Multi-way tree link system for accurately calculating road navigation distance and navigation time
Through the multi-forktree link accurate computing system and deep neural network model, considering road congestion, weather and traffic time data, the problem of poor navigation time accuracy of existing navigation systems is solved, and the accurate and real-time adjustment of navigation time is achieved.
Patent Information
- Application Number
- CN202411179071.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-27
- Publication Date
- 2024-12-03
AI Technical Summary
The existing navigation systems lack reference to the speed of the vehicle driving on the actual road section when calculating the navigation time to reach the destination, resulting in poor navigation time accuracy.
The multi-fork-tree link precision computing system is adopted, including GPS positioning module, destination acquisition module, multi-fork-tree traversal navigation route module, navigation time calculation module, navigation route selection module and navigation time real-time adjustment module, and consider the deep neural network model Road congestion, weather and traffic time data, adjust navigation time in real time.
Accurate calculation and real-time adjustment of navigation time are realized, and the navigation time accuracy of navigation system is improved.
Smart Images

Figure CN119063752A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of big data navigation systems, and in particular, relates to a multi-branch tree link system for accurately calculating road navigation distance and navigation time. Background Art
[0002] With the rapid development of the automobile industry, we have higher requirements for the accuracy of road navigation distance and navigation time in car navigation systems.
[0003] In the Chinese authorized patent with application number CN200710124541.5, a navigation system is disclosed, including an electronic map database and a remaining time determination device, the device including: a navigation information acquisition module, used to obtain the current position of the navigation object, the remaining distance of the road section to which the current position belongs, and the length of other road sections from the current position to the destination; a state determination module, used to determine the current state of the navigation object; a remaining time calculation module, used to calculate the remaining time according to the remaining distance of the road section to which the current position belongs, the length of other road sections from the current position to the destination and the current moving speed of the navigation object when the current state of the navigation object is dynamic, and to calculate the remaining time according to the remaining distance of the road section to which the current position belongs, the length of other road sections from the current position to the destination and the road speed of each road section when the current state of the navigation object is static; when the current speed of the navigation object is not equal to the current road speed, the driving speed on each remaining road section is estimated according to the ratio of the current speed to be higher / lower than the current road speed, and the remaining time of the remaining road section is obtained by dividing the remaining distance of each road section by each driving speed; a remaining time prompt module, used to prompt the remaining time. The invention solves the problem that the remaining time to a certain place cannot be calculated quickly and effectively.
[0004] The defect of the existing patent is that although the above patent realizes the rapid and effective calculation of the remaining time to reach a certain location, the calculation of the navigation time to the destination lacks the reference to the actual vehicle speed on the road section, resulting in poor accuracy of the navigation time. Summary of the invention
[0005] Aiming at the problem that the existing navigation system lacks reference to the actual road section vehicle speed when calculating the navigation time to the destination, resulting in poor navigation time accuracy, the present invention provides a multi-branch tree link accurate calculation system for road navigation distance and navigation time.
[0006] In order to achieve the above technical objectives, the technical solution adopted by the present invention is as follows:
[0007] A multi-tree link accurate calculation system for road navigation distance and navigation time, comprising a GPS positioning module, a destination acquisition module, a multi-tree traversal navigation route module, a navigation time calculation module, a navigation route selection module and a navigation time real-time adjustment module;
[0008] GPS positioning module, used to locate the current position of the vehicle or user;
[0009] The destination collection module is used to collect the desired destination location input by the user or vehicle port;
[0010] The multi-branch tree traversal navigation route module establishes the passable path nodes from the current location to the destination location through the multi-branch tree;
[0011] Navigation time calculation module, calculates the current travel time of each path node of the multi-branch tree;
[0012] The navigation route selection module selects the shortest route by traversing the travel time of each passable path node from the current location to the destination location;
[0013] The real-time adjustment module of navigation time feeds back the road traffic interference factors between the path nodes according to the selected shortest travel path, obtains the value of the increase in navigation time caused by the corresponding interference factors through the interference factor input into the trained deep neural network model, superimposes the value of the increase in navigation time on the current travel time of each path node, and feeds back the latest total navigation time in real time.
[0014] Furthermore, interference factors include congestion data between road nodes, weather data, and travel time period data;
[0015] Congestion data are measured using variable vehicle congestion length data or congestion types;
[0016] Weather data uses rainfall to measure road slipperiness data and light intensity data between nodes;
[0017] The traffic period data is measured by the length of road congestion caused by holiday traffic and the travel time between nodes during commuting hours.
[0018] Further, the deep neural network model includes an input layer, a convolutional layer, and an output layer;
[0019] The input layer is the interference factor, the output layer is the normal travel time superimposed time value of the road section between nodes, the convolution layer is the convolution function, and different interference factors are converted into the output layer using different convolution functions.
[0020] Furthermore, if there are multiple interference factors on the road section between nodes, a single interference factor is used to output the result, and then multiple interference factors are input into a deep neural network model to train the convolution layer function to obtain the final numerical prediction of the superposition time of the output layer travel time by multiple interference factors.
[0021] Furthermore, the multi-branch tree establishes a navigable path from the current location to the destination location in the following manner:
[0022] Method 1: Set the current position as the parent node, and all nodes before the destination position except the parent node as child nodes, and the nodes between nodes are the pass path; the last child node of the multi-branch tree before reaching the destination position is also the pass path;
[0023] Method 2: Set the destination location as the parent node, and all nodes before the current location except the parent node as child nodes. The nodes between nodes are the pass paths; the path from the current location to the next child node is also a pass path.
[0024] Furthermore, the current travel time of each path node of the multi-branch tree is calculated as follows:
[0025] Split the entire multi-branch tree path into node-to-node paths;
[0026] The average speed of the node-to-node path in the current historical time period is recorded as the travel speed;
[0027] The current travel time between nodes is obtained by dividing the travel path between nodes by the travel speed.
[0028] Compared with the prior art, the present invention has the following beneficial effects:
[0029] The real-time navigation time adjustment module can be used to adjust the total navigation time from the current location to the destination in real time, so that users can use the navigation system to locate the navigation time more accurately. BRIEF DESCRIPTION OF THE DRAWINGS
[0030] Figure 1 The system structure block diagram of a system for accurately calculating road navigation distance and navigation time through a multi-branch tree link in an embodiment of the present invention. DETAILED DESCRIPTION
[0031] In order to facilitate the understanding of those skilled in the art, the present invention is further described below in conjunction with embodiments and drawings. The contents mentioned in the implementation modes are not intended to limit the present invention.
[0032] like Figure 1 As shown, this embodiment provides a multi-tree link accurate calculation of road navigation distance and navigation time system, including a GPS positioning module, a destination acquisition module, a multi-tree traversal navigation route module, a navigation time calculation module, a navigation route selection module and a navigation time real-time adjustment module;
[0033] GPS positioning module, used to locate the current position of the vehicle or user;
[0034] The destination collection module is used to collect the desired destination location input by the user or vehicle port;
[0035] The multi-branch tree traversal navigation route module establishes the passable path nodes from the current location to the destination location through the multi-branch tree;
[0036] Navigation time calculation module, calculates the current travel time of each path node of the multi-branch tree;
[0037] The navigation route selection module selects the shortest route by traversing the travel time of each passable path node from the current location to the destination location;
[0038] The real-time adjustment module of navigation time feeds back the road traffic interference factors between the path nodes according to the selected shortest travel path, obtains the value of the increase in navigation time caused by the corresponding interference factors through the interference factor input into the trained deep neural network model, superimposes the value of the increase in navigation time on the current travel time of each path node, and feeds back the latest total navigation time in real time.
[0039] Interference factors include congestion data between road nodes, weather data, and travel time data;
[0040] Congestion data is measured using variable vehicle congestion length data or congestion type; congestion types such as traffic return or diversion traffic nodes causing congestion, traffic accidents on lanes, etc., lead to different congestion types, resulting in the impact of the congestion data of this node and the next node on the travel time, that is, the specific increase in the travel time data value. The vehicle congestion length data has different values for the increase in travel time depending on the length of the congested road between the node and the next node.
[0041] Weather data uses rainfall to measure road slipperiness data and light intensity data between nodes. The road slipperiness data will affect the friction coefficient between the vehicle and the ground, which in turn affects the vehicle's driving speed on the road between the nodes. At the same time, rainfall between different nodes may also have different effects on road slipperiness data, so it is necessary to calculate the travel time by node.
[0042] The traffic period data is measured by the length of road congestion caused by holiday traffic and the travel time between nodes during rush hour. The additional time of passing through the section between nodes is calculated based on whether the current date and time period are during rush hour.
[0043] The deep neural network model includes input layer, convolution layer and output layer;
[0044] The input layer is the interference factor, the output layer is the normal travel time superimposed time value of the road section between nodes, the convolution layer is the convolution function, and different interference factors are converted into the output layer using different convolution functions.
[0045] If there are multiple interference factors on the road section between nodes, a single interference factor is used to output the result, and then multiple interference factors are input into a deep neural network model to train the convolution layer function to obtain the final numerical prediction of the superposition time of the output layer travel time by multiple interference factors.
[0046] The way a multitree establishes a navigable path from the current location to the destination location includes:
[0047] Method 1: Set the current position as the parent node, and all nodes before the destination position except the parent node as child nodes, and the nodes between nodes are the pass path; the last child node of the multi-branch tree before reaching the destination position is also the pass path;
[0048] Method 2: Set the destination location as the parent node, and all nodes before the current location except the parent node as child nodes. The nodes between nodes are the pass paths; the path from the current location to the next child node is also a pass path.
[0049] The method for calculating the current travel time of each path node of the multi-branch tree is:
[0050] Split the entire multi-branch tree path into node-to-node paths;
[0051] The average speed of the node-to-node path in the current historical time period is recorded as the travel speed;
[0052] The current travel time between nodes is obtained by dividing the travel path between nodes by the travel speed.
[0053] Compared with the prior art, the present invention has the following beneficial effects:
[0054] The real-time navigation time adjustment module can be used to adjust the total navigation time from the current location to the destination in real time, so that users can use the navigation system to locate the navigation time more accurately.
[0055] The above is a detailed introduction to a multi-tree link accurate calculation of road navigation distance and navigation time system provided by the present application. The description of the specific embodiment is only used to help understand the method and its core idea of the present application. It should be pointed out that for ordinary technicians in this technical field, without departing from the principles of the present application, several improvements and modifications can be made to the present application, and these improvements and modifications also fall within the scope of protection of the claims of the present application.
Claims
1. A multi-tree link accurate calculation system for road navigation distance and navigation time, characterized in that: It includes GPS positioning module, destination acquisition module, multi-tree traversal navigation route module, navigation time calculation module, navigation route selection module and navigation time real-time adjustment module; GPS positioning module, used to locate the current position of the vehicle or user; The destination collection module is used to collect the desired destination location input by the user or vehicle port; The multi-branch tree traversal navigation route module establishes the passable path nodes from the current location to the destination location through the multi-branch tree; Navigation time calculation module, calculates the current travel time of each path node of the multi-branch tree; The navigation route selection module selects the shortest route by traversing the travel time of each passable path node from the current location to the destination location; The real-time adjustment module of navigation time feeds back the road traffic interference factors between the path nodes according to the selected shortest travel path, obtains the value of the increase in navigation time caused by the corresponding interference factors through the interference factor input into the trained deep neural network model, superimposes the value of the increase in navigation time on the current travel time of each path node, and feeds back the latest total navigation time in real time.
2. According to claim 1, a multi-tree link accurate calculation of road navigation distance and navigation time system is characterized in that: Interference factors include congestion data between road nodes, weather data, and travel time data; Congestion data are measured using variable vehicle congestion length data or congestion types; Weather data uses rainfall to measure road slipperiness data and light intensity data between nodes; The traffic period data is measured by the length of road congestion caused by holiday traffic and the travel time between nodes during commuting hours.
3. A multi-tree link accurate calculation system for road navigation distance and navigation time according to claim 2, characterized in that: The deep neural network model includes input layer, convolution layer and output layer; The input layer is the interference factor, the output layer is the normal travel time superimposed time value of the road section between nodes, the convolution layer is the convolution function, and different interference factors are converted into the output layer using different convolution functions.
4. A multi-tree link accurate calculation system for road navigation distance and navigation time according to claim 3, characterized in that: If there are multiple interference factors on the road section between nodes, a single interference factor is used to output the result, and then multiple interference factors are input into a deep neural network model to train the convolution layer function to obtain the final numerical prediction of the superposition time of the output layer travel time by multiple interference factors.
5. A multi-tree link accurate calculation system for road navigation distance and navigation time according to claim 4, characterized in that: The way a multitree establishes a navigable path from the current location to the destination location includes: Method 1: Set the current position as the parent node, and all nodes before the destination position except the parent node as child nodes, and the nodes between nodes are the pass path; the last child node of the multi-branch tree before reaching the destination position is also the pass path; Method 2: Set the destination location as the parent node, and all nodes before the current location except the parent node as child nodes. The nodes between nodes are the pass paths; the path from the current location to the next child node is also a pass path.
6. A multi-tree link accurate calculation system for road navigation distance and navigation time according to claim 5, characterized in that: The method for calculating the current travel time of each path node of the multi-branch tree is: Split the entire multi-branch tree path into node-to-node paths; The average speed of the node-to-node path in the current historical time period is recorded as the travel speed; The current travel time between nodes is obtained by dividing the travel path between nodes by the travel speed.
