Logistics transportation path planning system and method based on data analysis
Through data analysis and genetic algorithm optimization, path segments are dynamically divided and corrected, abnormal paths are identified and auxiliary verification is performed, and a smooth optimal path is generated. This solves the efficiency and safety problems of traditional methods in complex water conservancy transportation environments and achieves efficient and safe path planning.
Patent Information
- Application Number
- CN202510810705.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-17
- Publication Date
- 2025-09-23
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Traditional path planning methods are difficult to provide optimal routes in complex and changeable water transport environments, and fail to effectively consider real-time environmental changes, cargo characteristics and transportation conditions, resulting in low transportation efficiency and increased costs.
Through the data analysis-based path segmentation module, auxiliary verification analysis module and path fine-tuning module, the segment units are dynamically divided and corrected, combined with the genetic algorithm to optimize the path angle, identify abnormal paths and perform auxiliary verification to generate a smooth optimal path.
It achieves precise path management in a dynamic environment, reduces the misjudgment rate, improves transportation efficiency and safety, balances safety and cost, and significantly improves adaptability and real-time performance.
Smart Images
Figure CN120688712A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of transportation route planning, and specifically relates to a logistics transportation route planning system and method based on data analysis. Background Art
[0002] In the field of water freight transportation, traditional route planning methods often rely on fixed rules and experience, which can lead to inadequate routes in complex and changing transportation environments. These routes may fail to account for factors such as real-time environmental changes, cargo characteristics, and transportation conditions, leading to inefficient transportation, increased costs, and delays. Especially in river or waterway navigation, factors such as terrain, water flow, and weather conditions can significantly impact transportation safety and efficiency. Traditional planning methods struggle to fully account for these factors, hindering route planning accuracy.
[0003] With the development of information technology, data-driven route planning methods have gradually gained attention. By collecting and analyzing large amounts of data, these methods can more accurately identify and optimize transportation routes. However, existing data-driven route planning systems typically only focus on initial route planning and lack dynamic adjustment mechanisms during route operation. This makes it difficult for the system to respond quickly to sudden environmental changes or emergencies, affecting overall transportation efficiency. Based on this, a logistics transportation route planning system and method based on data analysis is proposed. Summary of the Invention
[0004] The purpose of the present invention is to provide a logistics transportation path planning system and method based on data analysis, which solves the technical problems of path segment management in a dynamic environment, data-driven dynamic segment division optimization and path fine-tuning optimization under multiple constraints.
[0005] A logistics transportation route planning system based on data analysis includes: a route segmentation module for managing the target cargo transportation route of water conservancy cargo transportation, obtaining each initial segment unit and recording its corresponding ontological feature data and transportation environment data, obtaining the path segment transportation data corresponding to each initial segment unit through data analysis, and obtaining each valid path transportation data set by identifying abnormal path segments; The auxiliary verification analysis module is used to perform path anomaly fine-tuning analysis based on the effective path transportation data set, obtain path anomaly values to determine whether to perform auxiliary verification, obtain auxiliary verification feedback data based on the auxiliary verification requirements obtained, and obtain a supplementary effective path transportation data set; The path anomaly fine-tuning analysis is performed based on the valid path transportation data set to obtain the path anomaly value to determine whether to perform auxiliary verification; The route segment division and correction module is used to analyze the supplementary effective route segment transportation data set, obtain the environmental dynamic factors, and combine them with the ontological feature data of the initial segment unit to divide and correct the segment length of the initial segment unit; The path fine-tuning module is connected to the path segment division and correction module to collect and output the fine-tuning angle constraint parameters and corresponding correction parameters generated by the corrected segment unit and combine them with the optimization algorithm to obtain the first and second fine-tuning angles, thereby adjusting the path direction and curvature.
[0006] As a further solution of the present invention: configuring the target cargo transportation path with the corresponding initial segment units includes: dividing the target cargo transportation path into a plurality of initial segment units of random equal lengths, namely ;in, Represents each segment unit, i is the identifier of different segment units ; n represents the number of segment units divided and ; n is a positive integer; The boundary coordinates and length of each section unit are recorded as the main feature data of the section unit. Based on the divided multiple section units, the corresponding transportation environment data of each section unit within the preset supervision period is collected, including wind speed, temperature, water flow speed, water depth, etc.: Preprocessing the transportation environment data corresponding to each of the above-mentioned section units, including cleaning and normalization, to obtain preprocessed transportation environment data; Define route segment transportation data based on pre-processed transportation environment data Including water velocity gradient , water depth fluctuation rate , historical navigation density ; The water flow velocity change gradient , according to the formula ;in, is the water velocity change gradient corresponding to different section units, is the water flow velocity corresponding to different section units, is the segment length corresponding to different segment units, Preset terrain correction coefficients corresponding to different section units; Water depth fluctuation , according to the formula ;in, is the water depth fluctuation rate corresponding to different section units, is the water depth measurement value corresponding to the number of measurements in different section units, The average water depth corresponding to different section units, The total number of measurements within the preset supervision period; Historical navigation density The passage frequency of ships in different section units is obtained through historical passage record data; According to the path segment parameters , construct the segment unit supervision function ; Among them, in the formula, Path segment data corresponding to different segment units in the preset supervision cycle; The standard range of route segment data corresponding to different segment units in the preset supervision cycle; The segment unit supervision flag contains a value of 0 or 1, indicating whether the segment status of the corresponding segment unit is normal or abnormal; By identifying abnormal route segments, the effective route transportation data sets are obtained.
[0007] As a further solution of the present invention, when obtaining each valid path transportation data set by identifying abnormal path segments, the method includes: Sorting and combining the section unit supervisions obtained by processing all the section units corresponding to the target cargo transportation route within the preset supervision period to obtain the section unit supervision sequence corresponding to the target cargo transportation route; Traverse and analyze the section unit supervision sequence of the target cargo transportation route and find the section unit supervision identifier with a value of 1; If there is no segment unit supervision identifier with a value of 1 in the segment unit supervision sequence, a normal instruction for the path segment unit is generated and prompted; If there is a segment unit supervision flag with a value of 1 in the segment unit supervision sequence, a path segment unit abnormal instruction is generated, and the segment unit is marked as an abnormal path segment unit according to the segment unit abnormal instruction. ; where j is the unit identifier of each abnormal path segment and ; m represents the number of abnormal path segment units; According to the marked abnormal route segments, the route segment transportation data corresponding to each abnormal route segment is extracted and marked as the valid route segment transportation data set. ; The effective path transportation data set includes the historical navigation density, water flow velocity change gradient, and water depth fluctuation rate corresponding to the abnormal path section.
[0008] As a further solution of the present invention: performing fine-tuning analysis on the path anomaly based on the valid path transportation data set, obtaining the path anomaly value to determine whether to perform auxiliary verification; including: According to the marked abnormal route segments, the valid route transportation data sets corresponding to the abnormal route segments are extracted. ; For the effective path transportation dataset Each valid path transport data in the abnormal path segment is analyzed independently, and the deviation value of each valid path transport data in each abnormal path segment from the standard range of the path segment data is obtained based on the deviation value calculation formula; and the weighted sum of the deviation value of each valid path transport data in each abnormal path segment is obtained to obtain the path abnormal value corresponding to each abnormal path segment. ; Path outliers With threshold Make comparisons; When the path outlier Not less than the threshold When the vehicle is in the vicinity of the designated position, a navigation alarm is issued; When the path outlier Less than threshold When the auxiliary verification is needed, it is determined based on the valid path transport data set whether it is needed. When it is determined that the auxiliary verification is needed, the abnormal path segment unit is determined based on the valid path data set and the path abnormality value; and an auxiliary verification signal is sent to the corresponding abnormal path segment unit.
[0009] As a further solution of the present invention: determining whether auxiliary verification is required based on the valid path data set; including: Collect each abnormal path section unit within the preset detection period Corresponding path outlier value , and check the current abnormal path segment unit Is there a path anomaly value of k consecutive abnormal points in all monitoring times within the preset detection period? approaching the threshold; If it does not exist, it means that there is no continuous abnormal state and there is no need to perform the supplementary operation of the finite path transportation data set; If it exists, it means there is a continuous abnormal state, and the corresponding abnormal path segment unit Mark as requiring auxiliary verification unit, send auxiliary verification signal to the corresponding abnormal path segment unit, and receive navigation monitoring feedback results from the segment unit, including actual track deviation value and ship draft depth change rate; According to the navigation monitoring feedback results received from the section unit, the navigation monitoring feedback results are added to the effective path data set to obtain a supplementary effective path section transportation data set. ; The supplementary effective path section transportation data set consists of basic effective path section transportation data and actual trajectory deviation value, and ship draft depth change rate.
[0010] As a further solution of the present invention, data analysis is performed on the supplementary effective path segment transport data set to obtain environmental dynamic factors and, combined with the ontological feature data of the initial segment unit, to divide and modify the segment length of the initial segment unit; including: After normalizing all types of data in the transportation dataset of each supplementary effective path section, the environmental factors corresponding to each abnormal path section unit are obtained by weighted summation. ; Based on the environmental factors corresponding to each abnormal path segment unit And its corresponding ontological feature data, perform segment unit correlation analysis, and determine segment merging and segmentation strategies; specifically, the ontological feature data includes: segment boundary coordinates and length of each abnormal path segment unit; Starting from the first abnormal path segment unit among all abnormal path segment units, the environmental factor difference between adjacent abnormal path segment units is calculated to obtain the segment merging judgment value. ; Where v represents the identifier of each adjacent abnormal path segment unit; when v=1, it is the difference value of the environmental factor between the first abnormal path segment unit and the second abnormal path segment unit, and so on; Merge segments to determine the value Its preset threshold Make comparisons; When the segment merges, the judgment value Less than the preset threshold When , the segment boundaries between the corresponding adjacent abnormal path segment units are removed; and multiple initial segment units A are updated to generate continuous new segment units ; When the segment merges, the judgment value Greater than the preset threshold When , the boundary between adjacent segments is marked as the mutation point of environmental factors; a new segment boundary is added at the mutation point, and the original adjacent segment is divided into two independent segments; and multiple initial segment units A are updated to generate continuous new segment units .
[0011] As a further solution of the present invention: collecting fine-tuning angle constraint parameters and corresponding correction parameters generated by the modified segment unit; combining the optimization algorithm to obtain first and second fine-tuning angles, thereby adjusting the path direction and curvature; including: path information corresponding to the updated segment unit, including the start and end points of each segment, segment length, and corresponding environmental factors and body feature data; Calculate the angle adjustment range based on the environmental factor β and body characteristic data of each segment and curvature change threshold ; According to the formula: ;in, is the safety factor, is the difference in environmental factors between adjacent sections, is the sum of the environmental factors of two adjacent sections, is the average length of adjacent segments; Curvature change threshold ;in, Empirical constant, is the environmental factor of the jth segment, is the length of the jth segment; Adjust the angle range and curvature change threshold , as angle constraint parameter and curvature correction parameter; Perform chromosome encoding design on each path angle to obtain multiple chromosomes; obtain a set of candidate angles based on constraint parameters including angle adjustment range and curvature change threshold. Where p is the number of candidate angles; Based on the above constraint parameters, a genetic algorithm is used for multi-objective optimization to construct a fitness function. ;in, is the weight coefficient, is the curvature safety penalty term, is the angle adjustment range, is the total length of the path; The genetic algorithm iterative process for each chromosome includes selection, crossover, and mutation. Through iterative optimization, a set of candidate direction angles is obtained. The angle combination with the highest fitness is selected to obtain the first fine-tuning angle. The curvature radius is adjusted, and the second fine-tuning angle is obtained based on the path satisfying C ≤ C_max near the mutation point. When the number of iterations reaches the preset upper limit, the iteration is terminated; Outputting the adjusted path includes: merging the optimized first fine-tuning angle and the second fine-tuning angle to generate final path parameters; Use Bezier curves or spline interpolation to eliminate angle mutation points and generate continuous paths.
[0012] As a further solution of the present invention: the first fine-tuning angle is composed of a set of direction angles of each segment; the second fine-tuning angle is composed of a set of curvature radii corresponding to each segment.
[0013] A logistics transportation route planning method based on data analysis includes the following steps: Step 1: Perform path management on the target cargo transportation path of water conservancy cargo transportation, obtain each initial segment unit and record its corresponding ontological feature data and transportation environment data, obtain the path segment transportation data corresponding to each initial segment unit through data analysis, and obtain each valid path transportation data set by identifying abnormal path segments; Step 2: Perform path anomaly fine-tuning analysis based on the effective path transportation dataset, obtain path anomaly values to determine whether to perform auxiliary verification, obtain auxiliary verification feedback data based on the auxiliary verification requirements determined, and obtain a supplementary effective path transportation dataset; Step 3: Analyze the supplementary effective path segment transport data set to obtain the environmental dynamic factors and combine them with the ontological feature data of the initial segment unit to divide and modify the segment length of the initial segment unit; Step 4: The fine-tuning angle constraint parameters generated by the segment unit after acquisition and output and the corresponding correction parameters are combined with an optimization algorithm to obtain the first and second fine-tuning angles, thereby adjusting the path direction and curvature.
[0014] Compared with the prior art, the present invention has the following beneficial effects: (1) The present invention dynamically divides and modifies segment units based on environmental factors, identifies environmental mutation points through segment merging judgment values, and automatically adjusts segment boundaries to solve the problem that traditional fixed segmentation cannot adapt to complex environments; combines multi-dimensional parameters such as water flow velocity gradient and historical navigation density to construct segment unit supervision functions to accurately identify abnormal paths; introduces continuous abnormal state detection to distinguish between occasional and continuous risks, thereby reducing the misjudgment rate; and supplements real-time data such as actual trajectory deviation and draft depth change rate through auxiliary verification signals, dynamically updates effective data sets, and improves the real-time and reliability of decision-making; realizes dynamic segment management and intelligent response mechanism, and improves the accuracy and adaptability of path planning; (2) The present invention uses a genetic algorithm combined with the angle adjustment range and the curvature change threshold constraint to generate the first fine-tuning angle and the second fine-tuning angle that take into account the path length and safety, thereby solving the problem of single adjustment and high risk of traditional methods; based on the dynamic triggering verification mechanism of path outliers, it reduces the consumption of redundant monitoring resources and balances safety and cost; and realizes multi-objective optimization and path smoothing technology, taking into account navigation safety and efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] Figure 1 Schematic diagram of the system framework structure of the present invention; Figure 2 Schematic diagram of the framework structure of the method of the present invention; Figure 3 This is a logic diagram for implementing the auxiliary verification and analysis module of the present invention. DETAILED DESCRIPTION
[0016] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.
[0017] Example 1: Please refer to Figure 1 ,This application provides a logistics transportation path planning system and method based on data analysis, including; The path segmentation module is used to manage the target cargo transportation path of water conservancy cargo transportation, obtain each initial segment unit and record its corresponding ontological feature data and transportation environment data, obtain the path segment transportation data corresponding to each initial segment unit through data analysis, and obtain each valid path transportation data set by identifying abnormal path segments; It should be noted that the target cargo transportation route for water conservancy cargo transportation in this example is obtained by using the starting point and destination of the transportation task determined by the logistics order or user demand as the basic input information; and based on the electronic navigation chart (ENC) or GIS system, combined with the shortest path algorithm (such as Dijkstra algorithm) to generate the basic path as the target cargo transportation route, with a total length of A; The configuration of the corresponding initial segment units for the target cargo transportation path includes: dividing the target cargo transportation path into a plurality of initial segment units of random equal lengths, namely ;in, Represents each segment unit, i is the identifier of different segment units ; n represents the number of segment units divided and ; n is a positive integer; The boundary coordinates and length of each section unit are recorded as the main feature data of the section unit. Based on the divided multiple section units, the corresponding transportation environment data of each section unit within the preset supervision period is collected, including wind speed, temperature, water flow speed, water depth, etc.: It should be noted that the preset supervision period can be determined according to existing water transport vessel supervision requirements, and the unit corresponding to the supervision period is hours, specifically one hour; the transportation environment data is obtained through multiple sensors such as hydrological sensors and temperature sensors; Preprocessing the transportation environment data corresponding to each of the above-mentioned section units, including cleaning and normalization, to obtain preprocessed transportation environment data; Define route segment transportation data based on pre-processed transportation environment data Including water velocity gradient , water depth fluctuation rate , historical navigation density ; The water flow velocity change gradient , according to the formula ;in, is the water velocity change gradient corresponding to different section units, is the water flow velocity corresponding to different section units, is the segment length corresponding to different segment units, The preset terrain correction coefficients corresponding to different section units are set by professional researchers based on actual needs; Water depth fluctuation , according to the formula ;in, is the water depth fluctuation rate corresponding to different section units, is the water depth measurement value corresponding to the number of measurements in different section units, The average water depth corresponding to different section units, The total number of measurements within the preset supervision period; Historical navigation density The passage frequency of ships in different section units is directly obtained through historical passage record data; According to the path segment parameters , construct the segment unit supervision function ; Among them, in the formula, Path segment data corresponding to different segment units in the preset supervision cycle; The standard range of route segment data corresponding to different segment units in the preset supervision period can be determined based on existing water transport vessel transportation requirements; It should be noted that the section unit supervision identifier is used to perform data calculation on the path section data of different section units within a preset supervision period to digitally represent the section status of the section unit; The segment unit supervision flag contains a value of 0 or 1, indicating whether the segment status of the corresponding segment unit is normal or abnormal; When obtaining each valid path transportation data set by identifying abnormal path segments; Sorting and combining the section unit supervisions obtained by processing all the section units corresponding to the target cargo transportation route within the preset supervision period to obtain the section unit supervision sequence corresponding to the target cargo transportation route; Traverse and analyze the section unit supervision sequence of the target cargo transportation route and find the section unit supervision identifier with a value of 1; If there is no segment unit supervision identifier with a value of 1 in the segment unit supervision sequence, a normal instruction for the path segment unit is generated and prompted; If there is a segment unit supervision flag with a value of 1 in the segment unit supervision sequence, a path segment unit abnormal instruction is generated, and the segment unit is marked as an abnormal path segment unit according to the segment unit abnormal instruction. ; where j is the unit identifier of each abnormal path segment and ; m represents the number of abnormal path segment units; According to the marked abnormal route segments, the route segment transportation data corresponding to each abnormal route segment is extracted and marked as the valid route segment transportation data set. ; The effective path transportation data set includes the historical navigation density, water flow velocity change gradient, and water depth fluctuation rate corresponding to the abnormal path section.
[0018] In an embodiment of the present invention, by performing data calculation on the path segment transportation data corresponding to each segment unit within a preset supervision period, the segment unit supervision identification corresponding to different segment units is obtained, which can not only realize the digital representation of the segment status of different segment units, but also provide reliable supervision data support for the subsequent collaborative verification analysis of different segment units, thereby improving the supervision analysis effect of the path segment and the subsequent expansion analysis support effect.
[0019] in accordance with Figure 3 ,The auxiliary verification analysis module is used to perform path anomaly fine-tuning analysis based on the ,valid path transport dataset, obtain the path anomaly value to determine whether to ,perform auxiliary verification, obtain auxiliary verification feedback data based on the ,judged auxiliary verification requirements, and obtain a ,supplementary effective path transport dataset; The method performs fine-tuning analysis on the path anomaly based on the valid path transport data set, obtains the path anomaly value and determines whether to perform auxiliary verification; specifically, According to the marked abnormal route segments, the valid route transportation data sets corresponding to the abnormal route segments are extracted. ; For the effective path transportation dataset Each valid path transport data in the abnormal path segment is analyzed independently, and the deviation value of each valid path transport data in each abnormal path segment from the standard range of the path segment data is obtained based on the deviation value calculation formula; and the weighted sum of the deviation value of each valid path transport data in each abnormal path segment is obtained to obtain the path abnormal value corresponding to each abnormal path segment. ; Path outliers With threshold Make comparisons; When the path outlier Not less than the threshold When the vehicle is in the vicinity of the designated position, a navigation alarm is issued; When the path outlier Less than threshold When the auxiliary verification is needed, the effective path transport data set is used to determine whether auxiliary verification is needed. When it is determined that auxiliary verification is needed, the abnormal path segment unit is determined according to the effective path data set and the path abnormality value; and an auxiliary verification signal is sent to the corresponding abnormal path segment unit; It should be noted that when the path outlier Not less than the threshold When a navigation alarm is issued, it means that the risk of the corresponding abnormal route section has exceeded the tolerable range, and the automated decision-making process must be interrupted immediately to prioritize navigation safety; Further, judging whether auxiliary verification is required according to the valid path data set; Collect each abnormal path section unit within the preset detection period Corresponding path outlier value , and check the current abnormal path segment unit Is there a path anomaly value of k consecutive abnormal points in all monitoring times within the preset detection period? approaching the threshold; If it does not exist, it means that there is no continuous abnormal state, and the abnormal state of the corresponding abnormal path segment unit is a short-term abnormality, and there is no need to perform the supplementary operation of the limited path transportation data set; If it exists, it means there is a continuous abnormal state, and the corresponding abnormal path segment unit Mark as requiring auxiliary verification unit, send auxiliary verification signal to the corresponding abnormal path segment unit, and receive navigation monitoring feedback results from the segment unit, including actual track deviation value and ship draft depth change rate; According to the navigation monitoring feedback results received from the section unit, the navigation monitoring feedback results are added to the effective path data set to obtain a supplementary effective path section transportation data set. The supplementary effective path segment transport data set consists of the basic effective path segment transport data, the actual trajectory deviation value, and the ship draft depth change rate; It should be noted that the above-mentioned actual trajectory deviation value and the ship draft depth change rate are directly obtained by feeding back to the navigation monitoring section through the multi-source sensor fusion technology. This is an existing mature technology and will not be described in detail in this embodiment.
[0020] The route segment division and correction module is used to analyze the supplementary effective route segment transportation data set, obtain the environmental dynamic factors, and combine them with the ontological feature data of the initial segment unit to divide and correct the segment length of the initial segment unit; The data analysis of the supplementary effective path segment transportation data set yields the following environmental dynamic factors: After normalizing all types of data in the transportation dataset of each supplementary effective path section, the environmental factors corresponding to each abnormal path section unit are obtained by weighted summation. ; Based on the environmental factors corresponding to each abnormal path segment unit And its corresponding ontological feature data, perform segment unit correlation analysis, and determine segment merging and segmentation strategies; specifically, the ontological feature data includes: segment boundary coordinates and length of each abnormal path segment unit; Starting from the first abnormal path segment unit among all abnormal path segment units, the environmental factor difference between adjacent abnormal path segment units is calculated to obtain the segment merging judgment value. ; Where v represents the identifier of each adjacent abnormal path segment unit; when v=1, it is the difference value of the environmental factor between the first abnormal path segment unit and the second abnormal path segment unit, and so on; Merge segments to determine the value Its preset threshold Make comparisons; When the segment merges, the judgment value Less than the preset threshold When , the segment boundaries between the corresponding adjacent abnormal path segment units are removed; and multiple initial segment units A are updated to generate continuous new segment units ; When the segment merges, the judgment value Greater than the preset threshold When , the boundary between adjacent segments is marked as the mutation point of environmental factors; a new segment boundary is added at the mutation point, and the original adjacent segment is divided into two independent segments; and multiple initial segment units A are updated to generate continuous new segment units ; It should be noted that in this implementation, the division of the original adjacent segments into two independent segments is divided into two new segments of equal length, and the length of the segment after division must meet the minimum safety length to avoid excessive fragmentation. For example, when the target cargo transportation route has a total length of A = 100 kilometers, the initial segment is divided into 5 initial segment units at 20-kilometer intervals: 、 、 、 、 ; By segment and Make a judgment; when the segment merging judgment value is less than the preset threshold, the segment boundaries between the corresponding adjacent abnormal path segment units are removed and the segment is merged , the remaining segments are 、 、 When the segment merging judgment value is greater than the preset threshold, a new segment boundary is added at the mutation point: [0-20] is divided into [0-10] and [10-20]; [20-40] is divided into [20-30] and [30-40]; the remaining segments remain unchanged: [40-60], [60-80], and [80-100]. The original adjacent segments are divided equally, and the segments after the new segment boundary are divided into 7 new segments of equal length and meeting the minimum safety length. The segmentation method in this embodiment is the equal division method, and the specific segmentation method can be adjusted according to actual needs. After the segment length of the initial segment unit is divided and corrected, the updated segment division parameters (length, boundary, and environmental factors) are passed to the path fine-tuning module.
[0021] The path fine-tuning module is connected to the path segment division and correction module to collect and output the fine-tuning angle constraint parameters and corresponding correction parameters generated by the corrected segment units; combining the optimization algorithm to obtain the first and second fine-tuning angles, thereby adjusting the path direction and curvature; Receive the updated path information corresponding to the segment units output by the "path segment division and correction module", including the start and end points of each segment, segment length, and corresponding environmental factors and entity feature data; Calculate the angle adjustment range based on the environmental factor β and body characteristic data of each segment and curvature change threshold ; According to the formula: ;in, is the safety factor, is the average length of adjacent segments; Curvature change threshold ;in, Empirical constant, β is the environmental factor of the current segment, and L is the segment length; Adjust the angle range and curvature change threshold , as angle constraint parameter and curvature correction parameter; A chromosome encoding design is performed for each path angle, that is, each path angle can be encoded into a chromosome, where each gene represents a possible path direction angle; a candidate angle set is designed based on the constraint parameters (angle adjustment range and curvature change threshold) Where p is the number of candidate angles. Based on the above constraint parameters, each target item is normalized and a genetic algorithm (GA) is used for multi-objective optimization to construct a fitness function. ;in, is the weight coefficient, is the curvature safety penalty term, is the angle adjustment range, is the total length of the path; The genetic algorithm iterative process of selection, crossover, and mutation is performed on each chromosome. Collectively, the following steps are performed: individuals with higher fitness (path direction angle and curvature combination) are selected for reproduction; crossover: a new generation of path solutions is generated using the crossover operation, which combines the angle and curvature information of multiple candidate solutions to produce more possible solutions; mutation: to avoid the trap of local optimal solutions, a mutation operation is added to randomly adjust some angle values or curvature radius to generate new candidate solutions; a set of candidate direction angles is obtained through iterative optimization; the angle combination with the highest fitness is selected to obtain the first fine-tuning angle (direction adjustment); the curvature radius is adjusted to ensure that the path satisfies C ≤ C_max near the mutation point, resulting in the second fine-tuning angle (curvature adjustment); It should be noted that the first fine-tuning angle: the optimal direction angle combination (direction adjustment) obtained by the genetic algorithm is used to adjust the path direction to adapt to changes in the local environment and body characteristics. The second fine-tuning angle: to ensure that the path does not make excessive turns at mutation points, the curvature radius is adjusted so that the curvature meets the constraints near all mutation points. This step ensures the smoothness and executableness of the path. When the number of iterations reaches the preset upper limit, the iteration is terminated; Outputting the adjusted path includes: combining the optimized first and second fine-tuning angles to generate final path parameters, wherein the final path parameters are composed of a direction angle sequence and a curvature sequence; The optimized first fine-tuning angle (direction) and the second fine-tuning angle (curvature) are combined to generate the final path parameters, which include: a direction angle sequence: a set of direction angles for each segment and a curvature sequence: a set of curvature radii corresponding to each segment; Use Bezier curves or spline interpolation to eliminate angle mutation points and generate continuous paths.
[0022] In this implementation, segment units are dynamically divided and corrected based on environmental factors (such as water flow velocity, water depth fluctuation rate, etc.), and environmental mutation points are identified by segment merging judgment values to automatically adjust boundaries, solving the problem that traditional fixed segmentation is not suitable for complex environments; a supervision function is constructed by combining multi-dimensional parameters to accurately identify abnormal paths, and continuous abnormal state detection is introduced to distinguish risks and reduce the misjudgment rate. Auxiliary verification signals are used to supplement real-time data to update the effective data set and improve decision-making quality; a genetic algorithm is used to generate fine-tuning angles that take into account both length and safety, and Bezier curves or spline interpolation are used to eliminate mutation points and generate smooth paths to improve control safety; historical navigation density is used to avoid congestion and shorten time, and a verification mechanism is triggered based on path outliers to balance safety and cost, realizing dynamic segment management, intelligent response mechanism, multi-objective optimization and path smoothing technology, improving path planning accuracy and adaptability, and taking into account navigation safety and efficiency.
[0023] Example 2: Please refer to Figure 2 , a logistics transportation path planning method based on data analysis, comprising the following steps: Step 1: Perform path management on the target cargo transportation path of water conservancy cargo transportation, obtain each initial segment unit and record its corresponding ontological feature data and transportation environment data, obtain the path segment transportation data corresponding to each initial segment unit through data analysis, and obtain each valid path transportation data set by identifying abnormal path segments; Step 2: Perform path anomaly fine-tuning analysis based on the effective path transportation dataset, obtain path anomaly values to determine whether to perform auxiliary verification, obtain auxiliary verification feedback data based on the auxiliary verification requirements determined, and obtain a supplementary effective path transportation dataset; Step 3: Analyze the supplementary effective path segment transport data set to obtain the environmental dynamic factors and combine them with the ontological feature data of the initial segment unit to divide and modify the segment length of the initial segment unit; Step 4: The fine-tuning angle constraint parameters generated by the segment unit after acquisition and output and the corresponding correction parameters are combined with an optimization algorithm to obtain the first and second fine-tuning angles, thereby adjusting the path direction and curvature.
[0024] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters and thresholds in the formulas are set by technicians in this field according to actual conditions.
[0025] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.
Claims
1. A logistics transportation route planning system based on data analysis, characterized in that: include: The path segmentation module is used to manage the target cargo transportation path of water conservancy cargo transportation, obtain each initial segment unit and record its corresponding ontological feature data and transportation environment data, obtain the path segment transportation data corresponding to each initial segment unit through data analysis, and obtain each valid path transportation data set by identifying abnormal path segments; The auxiliary verification analysis module is used to perform path anomaly fine-tuning analysis based on the effective path transportation data set, obtain the path anomaly value to determine whether to perform auxiliary verification, obtain auxiliary verification feedback data based on the auxiliary verification requirements obtained from the judgment results, and obtain a supplementary effective path transportation data set; The route segment division and correction module is used to analyze the supplementary effective route segment transportation data set, obtain the environmental dynamic factors, and combine them with the ontological feature data of the initial segment unit to divide and correct the segment length of the initial segment unit; The path fine-tuning module is connected to the path segment division and correction module to collect and output the fine-tuning angle constraint parameters and corresponding correction parameters generated by the corrected segment unit and combine them with the optimization algorithm to obtain the first and second fine-tuning angles, thereby adjusting the path direction and curvature.
2. A logistics transportation route planning system based on data analysis according to claim 1, characterized in that: The configuration of the corresponding initial segment units for the target cargo transportation path includes: dividing the target cargo transportation path into a plurality of initial segment units of random equal lengths, namely ;in, Represents each segment unit, i is the identifier of different segment units ; n represents the number of segment units divided and ; n is a positive integer; The boundary coordinates and length of each section unit are recorded as the main feature data of the section unit. Based on the divided multiple section units, the corresponding transportation environment data of each section unit within the preset supervision period is collected, including wind speed, temperature, water flow speed, water depth, etc.: Preprocessing the transportation environment data corresponding to each of the above-mentioned section units, including cleaning and normalization, to obtain preprocessed transportation environment data; Define route segment transportation data based on pre-processed transportation environment data Including water velocity gradient , water depth fluctuation rate , historical navigation density ; The water flow velocity change gradient , according to the formula ;in, is the water velocity change gradient corresponding to different section units, is the water flow velocity corresponding to different section units, is the segment length corresponding to different segment units, Preset terrain correction coefficients corresponding to different section units; Water depth fluctuation , according to the formula ;in, is the water depth fluctuation rate corresponding to different section units, is the water depth measurement value corresponding to the number of measurements in different section units, The average water depth corresponding to different section units, The total number of measurements within the preset supervision period; Historical navigation density The passage frequency of ships in different section units is obtained through historical passage record data; According to the path segment parameters , construct the segment unit supervision function ; Among them, in the formula, Path segment data corresponding to different segment units in the preset supervision cycle; The standard range of route segment data corresponding to different segment units in the preset supervision cycle; The segment unit supervision flag contains a value of 0 or 1, indicating whether the segment status of the corresponding segment unit is normal or abnormal; By identifying abnormal route segments, the effective route transportation data sets are obtained.
3. A logistics transportation route planning system based on data analysis according to claim 2, characterized in that: When obtaining valid route transportation data sets by identifying abnormal route segments, including: Sorting and combining the section unit supervisions obtained by processing all the section units corresponding to the target cargo transportation route within the preset supervision period to obtain the section unit supervision sequence corresponding to the target cargo transportation route; Traverse and analyze the section unit supervision sequence of the target cargo transportation route and find the section unit supervision identifier with a value of 1; If there is no segment unit supervision identifier with a value of 1 in the segment unit supervision sequence, a normal instruction for the path segment unit is generated and prompted; If there is a segment unit supervision flag with a value of 1 in the segment unit supervision sequence, a path segment unit abnormal instruction is generated, and the segment unit is marked as an abnormal path segment unit according to the segment unit abnormal instruction. ; where j is the unit identifier of each abnormal path segment and ; m represents the number of abnormal path segment units; According to the marked abnormal route segments, the route segment transportation data corresponding to each abnormal route segment is extracted and marked as the valid route segment transportation data set. ; The effective path transportation data set includes the historical navigation density, water flow velocity change gradient, and water depth fluctuation rate corresponding to the abnormal path section.
4. The data analysis-based logistics transportation route planning system according to claim 1, characterized in that: The method of performing fine-tuning analysis on the path anomaly based on the valid path transport data set and obtaining the path anomaly value to determine whether to perform auxiliary verification includes: According to the marked abnormal route segments, the valid route transportation data sets corresponding to the abnormal route segments are extracted. ; For the effective path transportation dataset Each valid path transport data in the abnormal path segment is analyzed independently, and the deviation value of each valid path transport data in each abnormal path segment from the standard range of the path segment data is obtained based on the deviation value calculation formula; and the weighted sum of the deviation value of each valid path transport data in each abnormal path segment is obtained to obtain the path abnormal value corresponding to each abnormal path segment. ; Path outliers With threshold Make comparisons; When the path outlier Not less than the threshold When the vehicle is in the vicinity of the designated position, a navigation alarm is issued; When the path outlier Less than threshold When the auxiliary verification is needed, it is determined based on the valid path transport data set whether it is needed. When it is determined that the auxiliary verification is needed, the abnormal path segment unit is determined based on the valid path data set and the path abnormality value; and an auxiliary verification signal is sent to the corresponding abnormal path segment unit.
5. A logistics transportation route planning system based on data analysis according to claim 4, characterized in that: Determine whether auxiliary verification is needed based on the valid path dataset; including: Collect each abnormal path section unit within the preset detection period Corresponding path outlier value , and check the current abnormal path segment unit Is there a path anomaly value of k consecutive abnormal points in all monitoring times within the preset detection period? approaching the threshold; If it does not exist, it means that there is no continuous abnormal state and there is no need to perform the supplementary operation of the finite path transportation data set; If it exists, it means there is a continuous abnormal state, and the corresponding abnormal path segment unit Mark as requiring auxiliary verification unit, send auxiliary verification signal to the corresponding abnormal path segment unit, and receive navigation monitoring feedback results from the segment unit, including actual track deviation value and ship draft depth change rate; According to the navigation monitoring feedback results received from the section unit, the navigation monitoring feedback results are added to the effective path data set to obtain a supplementary effective path section transportation data set. ; The supplementary effective path section transportation data set consists of basic effective path section transportation data and actual trajectory deviation value, and ship draft depth change rate.
6. The data analysis-based logistics transportation route planning system according to claim 1, characterized in that: Data analysis is performed on the supplementary effective path segment transport data set to obtain environmental dynamic factors and combine them with the ontological characteristic data of the initial segment unit to divide and modify the segment length of the initial segment unit; including: After normalizing all types of data in the transportation dataset of each supplementary effective path section, the environmental factors corresponding to each abnormal path section unit are obtained by weighted summation. ; Based on the environmental factors corresponding to each abnormal path segment unit And its corresponding ontological feature data, perform segment unit correlation analysis, and determine segment merging and segmentation strategies; specifically, the ontological feature data includes: segment boundary coordinates and length of each abnormal path segment unit; Starting from the first abnormal path segment unit among all abnormal path segment units, the environmental factor difference between adjacent abnormal path segment units is calculated to obtain the segment merging judgment value. ; Where v represents the identifier of each adjacent abnormal path segment unit; when v=1, it is the difference value of the environmental factor between the first abnormal path segment unit and the second abnormal path segment unit, and so on; Merge segments to determine the value Its preset threshold Make comparisons; When the segment merges, the judgment value Less than the preset threshold When , the segment boundaries between the corresponding adjacent abnormal path segment units are removed; and multiple initial segment units A are updated to generate continuous new segment units ; When the segment merges, the judgment value Greater than the preset threshold When , the boundary between adjacent segments is marked as the mutation point of environmental factors; a new segment boundary is added at the mutation point, and the original adjacent segment is divided into two independent segments; and multiple initial segment units A are updated to generate continuous new segment units .
7. The data analysis-based logistics transportation route planning system according to claim 1, characterized in that: Collect the fine-tuning angle constraint parameters and corresponding correction parameters generated by the modified segment unit, and combine them with the optimization algorithm to obtain the first and second fine-tuning angles, thereby adjusting the path direction and curvature; including: the path information corresponding to the updated segment unit, including the start and end points of each segment, segment length and corresponding environmental factors and body feature data, Calculate the angle adjustment range based on the environmental factor β and body characteristic data of each segment and curvature change threshold ; According to the formula: ;in, is the safety factor, is the difference in environmental factors between adjacent sections, is the sum of the environmental factors of two adjacent sections, is the average length of adjacent segments; Curvature change threshold ;in, Empirical constant, is the environmental factor of the jth segment, is the length of the jth segment; Adjust the angle range and curvature change threshold , as angle constraint parameter and curvature correction parameter; Perform chromosome encoding design on each path angle to obtain multiple chromosomes; obtain a set of candidate angles based on constraint parameters including angle adjustment range and curvature change threshold. Where p is the number of candidate angles; Based on the above constraint parameters, a genetic algorithm is used for multi-objective optimization to construct a fitness function. ;in, is the weight coefficient, is the curvature safety penalty term, is the angle adjustment range, is the total length of the path; The genetic algorithm iterative process for each chromosome includes selection, crossover, and mutation. Through iterative optimization, a set of candidate direction angles is obtained. The angle combination with the highest fitness is selected to obtain the first fine-tuning angle. The curvature radius is adjusted, and the second fine-tuning angle is obtained based on the path satisfying C ≤ C_max near the mutation point. When the number of iterations reaches the preset upper limit, the iteration is terminated; Outputting the adjusted path includes: merging the optimized first fine-tuning angle and the second fine-tuning angle to generate final path parameters; Use Bezier curves or spline interpolation to eliminate angle mutation points and generate continuous paths.
8. The data analysis-based logistics transportation route planning system according to claim 7, characterized in that: The first fine-tuning angle is composed of a set of direction angles of each segment; the second fine-tuning angle is composed of a set of curvature radii corresponding to each segment.
9. A logistics transportation route planning system based on data analysis according to claims 1-8, characterized in that: A logistics transportation route planning method based on data analysis is provided, comprising the following steps: Step 1: Perform path management on the target cargo transportation path of water conservancy cargo transportation, obtain each initial segment unit and record its corresponding ontological feature data and transportation environment data, obtain the path segment transportation data corresponding to each initial segment unit through data analysis, and obtain each valid path transportation data set by identifying abnormal path segments; Step 2: Perform path anomaly fine-tuning analysis based on the effective path transportation dataset, obtain path anomaly values to determine whether to perform auxiliary verification, obtain auxiliary verification feedback data based on the auxiliary verification requirements determined, and obtain a supplementary effective path transportation dataset; Step 3: Analyze the supplementary effective path segment transport data set to obtain the environmental dynamic factors and combine them with the ontological feature data of the initial segment unit to divide and modify the segment length of the initial segment unit; Step 4: The fine-tuning angle constraint parameters generated by the segment unit after acquisition and output and the corresponding correction parameters are combined with an optimization algorithm to obtain the first and second fine-tuning angles, thereby adjusting the path direction and curvature.