CN118917513A - Vehicle route optimization method and system based on big data - Google Patents

Abstract

The invention discloses a vehicle route optimization method and system based on big data, the content comprises data acquisition, data preprocessing, route comprehensive evaluation, route decision community construction, decision optimization and vehicle route optimization. The invention relates to the technical field of vehicle route planning, in particular to a vehicle route optimization method and system based on big data, wherein the scheme is used for preparing a more reasonable and efficient route through designing a direction factor, designing a trafficability detection factor, evaluating route safety and evaluating route stability, and improving the scientificity and accuracy of the evaluation; the bandwidth adjustment function and the community density function are designed, so that the decision basis is more comprehensive and accurate; the community center evolution strategy is designed, so that the decision process is more scientific and reasonable; the searching weight, the parameter area searching method and the parameter fine searching method are designed, so that the searching process is more strategic and targeted, and the quality and the adaptability of route decision are improved.

Description

Vehicle route optimization method and system based on big data

Technical Field

The present invention relates to the technical field of vehicle route planning, and in particular to a vehicle route optimization method and system based on big data.

Background Art

The vehicle route optimization method and system based on big data uses big data technology and artificial intelligence algorithms to achieve accurate planning of vehicle routes. However, the traditional vehicle route comprehensive evaluation method has the problems of incomplete, intricate and inaccurate evaluation; the traditional route decision community construction method has the problem of insufficient flexibility and adaptability of decision-making; the traditional route decision method has the problem of low quality and adaptability of route decisions due to improper parameter selection.

Summary of the invention

In view of the above situation, in order to overcome the defects of the prior art, the present invention provides a vehicle route optimization method and system based on big data. In view of the problems of incomplete, indetailed and inaccurate evaluation in the traditional comprehensive evaluation method of vehicle routes, this solution conducts a comprehensive evaluation of the route by establishing a route evaluation coordinate system, designing direction factors, designing trafficability detection factors, route safety evaluation and route stability evaluation, so as to evaluate the route more comprehensively and meticulously, more accurately reflect the actual situation and the influence of various complex factors on the route, formulate a more reasonable and efficient route, and improve the scientificity and accuracy of the evaluation; in view of the problems of insufficient flexibility and adaptability of decision-making in the traditional method of building a route decision community, this solution constructs a detailed route decision community to optimize the route. The bandwidth adjustment function and community density function are designed to make the decision basis more comprehensive and accurate, and improve the flexibility and adaptability of decision-making; the community center initialization and evolution strategy are adopted, and the stability and dynamic changes of the community are considered, which can classify and make decisions on routes more reasonably, making the decision process more scientific and reasonable; in view of the problem of low quality and adaptability of route decisions caused by improper parameter selection in traditional route decision methods, this scheme makes the search process more strategic and targeted by designing search weights, parameter area search methods and parameter fine search methods, and can find the optimal parameters more efficiently; at the same time, the optimization effect evaluation index is designed to measure the optimization effect more comprehensively and accurately, realize decision optimization more accurately, and improve the quality and adaptability of route decisions.

The technical solution adopted by the present invention is as follows: a vehicle route optimization method and system based on big data, the method comprising the following steps:

Step S1: data collection;

Step S2: data preprocessing;

Step S3: comprehensive route evaluation;

Step S4: constructing a route decision community;

Step S5: decision optimization;

Step S6: Vehicle route optimization.

Furthermore, in step S1, the data collection is to collect historical vehicle position data, vehicle status data, road condition data, weather data and average time per kilometer of the route; the position data includes longitude and latitude; the vehicle status data includes vehicle speed, acceleration and direction angle; the road condition data includes traffic flow, traffic light data and impassable traffic intersection data; the weather data includes temperature, precipitation and wind speed.

Furthermore, in step S2, the data preprocessing cleans the data, corrects erroneous data, removes duplicate data, and fills in missing data; and standardizes the data to unify the format and range of the data.

Furthermore, in step S3, the route comprehensive evaluation specifically includes the following steps:

Step S31: Establishing a route evaluation coordinate system, establishing a plane rectangular coordinate system with the vehicle position as the origin, and setting the coordinate system as the route evaluation coordinate system;

Step S32: Design the directional factor, which is expressed as follows:

;

Among them, h and G represent the current position and target position of the vehicle respectively. represents the direction factor between the vehicle's current position and the target position, q1 represents the guidance weight, The ordinate of the vehicle's current position. The ordinate of the target position. Indicates taking the absolute value, is the distance between the current position and the target point on the ordinate, Represents the Euclidean distance between the current position and the target position, Indicates the angle between the vehicle’s current orientation and the target position. represents the cosine function, represents the path curvature, represents the total angle of change in the vehicle's orientation as it moves along the path from h to G, represents the control parameter, and e represents the natural constant;

Step S33: Design a trafficability detection factor, which is expressed as follows:

;

Where V represents the index of the traffic decision location, represents the trafficability detection factor between the vehicle's current position and the Vth traffic decision position to the target position, Indicates the radius of travel without delay. represents the Euclidean distance between the vehicle's current position and the Vth traffic decision position to the target position;

Step S34: Route safety assessment, measuring the safety of the current location route, expressed as follows:

;

in, Indicates the line safety assessment value of the vehicle’s current location, Indicates the number of inaccessible locations among all traffic decision locations connected to the vehicle’s current location. Represents the number of all traffic decision positions connected to the current position of the vehicle;

Step S35: Route stability evaluation, expressed as follows:

;

in, The line stability evaluation value of the vehicle’s current position, Represents the factorial symbol;

Step S36: Comprehensive evaluation, expressed as follows:

;

in, represents the comprehensive route evaluation score from the vehicle's current location to the Vth traffic decision location to the target location, and They represent the deviation parameter and adjustment rate from the current position of the vehicle to the Vth traffic decision position to the target position, respectively. represents the set of all traffic decision locations connected to the vehicle’s current location, represents the symbol, a represents the element index of the traffic decision location set, and They represent the deviation parameter and adjustment rate from the current position of the vehicle to the ath traffic decision position to the target position, respectively. represents the trafficability detection factor between the current position of the vehicle and the ath traffic decision position to the target location, represents the direction factor between the vehicle's current position and the Vth traffic decision position to the target position, represents the direction factor between the vehicle's current position and the ath traffic decision position to the target position, and is the importance weight; all routes from the current location to the target location are counted, the comprehensive route evaluation score of all traffic decision locations on each route and the current location is calculated, the scores are summed up, and the comprehensive route evaluation score of each route is obtained.

Furthermore, in step S4, the construction of the route decision community specifically includes the following steps:

Step S41: constructing a route decision individual, performing a comprehensive route evaluation on the vehicle data, and calculating the route with the highest comprehensive route evaluation score; constructing a route decision individual, the individual is composed of the following feature data: vehicle location data, vehicle status data, road condition data, weather data, and the route with the highest comprehensive route evaluation score;

Step S42: Design a bandwidth adjustment function, which is expressed as follows:

;

Where i represents the index of the route decision individual, represents the i-th individual in the route decision community, m represents the scale parameter, represents the bandwidth adjustment function, It means taking the median, represents the individual closest to the i-th individual in the route decision community, represents the scale transformation factor;

Step S43: Design a community density function, calculate the Euclidean distance between the two individuals with the longest distance among all route decision individuals, and set this distance as the neighborhood width; set the area within 0.5 times the neighborhood width centered on the route decision individual as the neighborhood of the route decision individual, and calculate the community density value of the individual, which is expressed as follows:

;

in, represents the community density value of the i-th individual in the route decision community, j represents the neighborhood individual index of the i-th individual in the route decision community, represents the jth individual in the neighborhood of the i-th individual in the route decision community, E represents the Euclidean distance between the i-th individual in the route decision community and the j-th individual in the neighborhood;

Step S44: Initialize the community center, set 0.25 times the neighborhood width as the community width, calculate the community density of all route decision individuals, select the point with the highest community density as the first initial community center, calculate the community density of all remaining individuals except the selected community center point and the individuals within its community width, select the point with the highest community density as the initial community center again, repeat the operation until the number of remaining individuals is less than the number of selected community centers, calculate the average position of the remaining individuals, select the individual closest to the average position, and set it as the last community center;

Step S45: community member allocation, calculating the association value between community individuals and all community centers, and allocating community individuals to the community to which the community center with the highest association degree belongs, as shown below:

;

Where n represents the index of the community center, represents the nth community center, represents the community association value between the i-th route decision individual and the n-th community center, and represents the relevance weight, represents the Euclidean distance between the i-th route decision individual and the n-th community center;

Step S46: Community center evolution, introduce a training factor that is dynamically adjusted according to the stability of the community and a stability factor that controls the change speed of the community center, and design a community center evolution strategy, which is expressed as follows:

;

Among them, it represents the number of times the community center evolves, represents the nth community center during the it+1th community center evolution, represents the nth community center during the itth community center evolution, represents the training factor of the nth community center during the itth community center evolution, O represents the total number of route decision individuals in the nth community, represents the average offset between all route decision individuals in the nth community and the community center, represents the stability factor of the nth community during the itth community center evolution, It represents the position change of the nth community center from the it-1th community center evolution to the itth community center evolution;

Step S47: A route decision community is formed, and steps S44 to S45 are repeated until the center of the route decision community no longer changes.

Furthermore, in step S5, the decision optimization specifically includes the following steps:

Step S51: Optimization preparation, optimizing the entire route decision process by searching for parameters in the decision process, the parameters include guidance weight, control parameter, importance weight, scale transformation factor and relevance weight, creating a search space for route decision parameters, and randomly generating an initial route decision parameter search point group in the search space;

Step S52: preparing for optimization effect evaluation, setting the average of the reciprocals of the average time per kilometer corresponding to the route with the highest comprehensive route evaluation score of all route decision individuals in the community as the route decision optimization effect evaluation index;

Step S53: Design search weights, expressed as follows:

;

;

in, represents the first search weight, represents the second search weight, It represents a number that decreases linearly from 2 to 0 in steps of 0.5. Represents a random number ranging from 0 to 1;

Step S54: Designing a route decision parameter area search method, as shown below:

;

Where t represents the number of optimization searches. Indicates the location of the regional search parameters during the t+1th optimization search. Indicates the location of the parameter search point with the maximum value of the evaluation index of the current route decision optimization effect. Indicates the location of the regional search parameters during the t-th optimization search. It means taking the Chebyshev distance between two positions;

Step S55: Design a route decision parameter fine search method, the formula is as follows:

;

in, Indicates the position of the refined search parameters during the t+1th optimization search. , and They respectively represent the 2nd, 3rd, and 4th parameter positions of the route decision optimization effect evaluation index values arranged from high to low in the search points of the regional search during the t+1th optimization search;

Step S56: Decision optimization search, setting the optimization effect threshold, setting the maximum number of optimization searches, calculating the route decision optimization effect evaluation index value of the initial search point group, finding the position of the parameter search point with the largest value of the current route decision optimization effect evaluation index, first performing a regional search, then performing a fine search, calculating the route decision optimization effect evaluation index value of the searched parameter point, adding one to the number of searches, if there is a parameter point with a route decision optimization effect evaluation index value greater than the optimization effect threshold, setting the parameters of the search point with the largest value of the current route decision optimization effect evaluation index as the parameters of the route decision; if the maximum number of optimization searches is reached, re-perform the optimization search; otherwise, continue searching.

Furthermore, in step S6, the vehicle route optimization is performed by collecting vehicle information in real time, performing a comprehensive route evaluation, adding the evaluated new data to the constructed original route decision community data, reconstructing the route decision community, finding the route decision community to which the new data belongs, and selecting the route of the community center point as the optimal route for the vehicle.

The vehicle route optimization system based on big data provided by the present invention includes a data acquisition module, a data preprocessing module, a route comprehensive evaluation module, a route decision community building module, a decision optimization module and a vehicle route optimization module;

The data acquisition module collects historical vehicle location data, vehicle status data, road condition data, weather data and average time per kilometer of the route, and sends the data to the data preprocessing module;

The data preprocessing module receives the data sent by the data acquisition module, performs data preprocessing on the received data, and sends the preprocessed data to the route comprehensive evaluation module;

The route comprehensive evaluation module receives the data sent by the data preprocessing module, performs a comprehensive evaluation on the route, and sends the data to the route decision community construction module;

The route decision community building module receives data sent by the route comprehensive evaluation module, builds a route decision community, and sends the data to the decision optimization module;

The decision optimization module receives data sent by the route decision building community module, optimizes parameters of the route decision process, and sends the data to the vehicle route optimization module;

The vehicle route optimization module receives data from the decision optimization module, collects vehicle information in real time, performs a comprehensive route evaluation, adds the evaluated new data to the constructed original route decision community data, reconstructs the route decision community, finds the route decision community to which the new data belongs, and selects the route of the community center point as the optimal route for the vehicle.

The beneficial effects achieved by the present invention using the above scheme are as follows:

(1) In view of the problems of incomplete, intricate and inaccurate evaluation in traditional vehicle route comprehensive evaluation methods, this scheme conducts a comprehensive evaluation of routes by establishing a route evaluation coordinate system, designing direction factors, designing trafficability detection factors, route safety evaluation and route stability evaluation. This scheme evaluates routes more comprehensively and meticulously, more accurately reflects the actual situation and the impact of various complex factors on routes, and formulates more reasonable and efficient routes, thus improving the scientificity and accuracy of the evaluation.

(2) In order to address the problem of insufficient flexibility and adaptability of decision-making in the traditional method of building route decision communities, this scheme constructs detailed route decision individuals and designs bandwidth adjustment functions and community density functions to make the decision basis more comprehensive and accurate, thereby improving the flexibility and adaptability of decision-making. It also adopts community center initialization and evolution strategies, taking into account the stability and dynamic changes of the community, and can more reasonably classify and decide on routes, making the decision process more scientific and reasonable.

(3) In order to address the problem of low quality and adaptability of route decisions caused by improper parameter selection in traditional route decision methods, this solution designs search weights, parameter area search methods, and parameter fine search methods to make the search process more strategic and targeted, and to find the optimal parameters more efficiently. At the same time, it designs optimization effect evaluation indicators to measure the optimization effect more comprehensively and accurately, achieve decision optimization more accurately, and improve the quality and adaptability of route decisions.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is a schematic diagram of a process flow of a vehicle route optimization method based on big data provided by the present invention;

FIG2 is a schematic diagram of a vehicle route optimization system based on big data provided by the present invention;

FIG3 is a schematic diagram of the process of step S3;

FIG4 is a schematic diagram of the process of step S4;

FIG5 is a schematic flow chart of step S5.

The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

DETAILED DESCRIPTION

The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

In the description of the present invention, it should be understood that terms such as “upper”, “lower”, “front”, “back”, “left”, “right”, “top”, “bottom”, “inside” and “outside” indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore should not be understood as limiting the present invention.

Embodiment 1, referring to FIG1 , the vehicle route optimization method based on big data provided by the present invention comprises the following steps:

Step S1: Data collection, collecting historical vehicle location data, vehicle status data, road condition data, weather data and average time per kilometer of the route;

Step S2: data preprocessing, data cleaning and data standardization;

Step S3: Comprehensive evaluation of the route, by establishing a route evaluation coordinate system, designing a direction factor, designing a trafficability detection factor, a route safety evaluation, and a route stability evaluation to comprehensively evaluate the route;

Step S4: constructing a route decision community, by constructing route decision individuals, designing bandwidth adjustment functions, designing community density functions, initializing community centers, allocating community members, and evolving community centers;

Step S5: decision optimization, optimizing the parameters of the decision process by optimizing preparation, optimizing effect evaluation preparation, designing search weights, designing route decision parameter area search methods, and designing route decision parameter fine search methods;

Step S6: Vehicle route optimization, by collecting vehicle information in real time, conducting a comprehensive route evaluation, reconstructing the route decision community, finding the route decision community to which the new data belongs, and selecting the route at the center of the community as the optimal route for the vehicle.

Embodiment 2, referring to FIG. 1 , this embodiment is based on the above embodiment. In step S1 , the data collection is to collect historical vehicle position data, vehicle status data, road condition data and average time per kilometer of the route; the position data includes longitude and latitude; the vehicle status data includes vehicle speed, acceleration and direction angle; the road condition data includes traffic flow, traffic light data and impassable traffic intersection data; the weather data includes temperature, precipitation and wind speed.

Embodiment 3, referring to FIG1 , this embodiment is based on the above embodiment. In step S2 , the data preprocessing cleans the data, corrects erroneous data, removes duplicate data, and fills in missing data; the data is standardized to unify the format and range of the data.

Embodiment 4, referring to FIG. 1 and FIG. 3 , this embodiment is based on the above embodiment. In step S3, the route comprehensive evaluation specifically includes the following steps:

Step S31: Establishing a route evaluation coordinate system, establishing a plane rectangular coordinate system with the vehicle position as the origin, and setting the coordinate system as the route evaluation coordinate system;

Step S32: Design the directional factor, which is expressed as follows:

;

Among them, h and G represent the current position and target position of the vehicle respectively. represents the direction factor between the vehicle's current position and the target position, q1 represents the guidance weight, The ordinate of the vehicle's current position. The ordinate of the target position. Indicates taking the absolute value, is the distance between the current position and the target point on the ordinate, Represents the Euclidean distance between the current position and the target position, Indicates the angle between the vehicle’s current orientation and the target position. represents the cosine function, represents the path curvature, represents the total angle of change in the vehicle's orientation as it moves along the path from h to G, represents the control parameter, and e represents the natural constant;

Step S33: Design a trafficability detection factor, which is expressed as follows:

;

Where V represents the index of the traffic decision location, represents the trafficability detection factor between the vehicle's current position and the Vth traffic decision position to the target position, Indicates the radius of travel without delay. represents the Euclidean distance between the vehicle's current position and the Vth traffic decision position to the target position;

Step S34: Route safety assessment, measuring the safety of the current location route, expressed as follows:

;

in, Indicates the line safety assessment value of the vehicle’s current location, Indicates the number of inaccessible locations among all traffic decision locations connected to the vehicle’s current location. Represents the number of all traffic decision positions connected to the current position of the vehicle;

Step S35: Route stability evaluation, expressed as follows:

;

in, The line stability evaluation value of the vehicle’s current position, Represents the factorial symbol;

Step S36: Comprehensive evaluation, expressed as follows:

;

in, represents the comprehensive route evaluation score from the vehicle's current location to the Vth traffic decision location to the target location, and They represent the deviation parameter and adjustment rate from the current position of the vehicle to the Vth traffic decision position to the target position, respectively. represents the set of all traffic decision locations connected to the vehicle’s current location, represents the symbol, a represents the element index of the traffic decision location set, and They represent the deviation parameter and adjustment rate from the current position of the vehicle to the ath traffic decision position to the target position, respectively. represents the trafficability detection factor between the current position of the vehicle and the ath traffic decision position to the target location, represents the direction factor between the vehicle's current position and the Vth traffic decision position to the target position, represents the direction factor between the vehicle's current position and the ath traffic decision position to the target position, and is the importance weight; all routes from the current location to the target location are counted, the comprehensive route evaluation score of all traffic decision locations on each route and the current location is calculated, the scores are summed up, and the comprehensive route evaluation score of each route is obtained.

By executing the above operations, in order to address the problems of incomplete, intricate and inaccurate evaluation in the traditional comprehensive evaluation method of vehicle routes, this solution conducts a comprehensive evaluation of the route by establishing a route evaluation coordinate system, designing direction factors, designing trafficability detection factors, route safety evaluation and route stability evaluation. It evaluates the route more comprehensively and meticulously, more accurately reflects the actual situation and the impact of various complex factors on the route, formulates a more reasonable and efficient route, and improves the scientificity and accuracy of the evaluation.

Embodiment 5, referring to FIG. 1 and FIG. 4 , this embodiment is based on the above embodiment. In step S4, the construction of the route decision community specifically includes the following steps:

Step S41: constructing a route decision individual, performing a comprehensive route evaluation on the vehicle data, and calculating the route with the highest comprehensive route evaluation score; constructing a route decision individual, the individual is composed of the following feature data: vehicle location data, vehicle status data, road condition data, weather data, and the route with the highest comprehensive route evaluation score;

Step S42: Design a bandwidth adjustment function, which is expressed as follows:

;

Where i represents the index of the route decision individual, represents the i-th individual in the route decision community, m represents the scale parameter, represents the bandwidth adjustment function, It means taking the median, represents the individual closest to the i-th individual in the route decision community, represents the scale transformation factor;

Step S43: Design a community density function, calculate the Euclidean distance between the two individuals with the longest distance among all route decision individuals, and set this distance as the neighborhood width; set the area within 0.5 times the neighborhood width centered on the route decision individual as the neighborhood of the route decision individual, and calculate the community density value of the individual, which is expressed as follows:

;

in, represents the community density value of the i-th individual in the route decision community, j represents the neighborhood individual index of the i-th individual in the route decision community, represents the jth individual in the neighborhood of the i-th individual in the route decision community, represents the Euclidean distance between the i-th individual in the route decision community and the j-th individual in the neighborhood;

Step S44: Initialize the community center, set 0.25 times the neighborhood width as the community width, calculate the community density of all route decision individuals, select the point with the highest community density as the first initial community center, calculate the community density of all remaining individuals except the selected community center point and the individuals within its community width, select the point with the highest community density as the initial community center again, repeat the operation until the number of remaining individuals is less than the number of selected community centers, calculate the average position of the remaining individuals, select the individual closest to the average position, and set it as the last community center;

Step S45: community member allocation, calculating the association value between community individuals and all community centers, and allocating community individuals to the community to which the community center with the highest association degree belongs, as shown below:

;

Where n represents the index of the community center, represents the nth community center, represents the community association value between the i-th route decision individual and the n-th community center, and represents the relevance weight, represents the Euclidean distance between the i-th route decision individual and the n-th community center;

Step S46: Community center evolution, introduce a training factor that is dynamically adjusted according to the stability of the community and a stability factor that controls the change speed of the community center, and design a community center evolution strategy, which is expressed as follows:

;

Among them, it represents the number of times the community center evolves, represents the nth community center during the it+1th community center evolution, represents the nth community center during the itth community center evolution, represents the training factor of the nth community center during the itth community center evolution, O represents the total number of route decision individuals in the nth community, represents the average offset between all route decision individuals in the nth community and the community center, represents the stability factor of the nth community during the itth community center evolution, It represents the position change of the nth community center from the it-1th community center evolution to the itth community center evolution;

Step S47: A route decision community is formed, and steps S44 to S45 are repeated until the center of the route decision community no longer changes.

By performing the above operations, in order to address the problem of insufficient flexibility and adaptability of decision-making in the traditional method of building route decision communities, this solution constructs detailed route decision individuals, designs bandwidth adjustment functions and community density functions, makes the decision basis more comprehensive and accurate, and improves the flexibility and adaptability of decision-making; adopts community center initialization and evolution strategy, takes into account the stability and dynamic changes of the community, can classify and decide on routes more reasonably, and make the decision process more scientific and reasonable.

Embodiment 6, referring to FIG. 1 and FIG. 5 , this embodiment is based on the above embodiment. In step S5, the decision optimization specifically includes the following steps:

Step S51: Optimization preparation, optimizing the entire route decision process by searching for parameters in the decision process, the parameters include guidance weight, control parameter, importance weight, scale transformation factor and relevance weight, creating a search space for route decision parameters, and randomly generating an initial route decision parameter search point group in the search space;

Step S52: preparing for optimization effect evaluation, setting the average of the reciprocals of the average time per kilometer corresponding to the route with the highest comprehensive route evaluation score of all route decision individuals in the community as the route decision optimization effect evaluation index;

Step S53: Design search weights, expressed as follows:

;

;

in, represents the first search weight, represents the second search weight, It represents a number that decreases linearly from 2 to 0 in steps of 0.5. Represents a random number ranging from 0 to 1;

Step S54: Design a route decision parameter area search method, as shown below:

;

Where t represents the number of optimization searches. Indicates the location of the regional search parameters during the t+1th optimization search. Indicates the location of the parameter search point with the maximum value of the evaluation index of the current route decision optimization effect. Indicates the location of the regional search parameters during the t-th optimization search. It means taking the Chebyshev distance between two positions;

Step S55: Design a route decision parameter fine search method, the formula is as follows:

;

in, Indicates the position of the refined search parameters during the t+1th optimization search. , and They respectively represent the 2nd, 3rd, and 4th parameter positions of the route decision optimization effect evaluation index values arranged from high to low in the search points of the regional search during the t+1th optimization search;

Step S56: Decision optimization search, setting the optimization effect threshold, setting the maximum number of optimization searches, calculating the route decision optimization effect evaluation index value of the initial search point group, finding the position of the parameter search point with the largest value of the current route decision optimization effect evaluation index, first performing a regional search, then performing a fine search, calculating the route decision optimization effect evaluation index value of the searched parameter point, adding one to the number of searches, if there is a parameter point with a route decision optimization effect evaluation index value greater than the optimization effect threshold, setting the parameters of the search point with the largest value of the current route decision optimization effect evaluation index as the parameters of the route decision; if the maximum number of optimization searches is reached, re-perform the optimization search; otherwise, continue searching.

By performing the above operations, in order to address the problem of low quality and adaptability of route decisions caused by improper parameter selection in traditional route decision methods, this solution designs search weights, parameter area search methods and parameter fine search methods to make the search process more strategic and targeted, and can find the optimal parameters more efficiently. At the same time, it designs optimization effect evaluation indicators to measure the optimization effect more comprehensively and accurately, realize decision optimization more accurately, and improve the quality and adaptability of route decisions.

Embodiment 7, referring to FIG1 , this embodiment is based on the above embodiment. In step S6, the vehicle route optimization is to collect vehicle information in real time, conduct a comprehensive route evaluation, add the evaluated new data to the constructed original route decision community data, reconstruct the route decision community, find the route decision community to which the new data belongs, and select the route of the community center point as the optimal route for the vehicle.

Embodiment 8, referring to FIG2 , this embodiment is based on the above embodiment, and the vehicle route optimization system based on big data provided by the present invention includes a data acquisition module, a data preprocessing module, a route comprehensive evaluation module, a route decision community construction module, a decision optimization module and a vehicle route optimization module;

The data acquisition module collects historical vehicle position data, vehicle status data, road condition data and average time per kilometer of the route, and sends the data to the data preprocessing module;

The data preprocessing module receives the data sent by the data acquisition module, performs data preprocessing on the received data, and sends the preprocessed data to the route comprehensive evaluation module;

The route comprehensive evaluation module receives the data sent by the data preprocessing module, performs a comprehensive evaluation on the route, and sends the data to the route decision community construction module;

The route decision community building module receives data sent by the route comprehensive evaluation module, builds a route decision community, and sends the data to the decision optimization module;

The decision optimization module receives data sent by the route decision building community module, optimizes parameters of the route decision process, and sends the data to the vehicle route optimization module;

The vehicle route optimization module receives data from the decision optimization module, collects vehicle information in real time, performs a comprehensive route evaluation, adds the evaluated new data to the constructed original route decision community data, reconstructs the route decision community, finds the route decision community to which the new data belongs, and selects the route of the community center point as the optimal route for the vehicle.

It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

While the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that many changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the invention.

The present invention and its embodiments are described above, and such description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if ordinary technicians in the field are inspired by it, without departing from the purpose of the invention, they can design a structure and embodiment similar to the technical solution without creativity, which should belong to the protection scope of the present invention.

Claims (5)

1. A vehicle route optimization method based on big data, characterized in that the method comprises the following steps: Step S1: Data collection, collecting historical vehicle location data, vehicle status data, road condition data, weather data and average time per kilometer of the route; Step S2: data preprocessing, data cleaning and data standardization; Step S3: Comprehensive evaluation of the route, by establishing a route evaluation coordinate system, designing a direction factor, designing a trafficability detection factor, a route safety evaluation, and a route stability evaluation to comprehensively evaluate the route; Step S4: constructing a route decision community, by constructing route decision individuals, designing bandwidth adjustment functions, designing community density functions, initializing community centers, allocating community members, and evolving community centers; Step S5: decision optimization, optimizing the parameters of the decision process by optimizing preparation, optimizing effect evaluation preparation, designing search weights, designing route decision parameter area search methods, and designing route decision parameter fine search methods; Step S6: Vehicle route optimization, by collecting vehicle information in real time, conducting a comprehensive route evaluation, adding the evaluated new data to the constructed original route decision community data, reconstructing the route decision community, finding the route decision community to which the new data belongs, and selecting the route at the community center as the optimal route for the vehicle. 2. The vehicle route optimization method based on big data according to claim 1 is characterized in that: in step S3, the route comprehensive evaluation specifically includes the following steps: Step S31: Establishing a route evaluation coordinate system, establishing a plane rectangular coordinate system with the vehicle position as the origin, and setting the coordinate system as the route evaluation coordinate system; Step S32: Design the directional factor, which is expressed as follows: ; Among them, h and G represent the current position and target position of the vehicle respectively. represents the direction factor between the vehicle's current position and the target position, q1 represents the guidance weight, The ordinate of the vehicle's current position. The ordinate of the target position. Indicates taking the absolute value, is the distance between the current position and the target point on the ordinate, Represents the Euclidean distance between the current position and the target position, Indicates the angle between the vehicle’s current orientation and the target position. represents the cosine function, represents the path curvature, represents the total angle of change in the vehicle's orientation as it moves along the path from h to G, represents the control parameter, and e represents the natural constant; Step S33: Design a trafficability detection factor, which is expressed as follows: ; Where V represents the index of the traffic decision location, represents the trafficability detection factor between the vehicle's current position and the Vth traffic decision position to the target position, Indicates the radius of travel without delay. represents the Euclidean distance between the vehicle's current position and the Vth traffic decision position to the target position; Step S34: Route safety assessment, measuring the safety of the current location route, expressed as follows: ; in, Indicates the line safety assessment value of the vehicle’s current location, Indicates the number of inaccessible locations among all traffic decision locations connected to the vehicle’s current location. Represents the number of all traffic decision positions connected to the current position of the vehicle; Step S35: Route stability evaluation, expressed as follows: ; in, The line stability evaluation value of the vehicle’s current position, Represents the factorial symbol; Step S36: Comprehensive evaluation, expressed as follows: ; in, represents the comprehensive route evaluation score from the vehicle's current location to the Vth traffic decision location to the target location, and They represent the deviation parameter and adjustment rate from the current position of the vehicle to the Vth traffic decision position to the target position, respectively. represents the set of all traffic decision locations connected to the vehicle’s current location, represents the symbol, a represents the element index of the traffic decision location set, and They represent the deviation parameter and adjustment rate from the current position of the vehicle to the ath traffic decision position to the target position, respectively. represents the trafficability detection factor between the current position of the vehicle and the ath traffic decision position to the target location, represents the direction factor between the vehicle's current position and the Vth traffic decision position to the target position, represents the direction factor between the vehicle's current position and the ath traffic decision position to the target position, and is the importance weight; count all routes from the current location to the target location, calculate the comprehensive route evaluation score of all traffic decision locations on each route and the current location, sum the scores, and get the comprehensive route evaluation score of each route; In step S4, the construction of the route decision community specifically includes the following steps: Step S41: constructing a route decision individual, performing a comprehensive route evaluation on the vehicle data, and calculating the route with the highest comprehensive route evaluation score; constructing a route decision individual, the individual is composed of the following feature data: vehicle location data, vehicle status data, road condition data, weather data, and the route with the highest comprehensive route evaluation score; Step S42: Design a bandwidth adjustment function, which is expressed as follows: ; Where i represents the index of the route decision individual, represents the i-th individual in the route decision community, m represents the scale parameter, represents the bandwidth adjustment function, It means taking the median, represents the individual closest to the i-th individual in the route decision community, represents the scale transformation factor; Step S43: Design a community density function, calculate the Euclidean distance between the two individuals with the longest distance among all route decision individuals, and set this distance as the neighborhood width; set the area within 0.5 times the neighborhood width centered on the route decision individual as the neighborhood of the route decision individual, and calculate the community density value of the individual, which is expressed as follows: ; in, represents the community density value of the i-th individual in the route decision community, j represents the neighborhood individual index of the i-th individual in the route decision community, represents the jth individual in the neighborhood of the i-th individual in the route decision community, represents the Euclidean distance between the i-th individual in the route decision community and the j-th individual in the neighborhood; Step S44: Initialize the community center, set 0.25 times the neighborhood width as the community width, calculate the community density of all route decision individuals, select the point with the highest community density as the first initial community center, calculate the community density of all remaining individuals except the selected community center point and the individuals within its community width, select the point with the highest community density as the initial community center again, repeat the operation until the number of remaining individuals is less than the number of selected community centers, calculate the average position of the remaining individuals, select the individual closest to the average position, and set it as the last community center; Step S45: community member allocation, calculating the association value between community individuals and all community centers, and allocating community individuals to the community to which the community center with the highest association degree belongs, as shown below: ; Where n represents the index of the community center, represents the nth community center, represents the community association value between the i-th route decision individual and the n-th community center, and represents the relevance weight, represents the Euclidean distance between the i-th route decision individual and the n-th community center; Step S46: Community center evolution, represented as follows: ; Among them, it represents the number of times the community center evolves, represents the nth community center during the it+1th community center evolution, represents the nth community center during the itth community center evolution, represents the training factor of the nth community center during the itth community center evolution, O represents the total number of route decision individuals in the nth community, represents the average offset between all route decision individuals in the nth community and the community center, represents the stability factor of the nth community during the itth community center evolution, It represents the position change of the nth community center from the it-1th community center evolution to the itth community center evolution; Step S47: A route decision community is formed, and steps S44 to S45 are repeated until the center of the route decision community no longer changes. 3. The vehicle route optimization method based on big data according to claim 1 is characterized in that: in step S5, the decision optimization specifically includes the following steps: Step S51: Optimization preparation, optimizing the entire route decision process by searching for parameters in the decision process, the parameters include guidance weight, control parameter, importance weight, scale transformation factor and relevance weight, creating a search space for route decision parameters, and randomly generating an initial route decision parameter search point group in the search space; Step S52: preparing for optimization effect evaluation, setting the average of the reciprocals of the average time per kilometer corresponding to the route with the highest comprehensive route evaluation score of all route decision individuals in the community as the route decision optimization effect evaluation index; Step S53: Design search weights, expressed as follows: ; ; in, represents the first search weight, represents the second search weight, It represents a number that decreases linearly from 2 to 0 in steps of 0.5. Represents a random number ranging from 0 to 1; Step S54: Designing a route decision parameter area search method, as shown below: ; Where t represents the number of optimization searches. Indicates the location of the regional search parameters during the t+1th optimization search. Indicates the location of the parameter search point with the maximum value of the evaluation index of the current route decision optimization effect. Indicates the location of the regional search parameters during the t-th optimization search. It means taking the Chebyshev distance between two positions; Step S55: Design a route decision parameter fine search method, the formula is as follows: ; in, Indicates the position of the refined search parameters during the t+1th optimization search. , and They respectively represent the 2nd, 3rd, and 4th parameter positions of the route decision optimization effect evaluation index values arranged from high to low in the search points of the regional search during the t+1th optimization search; Step S56: Decision optimization search, set the optimization effect threshold, set the maximum number of optimization searches, calculate the route decision optimization effect evaluation index value of the initial search point group, find the position of the parameter search point with the largest value of the current route decision optimization effect evaluation index, first perform a regional search, then perform a fine search, calculate the route decision optimization effect evaluation index value of the searched parameter point, increase the number of searches by one, if there is a parameter point with a route decision optimization effect evaluation index value greater than the optimization effect threshold, set the parameters of the search point with the largest value of the current route decision optimization effect evaluation index as the parameters of the route decision; if the maximum number of optimization searches is reached, perform the optimization search again; otherwise, continue searching. 4. The vehicle route optimization method based on big data according to claim 1 is characterized in that: in step S2, the data preprocessing performs data cleaning on the data, corrects erroneous data, removes duplicate data, and fills in missing data; standardizes the data to unify the format and range of the data; In step S1, the data collection is to collect historical vehicle position data, vehicle status data, road condition data, weather data and average time per kilometer of the route; the position data includes longitude and latitude; the vehicle status data includes vehicle speed, acceleration and direction angle; the road condition data includes traffic flow, traffic light data and impassable traffic intersection data; the weather data includes temperature, precipitation and wind speed. 5. A vehicle route optimization system based on big data, used to implement the vehicle route optimization method based on big data as described in any one of claims 1 to 4, characterized in that it includes a data acquisition module, a data preprocessing module, a route comprehensive evaluation module, a route decision community construction module, a decision optimization module and a vehicle route optimization module; The data acquisition module collects historical vehicle location data, vehicle status data, road condition data, weather data and average time per kilometer of the route, and sends the data to the data preprocessing module; The data preprocessing module receives the data sent by the data acquisition module, performs data preprocessing on the received data, and sends the preprocessed data to the route comprehensive evaluation module; The route comprehensive evaluation module receives the data sent by the data preprocessing module, performs a comprehensive evaluation on the route, and sends the data to the route decision community construction module; The route decision community building module receives data sent by the route comprehensive evaluation module, builds a route decision community, and sends the data to the decision optimization module; The decision optimization module receives data sent by the route decision building community module, optimizes parameters of the route decision process, and sends the data to the vehicle route optimization module; The vehicle route optimization module receives data from the decision optimization module, collects vehicle information in real time, performs a comprehensive route evaluation, adds the evaluated new data to the constructed original route decision community data, reconstructs the route decision community, finds the route decision community to which the new data belongs, and selects the route of the community center point as the optimal route for the vehicle.