CN118195117B - Transportation route planning method and system based on artificial intelligence - Google Patents
Transportation route planning method and system based on artificial intelligence Download PDFInfo
- Publication number
- CN118195117B CN118195117B CN202410605692.6A CN202410605692A CN118195117B CN 118195117 B CN118195117 B CN 118195117B CN 202410605692 A CN202410605692 A CN 202410605692A CN 118195117 B CN118195117 B CN 118195117B
- Authority
- CN
- China
- Prior art keywords
- transportation
- route
- segmented
- task
- optimizing
- 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
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 20
- 238000012544 monitoring process Methods 0.000 claims abstract description 60
- 230000010354 integration Effects 0.000 claims abstract description 59
- 230000002452 interceptive effect Effects 0.000 claims abstract description 10
- 230000011218 segmentation Effects 0.000 claims description 40
- 238000000354 decomposition reaction Methods 0.000 claims description 12
- 238000012502 risk assessment Methods 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 8
- 230000000694 effects Effects 0.000 abstract description 5
- 230000000875 corresponding effect Effects 0.000 description 20
- 238000005457 optimization Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 239000000126 substance Substances 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 230000037361 pathway Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
- G06Q10/0835—Relationships between shipper or supplier and carriers
- G06Q10/08355—Routing methods
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Quality & Reliability (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a transportation route planning method and a transportation route planning system based on artificial intelligence, which relate to the technical field of intelligent transportation, and the method comprises the following steps: the interactive transportation route planning system receives a target transportation task; performing task analysis on the target transportation task, and decomposing the target transportation task into a plurality of segmented transportation tasks; acquiring a plurality of planning route sets corresponding to the segmented transportation tasks respectively, and outputting a plurality of groups of planning route sets; respectively monitoring a plurality of groups of planned route sets through an internet of things connection information integration device, and outputting an information integration monitoring database; and establishing a segmented route optimizing model, calling data in an information integration monitoring database to optimize a plurality of segmented transportation tasks, and outputting a plurality of segmented optimizing routes corresponding to the segmented transportation tasks. Thereby achieving the technical effects of reducing the information updating cost and improving the route planning efficiency.
Description
Technical Field
The invention relates to the technical field of intelligent transportation, in particular to a transportation route planning method and system based on artificial intelligence.
Background
The transportation route planning has wide application in a plurality of fields such as logistics, travel and the like. Particularly, vehicles carrying dangerous chemicals, if the vehicles do not have specific planning lines for mastering road information due to the specificity and dangerousness of the chemicals, the vehicles can slow down logistics processes due to the problems of line forbidden or unknown road conditions, and the transportation safety is threatened seriously. The existing route planning and speed limiting reminding function scheme is internally provided with road network information, and has the technical problems of high updating cost and poor timeliness of route planning.
Disclosure of Invention
The invention provides a transportation route planning method and system based on artificial intelligence, which are used for solving the technical problems of high updating cost and poor route planning timeliness in the prior art and realizing the technical effects of reducing the information updating cost and improving the route planning efficiency.
In a first aspect, the present invention provides a method for planning a transportation route based on artificial intelligence, wherein the method comprises:
And the interactive transportation route planning system receives the target transportation task.
And carrying out task analysis on the target transportation task, decomposing the target transportation task into a plurality of segmented transportation tasks, wherein each segmented transportation task corresponds to a starting point and a target point, and the starting point of the next segmented transportation task is the same as the target point of the previous segmented transportation task.
And acquiring the planned route sets respectively corresponding to the segmented transportation tasks, and outputting a plurality of groups of planned route sets.
And respectively monitoring the plurality of groups of planned route sets through the internet of things connection information integration device, and outputting an information integration monitoring database.
Establishing a segmented route optimizing model, calling the data in the information integration monitoring database to optimize the segmented transportation tasks by the segmented route optimizing model, and outputting a plurality of segmented optimizing routes corresponding to the segmented transportation tasks.
According to the method, the target transportation task is effectively decomposed into a plurality of segmented transportation tasks, and planning is carried out for each segmented task, so that complex transportation requirements can be flexibly met. The information integration device is connected with the Internet of things to monitor the planned route set and output the information integration monitoring database, so that real-time monitoring and data integration of the transportation task execution process are realized, and the transportation process is facilitated to be optimized. And establishing a segmented route optimizing model, calling data in an information integration monitoring database to optimize a plurality of segmented transportation tasks, and outputting a plurality of segmented optimizing routes. The optimizing model can dynamically optimize the segmented route according to real-time monitoring data and task characteristics, and improves the transportation efficiency and accuracy.
The method generally adopts an intelligent route planning idea, and can dynamically adjust the route planning according to actual conditions and monitoring data, so that the transportation process is more efficient and reliable.
In a second aspect, the present invention also provides an artificial intelligence based transportation route planning system, wherein the system comprises:
And the task acquisition module is used for receiving the target transportation task by the interactive transportation route planning system.
The analysis segmentation module is used for carrying out task analysis on the target transportation task and decomposing the target transportation task into a plurality of segmentation transportation tasks, each segmentation transportation task corresponds to a starting point and a target point, and the starting point of the next segmentation transportation task is the same as the target point of the last segmentation transportation task.
And the segment planning module is used for acquiring the planning route sets corresponding to the segmented transportation tasks respectively and outputting a plurality of groups of planning route sets.
The route monitoring module is used for respectively monitoring the plurality of groups of planned route sets through the internet of things connection information integration device and outputting an information integration monitoring database.
The optimizing selection module is used for establishing a segmented route optimizing model, the segmented route optimizing model calls data in the information integration monitoring database to optimize the segmented transportation tasks, and a plurality of segmented optimizing routes corresponding to the segmented transportation tasks are output.
The invention discloses a transportation route planning method and system based on artificial intelligence, comprising the following steps: and the interactive transportation route planning system receives the target transportation task, analyzes the task and decomposes the task into a plurality of segmented transportation tasks. Each segmented task has a start point and a target point, and the start point of an adjacent segmented task is the same as the target point. The system obtains a set of planned routes for each segment task and outputs a plurality of sets of planned routes. The routes are monitored through the internet of things connection information integration device, and the information integration monitoring database is output. The system establishes a segmented route optimizing model, optimizes the segmented tasks by using the data in the monitoring database, and obtains optimized routes of a plurality of segmented tasks. The transportation route planning method and system based on artificial intelligence solve the technical problems of high updating cost and poor timeliness of route planning, and achieve the technical effects of reducing information updating cost and improving route planning efficiency.
Drawings
FIG. 1 is a flow chart of an artificial intelligence based transportation route planning method according to the present invention.
Fig. 2 is a schematic structural diagram of an artificial intelligence-based transportation route planning system according to the present invention.
Reference numerals illustrate: the system comprises a task acquisition module 11, a parsing and segmenting module 12, a segment planning module 13, a route monitoring module 14 and a optimizing and selecting module 15.
Detailed Description
The technical scheme provided by the embodiment of the invention aims to solve the technical problems of high updating cost and poor timeliness of line planning in the prior art, and adopts the following overall thought:
First, the interactive transport route planning system receives a target transport mission. Then, the target transportation task is subjected to task analysis and is decomposed into a plurality of segmented transportation tasks, each segmented transportation task comprises a starting point and a target point, and the starting point of the subsequent segmented transportation task is identical to the target point of the previous segmented transportation task. And then, acquiring a planned route set corresponding to each segmented transportation task, and outputting a plurality of groups of planned route sets. And then, the planned route sets are monitored through the internet of things connection information integration device, and an information integration monitoring database is output. And finally, establishing a segmented route optimizing model, calling data in an information integration monitoring database to optimize the segmented transportation tasks, and outputting a plurality of segmented optimizing routes which respectively correspond to each segmented transportation task.
The foregoing aspects will be better understood by reference to the following detailed description of the invention taken in conjunction with the accompanying drawings and detailed description. It should be apparent that the described embodiments are only some embodiments of the present invention and not all embodiments of the present invention, and it should be understood that the present invention is not limited by the exemplary embodiments used only to explain the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to fall within the scope of the invention. It should be noted that, for convenience of description, only some, but not all of the drawings related to the present invention are shown.
Example 1
FIG. 1 is a flow chart of an artificial intelligence based transportation route planning method according to the present invention; wherein, include:
And the interactive transportation route planning system receives the target transportation task.
Optionally, the transportation route planning system refers to an information system for managing transportation tasks, and the transportation route planning system stores a plurality of transportation tasks therein. The target transportation task refers to a target list of dangerous chemical goods or objects to be transported, and the target list includes types, quantity, transportation containers, transportation routes, transportation time requirements and the like of dangerous goods.
Illustratively, the target transportation mission is received via a system interface of the transportation route planning system based on a given data transmission protocol. The target transportation task contains basic information required for transportation route planning.
And carrying out task analysis on the target transportation task, decomposing the target transportation task into a plurality of segmented transportation tasks, wherein each segmented transportation task corresponds to a starting point and a target point, and the starting point of the next segmented transportation task is the same as the target point of the previous segmented transportation task.
Optionally, based on task analysis of the target transportation task, the target transportation task is decomposed into smaller units, each segmented transportation task corresponds to a starting point and a target point, and the starting point of the segmented transportation task coincides with the target point of the previous segmented transportation task in geographic position.
Illustratively, task parsing and decomposition is performed, including segmentation based on segment length constraints, segmentation based on driving duration, segmentation based on path control points, and so forth. Specifically, the route is divided into a plurality of paragraphs based on the segmentation of the driving duration taking into account the driving duration limit of the driver, the driving duration of each paragraph not exceeding the limit. For example, the driving duration limit is 8 hours, and the route is divided into a plurality of segments according to the predicted driving speed and road condition, and the predicted driving duration of each segment is not more than 8 hours. In addition, path control point-based segmentation divides a route into multiple paragraphs, each of which may pass one or more control points, based on control points on the route. The control point may be a place where a stop is needed, such as a gas station, a restaurant, a rest area, etc., or a place where avoidance or priority is needed, such as a congestion section, a construction section, a scenic spot, etc.
Through the steps, the complex transportation task is decomposed into a plurality of simple subtasks, so that the complexity of the problem is reduced, the flexibility, the efficiency and the accuracy of planning are improved, and meanwhile, each section is conveniently monitored and controlled, so that the safety and the compliance of the transportation task are ensured.
In some embodiments, decomposing the target transportation task into a plurality of segmented transportation tasks includes:
and carrying out equidistant decomposition on the target transportation task to obtain K initial segmented circuits.
And acquiring the path junction node of each initial segment line in the K initial segment lines.
And carrying out complexity analysis by using the path junction node, and outputting K line complexity.
And taking the smallest variance of the K line complexity as a decomposition target, and outputting a plurality of segmented transportation tasks.
Specifically, the target transportation task is broken down into a plurality of segmented transportation tasks. Firstly, carrying out equidistant decomposition on a target transportation task to obtain K initial segmented lines. This step ensures that the length of each segmented line is approximately equal, thereby evenly distributing the transportation tasks. Then, the pathway junction node of each of the K initial segment lines is obtained. Hub nodes refer to key nodes that play a role in connection or conversion in segmented lines, including cities, transportation hubs, important intersections, and the like. Then, the complexity analysis is performed by the approach hub node, and K line complexity is output. The line complexity is related to the number, type, distribution, etc. of path junction nodes. Illustratively, the larger the scale of the route points, the larger the number of the route points, and the worse the road conditions, the higher the corresponding line complexity, the higher the line complexity, and the greater the difficulty of line planning.
Further, taking the smallest variance of K line complexity as a decomposition target, outputting a plurality of segmented transportation tasks, in other words, searching a decomposition scheme based on the K line complexity, so that the variances of the complexity values are smallest. This step may ensure that the complexity of the segmented transportation tasks is approximately equal, thereby evenly distributing the planning tasks.
By the method, the optimal decomposition of the target transportation task is realized, and the task decomposition method based on the target with minimum complexity analysis and variance ensures that the acquired multiple segmented transportation tasks have relatively balanced planning difficulty, and is convenient for parallel processing of the multiple segmented transportation tasks, so that the efficiency of subsequent optimization is facilitated.
And acquiring the planned route sets respectively corresponding to the segmented transportation tasks, and outputting a plurality of groups of planned route sets.
Alternatively, for each segmented transportation mission, there are a plurality of possible transportation routes from the start point to the end point. And obtaining a plurality of possible planned routes for each segmented transportation task, storing the possible planned routes in a correlated manner as a group of planned route sets, and correspondingly generating a plurality of groups of planned route sets for the segmented transportation tasks, so as to provide more choices for the next route selection.
Optionally, for each segmented transportation task, factors such as a starting point, an ending point, cargo characteristics, transportation time requirements, road conditions, weather and the like of each segmented transportation task, driver preferences and the like are comprehensively considered, and a plurality of possible transportation routes are generated. Illustratively, the planned route includes a shortest route, a fastest route, a most fuel efficient route, a least traffic light route, avoidance of high risk, and the like. All possible planned routes for each segmented transportation mission are then aggregated together to form a planned route set. Each set of planned routes corresponds to a segmented transportation mission.
And respectively monitoring the plurality of groups of planned route sets through the internet of things connection information integration device, and outputting an information integration monitoring database.
In some embodiments, the information integration device includes a plurality of information sensing channels for integrating a plurality of information sensing modules including at least a vehicle information sensing module, a traffic information sensing module, a climate information sensing module, and a user information sensing module.
The output end of the information integration device is in communication connection with a cloud processor, and the cloud processor is in communication connection with the transportation route planning system.
Optionally, the information integration device connected through the internet of things monitors the plurality of groups of planned route sets and outputs the information integration monitoring database. The information integration device comprises a plurality of information sensing channels, and the channels are used for integrating a plurality of information sensing modules.
Specifically, the information sensing module at least comprises a vehicle-mounted information sensing module (used for monitoring the state of a vehicle), a traffic information sensing module (used for monitoring road conditions), a climate information sensing module (used for monitoring weather conditions) and a user information sensing module (used for monitoring user preference and requirements).
Illustratively, the activation information assembly monitors each set of planned routes in real time. The monitored content comprises vehicle oil consumption, running speed, acceleration, road traffic flow, average passing speed, passing time, predicted running time, temperature, humidity, wind speed and the like.
Optionally, the monitored results are integrated together to form an information integration monitoring database. The information integration monitoring database is a database system for storing monitoring data, and real-time monitoring data and historical data of each segmented transportation task are stored in a structured mode.
Further, the output end of the information integration device is in communication connection with a cloud processor, and the cloud processor is in communication connection with a transportation route planning system. The cloud processor is a special cloud computing device with computing capability and storage capability and is used for processing and analyzing data in the information integration monitoring database. The arrangement can ensure timely transmission and processing of information, thereby improving the response speed and accuracy of the system.
Establishing a segmented route optimizing model, calling the data in the information integration monitoring database to optimize the segmented transportation tasks by the segmented route optimizing model, and outputting a plurality of segmented optimizing routes corresponding to the segmented transportation tasks.
In some embodiments, the segment route optimization model invoking data in the information integration monitoring database to optimize the plurality of segment transportation tasks comprises:
Establishing a segmented route optimizing model, wherein the segmented route optimizing model comprises a key route positioning model and a segmented balance optimizing model.
And the key route positioning model calls the data in the information integration monitoring database to identify transportation risk characteristics of the plurality of segmented transportation tasks, wherein the transportation risk characteristics comprise task delay risk characteristics, task safety risk characteristics and personnel safety risk characteristics.
And analyzing according to the task delay risk characteristics, the task safety risk characteristics and the personnel safety risk characteristics to obtain a plurality of task risk indexes.
And determining a first sectional transportation task according to the task risk indexes, wherein the first sectional transportation task is a sectional route with the task risk index larger than a preset task risk index.
And the sectional balance optimizing model carries out balance optimizing based on the first sectional transportation task and outputs a plurality of sectional optimizing routes.
Optionally, a key route positioning model and a segmentation balance optimizing model are constructed based on a convolutional neural network and combined with an optimizing algorithm, and integrated into a segmentation route optimizing model. The key route positioning model is used for determining a key route, and the key route refers to a route with the greatest influence on the completion time of the whole transportation task. The sectional balance optimizing model is used for searching an optimal route combination in a plurality of sectional transportation tasks so as to maximize the overall transportation efficiency.
Illustratively, a critical route location model is constructed, first, historical monitoring data is acquired and feature extraction is performed on the historical monitoring data to obtain distance features, time features, security features, weather risk features, and cost features. These features help to better understand the nature and condition of the route. And then, corresponding weights are distributed to different features according to the route planning requirements, and a key route positioning model is constructed by using a convolutional neural network based on the weights. Next, model training is performed based on the features and the recorded data. Through training, the segmented route optimizing model learns the association relation between the multidimensional features and the risk indexes, so that the transportation risk feature identification capability is obtained.
Optionally, the data in the information integration monitoring database is called and input into a key route positioning model, a plurality of segmented transportation tasks are carried out to carry out transportation risk feature identification, and task delay risk features, task safety risk features and personnel safety risk features are obtained. And then traversing the plurality of segmented transportation tasks to perform task risk analysis according to the task delay risk features, the task safety risk features and the personnel safety risk features, and acquiring a plurality of task risk indexes.
Further, according to the task risk indexes, threshold judgment is performed, if the task risk index is larger than the preset task risk index, it is indicated that abnormal risk of the segmented transportation task corresponding to the task risk index is larger, and the segmented transportation task is determined to be the first segmented transportation task.
Preferably, the first segmented transportation task is a most risky segmented transportation task determined according to the critical route positioning model.
Optionally, the segment balancing optimizing model performs balancing optimizing on the first segment transportation task, selects an optimal route from candidate routes of each segment of the multiple sets of planned routes, and outputs multiple segment optimizing routes. The segment equalization optimizing model is constructed based on an optimizing algorithm.
In some embodiments, the segment route optimization model invoking data in the information integration monitoring database to optimize the plurality of segment transportation tasks comprises:
A first set of planned routes for the first segmented transportation mission is obtained.
And the segmentation balance optimizing model calls data in the information integration monitoring database to perform risk analysis on the first planning route set, and a first route risk set corresponding to the first planning route set is obtained.
And generating a first selected probability set according to the first route risk set.
And the segmentation balance optimizing model optimizes the rest segmentation transportation tasks according to the first selected probability set and outputs a plurality of segmentation optimizing routes.
Optionally, a planned route set is obtained, risk analysis and optimization are performed, and first, a first planned route set corresponding to a first sectional transportation task in a plurality of groups of planned route sets is extracted. And then, invoking data in the information integration monitoring database by the segmentation balance optimizing model to perform risk analysis on the first planning route set. Specifically, the method includes analyzing factors such as traffic conditions, weather conditions, route lengths, expected running time and the like of routes, and generating a first route risk set corresponding to a first planned route set.
Further, a first set of selected probabilities is generated from the first set of route risks. The first selected probability set comprises the probability that the segmented transportation task is selected for optimizing, and the higher the overall risk level of the route risk set in the segmented transportation task is, the higher the corresponding selection probability is, in other words, if the risk typical values of a plurality of routes in the route risk set are higher, the more the segmented transportation task needs to be optimized.
Finally, the segment balancing optimizing model optimizes the rest segment transportation tasks according to the first selected probability set. And preferentially processing the high-risk segmented tasks through risk analysis and optimizing, and finding an optimal route for each segmented transportation task. So as to improve the efficiency and accuracy of the transportation task and reduce the transportation cost.
Further, in some implementations, the segment balancing optimizing model determines a first segment route according to the first selected probability set, where the first segment route is a route with the highest selected probability.
And the segmentation balance optimizing model performs one-round optimizing on the rest segmentation transportation tasks according to the first segmentation route and outputs a plurality of segmentation optimizing routes.
Further, the expression of the segment equalization optimizing model is as follows:
；
wherein, For the first segment transport taskCost function of the planned route set relative to the remaining segmented transportation mission.
For the first sectional transport taskIs provided with a first set of planned routes,A set of planned routes for the remaining segmented transportation mission,，For the total number of the plurality of segmented transportation tasks, the first selected probability is set toThe method is used for selecting the optimal segmentation route of the round.
Multiple sets of planned route sets are output for each corresponding planned route set based on each transportation task,，Number of planned routes for each set of planned routes.
Represent the firstA set of alternative routes in the individual transportation tasks; Is shown in Lower (th)Routing individual transportation tasksIs a function of the probability of (1),To transport tasks based on a first segmentLower multi-group planning route setThe generated payment cost, orderThe minimum convergence outputs a plurality of segment optimized routes.
Through the steps, the route optimization of the task with higher risk level in the segmented transportation task is ensured, and the efficiency of the route optimization is improved.
In summary, the transportation route planning method based on artificial intelligence provided by the invention has the following technical effects:
Receiving a target transportation task through an interactive transportation route planning system; carrying out task analysis on the target transportation task, decomposing the target transportation task into a plurality of segmented transportation tasks, wherein each segmented transportation task corresponds to a starting point and a target point, and the starting point of the next segmented transportation task is the same as the target point of the previous segmented transportation task; acquiring a plurality of planning route sets corresponding to the segmented transportation tasks respectively, and outputting a plurality of groups of planning route sets; respectively monitoring a plurality of groups of planned route sets through an internet of things connection information integration device, and outputting an information integration monitoring database; establishing a segmented route optimizing model, calling data in an information integration monitoring database by the segmented route optimizing model to optimize a plurality of segmented transportation tasks, and outputting a plurality of segmented optimizing routes corresponding to the segmented transportation tasks. Therefore, the technical problems of high updating cost and poor timeliness of route planning are solved, and the technical effects of reducing the information updating cost and improving the route planning efficiency are realized.
Example two
Fig. 2 is a schematic diagram of an artificial intelligence-based transportation route planning system according to the present invention. For example, the flow diagram of the method for planning a transportation route based on artificial intelligence of the present invention in fig. 1 can be implemented by the structure shown in fig. 2.
Based on the same conception as the transportation route planning method based on artificial intelligence in the embodiment, the transportation route planning system based on artificial intelligence further comprises:
the task acquisition module 11 is configured to receive a target transportation task by using the interactive transportation route planning system.
The analysis segmentation module 12 is configured to perform task analysis on the target transportation task, decompose the target transportation task into a plurality of segmented transportation tasks, each segmented transportation task corresponds to a starting point and a target point, and the starting point of the next segmented transportation task is the same as the target point of the previous segmented transportation task.
The segment planning module 13 is configured to obtain planned route sets corresponding to the multiple segment transportation tasks, and output multiple sets of planned route sets.
The route monitoring module 14 is configured to monitor the plurality of sets of planned route sets respectively through the internet of things connection information integration device, and output an information integration monitoring database.
The optimizing and selecting module 15 is configured to establish a segment route optimizing model, call the data in the information integration monitoring database to optimize the plurality of segment transportation tasks, and output a plurality of segment optimizing routes corresponding to the plurality of segment transportation tasks.
Wherein the parsing segmentation module 12 comprises:
and the target transportation task decomposing unit is used for equidistantly decomposing the target transportation task to obtain K initial segmented lines.
And the hub node acquisition unit is used for acquiring the path hub node of each initial segment line in the K initial segment lines.
And the complexity analysis unit is used for carrying out complexity analysis by the path junction node and outputting K line complexity.
And the decomposition optimization unit is used for outputting a plurality of segmented transportation tasks by taking the minimum variance of the K line complexity as a decomposition target.
Further, the optimizing selection module 15 includes:
The optimizing model building unit is used for building a segmented route optimizing model, and the segmented route optimizing model comprises a key route positioning model and a segmented balance optimizing model.
The risk feature recognition unit is used for calling the data in the information integration monitoring database by the key route positioning model to recognize transportation risk features of the segmented transportation tasks, and the transportation risk feature recognition unit comprises task delay risk features, task safety risk features and personnel safety risk features.
The risk index obtaining unit is used for analyzing according to the task delay risk characteristics, the task safety risk characteristics and the personnel safety risk characteristics to obtain a plurality of task risk indexes.
The first sectional transportation task determining unit is used for determining a first sectional transportation task according to the task risk indexes, wherein the first sectional transportation task is a sectional route with the task risk index larger than a preset task risk index.
The sectional balance optimizing unit is used for carrying out balance optimizing on the basis of the first sectional transportation task by the sectional balance optimizing model and outputting a plurality of sectional optimizing routes.
Further, the segment balancing optimizing unit in the optimizing selecting module 15 includes:
and the set acquisition unit is used for acquiring a first planned route set of the first segmented transportation task.
And the aggregate risk analysis unit is used for calling the data in the information integration monitoring database by the segmentation balance optimizing model to perform risk analysis on the first planning route aggregate to acquire a first route risk aggregate corresponding to the first planning route aggregate.
And the selection probability generating unit is used for generating a first selected probability set according to the first route risk set.
And the allowance task optimizing unit is used for optimizing the rest segmented transportation tasks according to the first selected probability set by the segmented balance optimizing model and outputting a plurality of segmented optimizing routes.
In some implementations, the information integration device in the system includes a plurality of information sensing channels for integrating a plurality of information sensing modules including at least a vehicle information sensing module, a traffic information sensing module, a climate information sensing module, and a user information sensing module.
The output end of the information integration device is in communication connection with a cloud processor, and the cloud processor is in communication connection with the transportation route planning system.
It should be understood that the embodiments mentioned in this specification focus on differences from other embodiments, and that the specific embodiment in the first embodiment is equally applicable to an artificial intelligence based transportation route planning system described in the second embodiment, and is not further developed herein for brevity of description.
It is to be understood that both the foregoing description and the embodiments of the present invention enable one skilled in the art to utilize the present invention. While the invention is not limited to the embodiments described above, it should be understood that: modifications of the technical solutions described in the foregoing embodiments or equivalent substitutions of some technical features thereof may be still performed by those skilled in the art; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention.
Claims (4)
1. A method of transportation route planning based on artificial intelligence, the method comprising:
The interactive transportation route planning system receives a target transportation task;
performing task analysis on the target transportation task, decomposing the target transportation task into a plurality of segmented transportation tasks, wherein each segmented transportation task corresponds to a starting point and a target point, and the starting point of the next segmented transportation task is the same as the target point of the previous segmented transportation task;
Acquiring planning route sets respectively corresponding to the plurality of segmented transportation tasks, and outputting a plurality of groups of planning route sets;
the information integration device is connected with the Internet of things to monitor the plurality of groups of planned route sets respectively, and an information integration monitoring database is output;
Establishing a segmented route optimizing model, wherein the segmented route optimizing model calls data in the information integration monitoring database to optimize the segmented transportation tasks, and outputs a plurality of segmented optimizing routes corresponding to the segmented transportation tasks;
The method comprises the steps that the segmented route optimizing model calls data in the information integration monitoring database to optimize the segmented transportation tasks, and the method comprises the following steps:
Establishing a segmented route optimizing model, wherein the segmented route optimizing model comprises a key route positioning model and a segmented balance optimizing model;
The key route positioning model calls data in the information integration monitoring database to identify transportation risk characteristics of the plurality of segmented transportation tasks, wherein the transportation risk characteristics comprise task delay risk characteristics, task safety risk characteristics and personnel safety risk characteristics;
Analyzing according to the task delay risk characteristics, the task safety risk characteristics and the personnel safety risk characteristics to obtain a plurality of task risk indexes;
Determining a first segmented transportation task according to the task risk indexes, wherein the first segmented transportation task is a segmented route with a task risk index larger than a preset task risk index;
the sectional balance optimizing model carries out balance optimizing based on the first sectional transportation task and outputs a plurality of sectional optimizing routes;
Acquiring a first planned route set of the first segmented transportation task;
The segmentation balanced optimizing model calls data in the information integration monitoring database to perform risk analysis on the first planning route set, and a first route risk set corresponding to the first planning route set is obtained;
generating a first selected probability set according to the first route risk set;
The subsection balance optimizing model optimizes the rest subsection transportation tasks according to the first selected probability set and outputs a plurality of subsection optimizing routes;
The segmentation balanced optimizing model determines a first segmentation route according to the first selected probability set, wherein the first segmentation route is the route with the largest selected probability;
The subsection balance optimizing model optimizes the rest subsection transportation tasks for one round according to the first subsection route and outputs a plurality of subsection optimizing routes;
the expression of the segmentation equilibrium optimizing model is as follows:
Wherein E i(σi|σ-i) is the cost function of the planned route set of the first segmented transportation mission i relative to the remaining segmented transportation missions;
Sigma i is a first planned route set of a first segmented transportation task i, sigma -i is a planned route set of the remaining segmented transportation tasks, sigma -i＝(σ1,…,σi-1,σi+1…,σN), N is the total number of the plurality of segmented transportation tasks, and the segmented route for the round of optimizing is selected in sigma i according to the first selected probability set;
S is a plurality of groups of planned route sets output based on the planned route sets corresponding to the transportation tasks respectively, j= {0, 1..n }, and n is the number of planned routes of each planned route set; σ j represents an alternative route set in the j-th transportation mission; σ j[sj represents the probability of the jth transportation mission route S j at σ j, u i (S) is the payment cost based on the multiple set of planned routes S at the first segmented transportation mission i, letting E i(σi|σ-i) converge minimally to output multiple segmented optimized routes.
2. The method of claim 1, wherein the target transportation task is broken down into a plurality of segmented transportation tasks, the method comprising:
equidistant decomposition is carried out on the target transportation task, and K initial segmented circuits are obtained;
Acquiring a path junction node of each initial segment line in the K initial segment lines;
Carrying out complexity analysis by the path junction node, and outputting K line complexity;
and taking the smallest variance of the K line complexity as a decomposition target, and outputting a plurality of segmented transportation tasks.
3. The method of claim 1, wherein the information integration device comprises a plurality of information sensing channels for integrating a plurality of information sensing modules including at least a vehicle information sensing module, a traffic information sensing module, a climate information sensing module, and a user information sensing module;
the output end of the information integration device is in communication connection with a cloud processor, and the cloud processor is in communication connection with the interactive transportation route planning system.
4. An artificial intelligence based transportation route planning system, the system comprising:
the task acquisition module is used for receiving a target transportation task;
the analysis segmentation module is used for carrying out task analysis on the target transportation task and decomposing the target transportation task into a plurality of segmentation transportation tasks, each segmentation transportation task corresponds to a starting point and a target point, and the starting point of the next segmentation transportation task is the same as the target point of the previous segmentation transportation task;
The sectional planning module is used for acquiring planning route sets corresponding to the plurality of sectional transportation tasks respectively and outputting a plurality of groups of planning route sets;
The route monitoring module is used for respectively monitoring the plurality of groups of planned route sets through the internet of things connection information integration device and outputting an information integration monitoring database;
The optimizing selection module is used for establishing a segmented route optimizing model, and the segmented route optimizing model calls data in the information integration monitoring database to optimize the segmented transportation tasks and outputs a plurality of segmented optimizing routes corresponding to the segmented transportation tasks;
wherein, the optimizing selection module comprises:
The optimizing model building unit is used for building a segmented route optimizing model, and the segmented route optimizing model comprises a key route positioning model and a segmented balancing optimizing model;
The risk feature recognition unit is used for calling the data in the information integration monitoring database by the key route positioning model to recognize transportation risk features of the segmented transportation tasks, and the transportation risk features comprise task delay risk features, task safety risk features and personnel safety risk features;
the risk index acquisition unit is used for analyzing according to the task delay risk characteristics, the task safety risk characteristics and the personnel safety risk characteristics to acquire a plurality of task risk indexes;
The first sectional transportation task determining unit is used for determining a first sectional transportation task according to the task risk indexes, wherein the first sectional transportation task is a sectional route with a task risk index larger than a preset task risk index;
The sectional balance optimizing unit is used for carrying out balance optimizing on the basis of the first sectional transportation task by the sectional balance optimizing model and outputting a plurality of sectional optimizing routes;
the collection acquisition unit is used for acquiring a first planned route collection of the first segmented transportation task;
The set risk analysis unit is used for calling the data in the information integration monitoring database by the segmentation equilibrium optimizing model to perform risk analysis on the first planning route set, and acquiring a first route risk set corresponding to the first planning route set;
The selection probability generation unit is used for generating a first selected probability set according to the first route risk set;
The balance task optimizing unit is used for optimizing the rest segment transportation tasks according to the first selected probability set by the segment balancing optimizing model and outputting a plurality of segment optimizing routes;
The segmentation balanced optimizing model determines a first segmentation route according to the first selected probability set, wherein the first segmentation route is the route with the largest selected probability;
The subsection balance optimizing model optimizes the rest subsection transportation tasks for one round according to the first subsection route and outputs a plurality of subsection optimizing routes;
the expression of the segmentation equilibrium optimizing model is as follows:
Wherein E i(σi|σ-i) is the cost function of the planned route set of the first segmented transportation mission i relative to the remaining segmented transportation missions;
Sigma i is a first planned route set of a first segmented transportation task i, sigma -i is a planned route set of the remaining segmented transportation tasks, sigma -i＝(σ1,…,σi-1,σi+1…,σN), N is the total number of the plurality of segmented transportation tasks, and the segmented route for the round of optimizing is selected in sigma i according to the first selected probability set;
S is a plurality of groups of planned route sets output based on the planned route sets corresponding to the transportation tasks respectively, j= {0, 1..n }, and n is the number of planned routes of each planned route set; σ j represents an alternative route set in the j-th transportation mission; σ j[sj represents the probability of the jth transportation mission route S j at σ j, u i (S) is the payment cost based on the multiple set of planned routes S at the first segmented transportation mission i, letting E i(σi|σ-i) converge minimally to output multiple segmented optimized routes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410605692.6A CN118195117B (en) | 2024-05-16 | 2024-05-16 | Transportation route planning method and system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410605692.6A CN118195117B (en) | 2024-05-16 | 2024-05-16 | Transportation route planning method and system based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118195117A CN118195117A (en) | 2024-06-14 |
| CN118195117B true CN118195117B (en) | 2024-08-13 |
Family
ID=91406759
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410605692.6A Active CN118195117B (en) | 2024-05-16 | 2024-05-16 | Transportation route planning method and system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118195117B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116957174A (en) * | 2023-09-21 | 2023-10-27 | 云南中畅物流有限公司 | Freight line integrated planning method and system based on data fusion |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10663311B2 (en) * | 2016-08-22 | 2020-05-26 | Microsoft Technology Licensing, Llc | Generating personalized routes with user route preferences |
| CN108647841A (en) * | 2018-07-10 | 2018-10-12 | 临沂大学 | A kind of multiple step format combined haulage system and method |
| CN111160665A (en) * | 2019-12-31 | 2020-05-15 | 科技谷（厦门）信息技术有限公司 | System and method for planning large cargo transportation line |
| CN112418749B (en) * | 2020-09-30 | 2024-01-05 | 南京力通达电气技术有限公司 | Comprehensive evaluation method for transportation efficiency of large power equipment |
| CN113537752B (en) * | 2021-07-09 | 2024-06-14 | 大连海事大学 | Traffic transportation big data scheduling method and platform based on multiple data sources |
| CN114234991A (en) * | 2021-11-25 | 2022-03-25 | 中国南方电网有限责任公司 | Navigation path planning method and device, computer equipment and storage medium |
| CN117629213A (en) * | 2023-11-17 | 2024-03-01 | 中交机电工程局有限公司 | Path planning method based on urban rail transit information |
-
2024
- 2024-05-16 CN CN202410605692.6A patent/CN118195117B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116957174A (en) * | 2023-09-21 | 2023-10-27 | 云南中畅物流有限公司 | Freight line integrated planning method and system based on data fusion |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118195117A (en) | 2024-06-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhang et al. | A framework for passengers demand prediction and recommendation | |
| Zheng et al. | Order dispatch in price-aware ridesharing | |
| US9404760B2 (en) | Efficient route planning in public transportation networks | |
| US20210302585A1 (en) | Smart navigation method and system based on topological map | |
| US10119826B2 (en) | System and method for accelerating route search | |
| US8566031B2 (en) | Map matching system, map matching method and program | |
| Taha et al. | Route planning considerations for autonomous vehicles | |
| US8494999B2 (en) | Sensor based truth maintenance method and system | |
| CN107609694B (en) | Structure optimization method for offshore wind power cluster power transmission system and storage medium | |
| CN111815946A (en) | Method and device for determining abnormal road section, storage medium and electronic equipment | |
| CN111947676B (en) | Express delivery path planning method and device, electronic equipment and storage medium | |
| CN116824861B (en) | Method and system for scheduling sharing bicycle based on multidimensional data of urban brain platform | |
| Wang et al. | A reinforcement learning approach for online service tree placement in edge computing | |
| CN114005297A (en) | Motorcade coordinated driving method based on Internet of vehicles | |
| CN113682302B (en) | Driving state estimation method and device, electronic equipment and storage medium | |
| CN113159577B (en) | Urban road planning method based on crowd sensing | |
| CN118258420A (en) | Path planning method and system based on multiple carriers, electronic equipment and storage medium | |
| CN118195117B (en) | Transportation route planning method and system based on artificial intelligence | |
| CN114253975A (en) | Load-aware road network shortest path distance calculation method and device | |
| CN112084339B (en) | Traffic knowledge graph construction method based on cross-media data | |
| CN111582527A (en) | Travel time estimation method and device, electronic equipment and storage medium | |
| US11237008B2 (en) | System and method for controlling vehicular pollution concentration and providing maximum traffic flow throughput | |
| Deleplanque et al. | Dial-a-ride problem with time windows, transshipments, and dynamic transfer points | |
| CN115994726B (en) | Dispatch path adjustment method, dispatch path adjustment device, electronic equipment and computer readable medium | |
| Ivaschenko et al. | Multi-layer data model for transportation logistics solutions |
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 | ||
| GR01 | Patent grant |