed of the target automobile, including: using a number conversion formula to represent the numerical conversion relationship between the number of training operations of the Hopfield neural network and the monotonous positive correlation of the highest speed of the target automobile. And the numerical conversion relationship between the number of training operations of the Hopfield neural network and the monotonous positive correlation of the highest speed of the target automobile includes: the highest speed of the target automobile is the input value of the number conversion formula, and the number of training operations of the Hopfield neural network corresponding to the monotonous positive correlation of the highest speed of the target automobile is the output value of the number conversion formula.

[0010] <Embodiment two of the application> Compared with the first embodiment of the application, the straight-through state real-time big data judgment method according to the second embodiment of the application further includes the following steps: Receiving the AI intelligent judgment model corresponding to the target automobile, and completing the model storage of the AI intelligent judgment model corresponding to the target automobile by storing the model parameters of the AI intelligent judgment model corresponding to the target automobile; Specifically, receiving the AI intelligent judgment model corresponding to the target automobile, and completing the model storage of the AI intelligent judgment model corresponding to the target automobile by storing the model parameters of the AI intelligent judgment model corresponding to the target automobile includes: selecting an MMC storage chip for receiving the AI intelligent judgment model corresponding to the target automobile, and completing the model storage of the AI intelligent judgment model corresponding to the target automobile by storing the model parameters of the AI intelligent judgment model corresponding to the target automobile.

[0011] <Embodiment three of the application> Compared with the first embodiment of the application, the straight-through state real-time big data judgment method according to the third embodiment of the application further includes the following steps: Receiving the straight-through identifier indicating whether the target automobile can pass through the set traffic light intersection with green light at the current driving speed, and wirelessly transmitting the straight-through identifier indicating whether the target automobile can pass through the set traffic light intersection with green light at the current driving speed to the remote automobile operation management server through the mobile communication network.

[0012] Next, the specific steps of the straight-through state real-time big data judgment method of the application will be further described.

[0013] In the straight-through state real-time big data judgment method according to any embodiment of the application: The AI intelligent judgment model corresponding to the target automobile is used to intelligently judge whether the target automobile can pass through the set traffic light intersection with a green light at the current driving speed, and the method comprises the following steps: inputting the current driving speed of the target automobile, the positioning data of the target automobile, the positioning data of each road section corresponding to each road section between the positioning data of the target automobile and the positioning data of the set traffic light intersection, the positioning data of the target automobile and the positioning data of the set traffic light intersection, the red light set duration corresponding to each traffic light intersection between the positioning data of the target automobile and the positioning data of the set traffic light intersection, the current light type code, the current light remaining duration and the green light set duration of each traffic light intersection between the positioning data of the target automobile and the positioning data of the set traffic light intersection into the AI intelligent judgment model corresponding to the target automobile in parallel to start the operation of the AI intelligent judgment model corresponding to the target automobile. And wherein the current driving speed of the target automobile, the positioning data of the target automobile, the positioning data of each road section corresponding to each road section between the positioning data of the target automobile and the positioning data of the set traffic light intersection, the positioning data of the target automobile and the positioning data of the set traffic light intersection, the red light set duration corresponding to each traffic light intersection between the positioning data of the target automobile and the positioning data of the set traffic light intersection, the current light type code, the current light remaining duration and the green light set duration of each traffic light intersection between the positioning data of the target automobile and the positioning data of the set traffic light intersection are input into the AI intelligent judgment model corresponding to the target automobile in parallel to start the operation of the AI intelligent judgment model corresponding to the target automobile.

[0014] And in the real-time big data judgment method of the straight-through state according to any embodiment of the application: The positioning data of the target automobile and the positioning data of the set traffic light intersection are acquired, and each road section data corresponding to each road section between the positioning data of the target automobile and the positioning data of the set traffic light intersection is parsed, and the road section data corresponding to each road section is the length, the maximum speed limit, the current congestion identifier, the number of lanes, the average lane width, the number of intersecting road sections, and the number of surrounding permanent residents, and further comprising: for each road section, when the current congestion identifier of the road section adopts a binary numerical value representation of the road section corresponding road section number and a 0B00 connection mode, it indicates that the road section is a congested road section. The positioning data of the target automobile and the positioning data of the set traffic light intersection are acquired, and each road section data corresponding to each road section between the positioning data of the target automobile and the positioning data of the set traffic light intersection is parsed, and the road section data corresponding to each road section is the length, the maximum speed limit, the current congestion identifier, the number of lanes, the average lane width, the number of intersecting road sections, and the number of surrounding permanent residents, and further comprising: for each road section, when the current congestion identifier of the road section adopts a binary numerical value representation of the road section corresponding road section number and a 0B10 connection mode, it indicates that the road section is a smooth road section. The positioning data of the target automobile and the positioning data of the set traffic light intersection are acquired, and each road section data corresponding to each road section between the positioning data of the target automobile and the positioning data of the set traffic light intersection is parsed, and the road section data corresponding to each road section is the length, the maximum speed limit, the current congestion identifier, the number of lanes, the average lane width, the number of intersecting road sections, and the number of surrounding permanent residents, and further comprising: the positioning data of the target automobile and the positioning data of the set traffic light intersection are respectively represented by numerical values in a Beidou positioning mode.

[0015] In addition, in the straight-through state real-time big data judgment method, the positioning data of the target automobile and the positioning data of the set traffic light intersection are acquired, and each road section data corresponding to each road section between the positioning data of the target automobile and the positioning data of the set traffic light intersection is parsed, and the road section data corresponding to each road section is the length, the maximum speed limit, the current congestion identifier, the number of lanes, the average lane width, the number of intersecting road sections, and the number of surrounding permanent residents, and further comprising: when the average value of each vehicle speed corresponding to each vehicle in a certain road section is less than or equal to a set speed threshold, the road section is judged to be a congested road section.

[0016] Those skilled in the art will appreciate that various modifications and changes can be made without departing from the scope and spirit of the application. It is therefore intended that the foregoing description be illustrative only, not limiting. Since the scope of the application is defined by the claims and equivalents thereof rather than by the description of the specification, any change and modification falling within the scope and boundary of the claims or equivalents of these ranges and boundaries is subject to the claims.

Claims

1. A method for judging real-time big data in a pass-through state, characterized in that, The method comprises: acquiring positioning data of a target automobile and positioning data of a set traffic light intersection, analyzing each section data corresponding to each section between the positioning data of the target automobile and the positioning data of the set traffic light intersection, and each section data corresponding to each section being length, maximum speed limit, current congestion identifier, number of lanes, average lane width, number of intersecting sections, and number of surrounding permanent residents; based on the current driving speed of the target automobile, the positioning data of the target automobile, each section data corresponding to each section between the positioning data of the target automobile and the positioning data of the set traffic light intersection, each red light setting duration corresponding to each traffic light intersection between the positioning data of the target automobile and the positioning data of the set traffic light intersection, each current light type code, each current light remaining duration, and each green light setting duration, using an AI intelligent judgment model corresponding to the target automobile to intelligently judge whether the target automobile can pass through the set traffic light intersection with a green light at the current driving speed; wherein the AI intelligent judgment model corresponding to the target automobile outputs a pass-through identifier indicating whether the target automobile can pass through the set traffic light intersection with a green light at the current driving speed; wherein the AI intelligent judgment model corresponding to the target automobile is a Hopfield neural network after multiple training operations, and the number of training operations of the Hopfield neural network is monotonically positively correlated with the maximum speed of the target automobile; wherein acquiring the positioning data of the target automobile and the positioning data of the set traffic light intersection, analyzing each section data corresponding to each section between the positioning data of the target automobile and the positioning data of the set traffic light intersection, and each section data corresponding to each section being length, maximum speed limit, current congestion identifier, number of lanes, average lane width, number of intersecting sections, and number of surrounding permanent residents comprises: the number of surrounding permanent residents of each section is the cumulative value of each permanent resident number corresponding to each resident building along the section.

2. The real-time big data judgment method of the pass-through state according to claim 1, wherein: the AI intelligent judgment model corresponding to the target automobile is a Hopfield neural network after multiple training operations, and the number of training operations of the Hopfield neural network is monotonically positively correlated with the maximum speed of the target automobile comprises: using a number transformation formula to represent the numerical transformation relationship between the number of training operations of the Hopfield neural network and the maximum speed of the target automobile; wherein using a number transformation formula to represent the numerical transformation relationship between the number of training operations of the Hopfield neural network and the maximum speed of the target automobile comprises: the maximum speed of the target automobile is the input value of the number transformation formula, and the number of training operations of the Hopfield neural network monotonically positively correlated with the maximum speed of the target automobile is the output value of the number transformation formula.

3. The pass-through state real-time big data determination method of claim 2, wherein, The method further comprises: receiving the AI intelligent judgment model corresponding to the target automobile, and completing model storage of the AI intelligent judgment model corresponding to the target automobile by storing each model parameter of the AI intelligent judgment model corresponding to the target automobile.

4. The pass-through state real-time big data determination method of claim 2, wherein, The method further comprises: receiving a straight-through identifier indicating whether the target automobile can straight-through to the set traffic light intersection with the current driving speed, and transmitting the straight-through identifier indicating whether the target automobile can straight-through to the set traffic light intersection with the current driving speed to the remote automobile operation management server through the mobile communication network.

5. The straight-through state real-time big data judgment method according to any one of claims 2-4, characterized in that: the AI intelligent judgment model corresponding to the target automobile is used to intelligently judge whether the target automobile can straight-through to the set traffic light intersection with the current driving speed based on the current driving speed of the target automobile, the positioning data of the target automobile, the road section data corresponding to each road section between the positioning data of the target automobile and the positioning data of the set traffic light intersection, the red light setting duration corresponding to each traffic light intersection between the positioning data of the target automobile and the positioning data of the set traffic light intersection, the current light type code, the current light remaining duration, and the green light setting duration, which comprises: inputting the current driving speed of the target automobile, the positioning data of the target automobile, the road section data corresponding to each road section between the positioning data of the target automobile and the positioning data of the set traffic light intersection, the red light setting duration corresponding to each traffic light intersection between the positioning data of the target automobile and the positioning data of the set traffic light intersection, the current light type code, the current light remaining duration, and the green light setting duration to the AI intelligent judgment model corresponding to the target automobile in parallel, so as to start the operation of the AI intelligent judgment model corresponding to the target automobile.

6. The straight-through state real-time big data judgment method according to claim 5, characterized in that: the inputting the current driving speed of the target automobile, the positioning data of the target automobile, the road section data corresponding to each road section between the positioning data of the target automobile and the positioning data of the set traffic light intersection, the red light setting duration corresponding to each traffic light intersection between the positioning data of the target automobile and the positioning data of the set traffic light intersection, the current light type code, the current light remaining duration, and the green light setting duration to the AI intelligent judgment model corresponding to the target automobile in parallel, so as to start the operation of the AI intelligent judgment model corresponding to the target automobile, comprises: using a programmable logic device to input the current driving speed of the target automobile, the positioning data of the target automobile, the road section data corresponding to each road section between the positioning data of the target automobile and the positioning data of the set traffic light intersection, the red light setting duration corresponding to each traffic light intersection between the positioning data of the target automobile and the positioning data of the set traffic light intersection, the current light type code, the current light remaining duration, and the green light setting duration to the AI intelligent judgment model corresponding to the target automobile in parallel, so as to start the operation of the AI intelligent judgment model corresponding to the target automobile.

7. The straight-through state real-time big data judgment method according to any one of claims 2-4, characterized in that: The positioning data of the target automobile and the positioning data of the set traffic light intersection are acquired, and each road section data corresponding to each road section between the positioning data of the target automobile and the positioning data of the set traffic light intersection is parsed, and the road section data corresponding to each road section is the length, the maximum speed limit, the current congestion identifier, the number of lanes, the average lane width, the number of intersecting road sections, and the number of surrounding permanent residents, and further comprising: for each road section, when the current congestion identifier of the road section adopts a mode of connecting the binary value of the road section number corresponding to the road section with 0B00, it indicates that the road section is a congested road section.

8. The method of claim 7, wherein: The positioning data of the target automobile and the positioning data of the set traffic light intersection are acquired, and each road section data corresponding to each road section between the positioning data of the target automobile and the positioning data of the set traffic light intersection is parsed, and the road section data corresponding to each road section is the length, the maximum speed limit, the current congestion identifier, the number of lanes, the average lane width, the number of intersecting road sections, and the number of surrounding permanent residents, and further comprising: for each road section, when the current congestion identifier of the road section adopts a mode of connecting the binary value of the road section number corresponding to the road section with 0B10, it indicates that the road section is a smooth road section.

9. The method of claim 8, wherein: The positioning data of the target automobile and the positioning data of the set traffic light intersection are acquired, and each road section data corresponding to each road section between the positioning data of the target automobile and the positioning data of the set traffic light intersection is parsed, and the road section data corresponding to each road section is the length, the maximum speed limit, the current congestion identifier, the number of lanes, the average lane width, the number of intersecting road sections, and the number of surrounding permanent residents, and further comprising: the positioning data of the target automobile and the positioning data of the set traffic light intersection are respectively represented by the Beidou positioning mode.