Intelligent logistics-oriented path planning method and system

Abstract

The invention relates to the technical field of intelligent logistics, and discloses an intelligent logistics-oriented path planning method and system, and the method comprises the steps: determining a working area of a logistics vehicle, dividing the logistics vehicle into multiple paths according to traffic lights and guiding arrows, collecting the information of the paths and the vehicle through a detection unit, drawing an electronic map from an overlook angle, and carrying out the planning of the path. The processing unit calculates the vehicle density P of the obtained path; acquiring corresponding vehicle density according to corresponding parameter information, sequencing vehicle density data groups, planning a path by combining with an actual departure place and a destination, predicting a next time period by acquiring current vehicle speed and time period information, and performing combined analysis on three parameters including the vehicle density, an average vehicle speed and a vehicle speed fluctuation value to obtain a vehicle density prediction result. Therefore, the effect of improving the working efficiency is achieved.

Description

Technical Field

[0001] The present invention relates to the field of smart logistics technology, and specifically to a path planning system for smart logistics. Background Art

[0002] Smart logistics refers to a modern logistics model that uses intelligent technologies such as smart software and hardware, the Internet of Things, and big data to achieve refined, dynamic, and visual management of all aspects of logistics, improve the intelligent analysis and decision-making and automated operation execution capabilities of the logistics system, and enhance the efficiency of logistics operations. In the route planning stage of logistics transportation, it is necessary to select the degree of traffic on the route and choose the best route to achieve the effect of improving work efficiency.

[0003] For example, a Chinese invention patent with application publication number CN114897460A discloses an intelligent logistics query system, which can provide modeling data support for the distribution area within the entire range based on remote sensing data information, use a three-dimensional simulation module to establish a three-dimensional simulation map, and set an update unit to update road abnormal points in real time. It uses the difference in express quality to judge the energy consumption of express vehicles, and comprehensively considers various situations from the perspective of practical application to achieve the lowest energy consumption while ensuring timely express delivery.

[0004] Combined with the above application and the contents of the prior art: Generally, logistics vehicles plan their routes before work, but in actual logistics transportation, each environmental factor such as weather, time period and date has a significant impact on road conditions. For example, rush hour commuting, holiday travel peaks, rainy days, snowy days and other bad weather will also have a significant impact on road conditions. If the route can be planned only based on the number of vehicles on the route, as working hours pass, environmental factors will have a significant impact on the vehicle condition of the planned route, which will cause the route selected in advance by the logistics vehicle to be inconsistent with the actual situation, hindering the progress of logistics work, which is contrary to the purpose of planning the route. Summary of the invention

[0005] 1. Technical issues to be resolved

[0006] In view of the deficiencies in the prior art, the present invention provides a path planning method and system for smart logistics. By testing the impact of weather, date and time period on vehicle density, an evaluation model is constructed to obtain the density of vehicles on the road in real time. By combining the current vehicle speed and time period for extrapolated analysis, the degree of vehicle congestion in the next time period is obtained, thereby achieving the effect of planning a path in real time based on current environmental information.

[0007] (II) Technical solution

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions: a path planning system for smart logistics, comprising:

[0009] The detection unit detects the traffic information data in the working area of ​​the logistics vehicle.

[0010] The processing unit receives the traffic information data outputted by the detection unit and calculates and analyzes the data.

[0011] Feedback unit, which receives data information output from the detection unit and the processing unit and provides feedback to the logistics personnel;

[0012] The detection unit includes an image detection module, a speed detection module and an environment module. The image detection module is used to capture information about the path and vehicles on the path within the working area. The speed detection module is used to detect the speed V of the vehicle on the path. The environment module is used to receive weather information, date information and time information from the outside.

[0013] The processing unit includes a two-dimensional model module, a calculation and analysis module, and a transmission module. The two-dimensional model module analyzes the image information transmitted by the detection unit, divides the working area into several paths according to the traffic information of traffic lights, road signs and turn arrows, and draws electronic maps and vehicle images. The calculation and analysis module obtains the information collected from the environment module, and calculates the area of ​​the path according to the drawn electronic map and vehicle image. and the total area of ​​all vehicles on the path , the vehicle density P is calculated, the calculation and analysis module is used to calculate and count the vehicle density P of the path under different environmental information, and the transmission module is used to transmit the corresponding path and the calculation result to the feedback unit;

[0014] The feedback unit includes a threshold module and an early warning module. The threshold module is preset with a congestion threshold, which is used to compare the size relationship between the vehicle density P and the congestion threshold to determine whether the road condition is congested. The early warning module is used to output road condition information to the logistics personnel terminal.

[0015] Preferably, the image transmitted by the image detection module is processed by the two-dimensional model module, and the electronic map and the vehicle image are drawn from a bird's-eye view. The calculation and analysis module determines the length of each path according to the moving direction and the guide arrow. He Kuan After cleaning the data, The area of ​​the path is ;

[0016] According to the number of vehicles in the navigation and the total length L2 and total width W2 of all vehicles captured by image detection technology, the data will be cleaned and The total area occupied by vehicles is S2. The formula for the vehicle density P of each path is obtained from the path area S1 of each segment and the total area occupied by vehicles on the path S2:

[0017]

[0018] in, , thereby calculating the vehicle density of each path in the working area, and transmitting the result to the feedback unit through the transmission module. The transmission module can also be used to receive the signal fed back by the feedback unit.

[0019] Preferably, by calculating and analyzing the vehicle density P in several days, the information in the environment module in several days is collected, including date, weather and time information, the dates are divided into working days and holidays, the weather is divided into unsuitable weather and suitable weather, the time is divided into travel peak hours and non-travel peak hours, and the corresponding vehicle density P is determined;

[0020] According to the logistic regression analysis, the relationship between the vehicle density P corresponding to the environmental information and the congestion threshold is confirmed, and the weight value of the corresponding environmental information on the numerical change of the vehicle density P is obtained, and the density index PM is generated, and an evaluation model of the density index PM is constructed by the weighted average method.

[0021] Preferably, three sets of environmental information data are obtained through the road condition records of several days, which are the vehicle density P data information under the single weather environment, the single date environment and the single time environment. The change value of the vehicle density P under the single environmental information is obtained by the variance formula, and then the average value of the change value under the single environmental information is determined by the mean formula, including the date mean D, the time mean T and the weather mean W. The influence of date, time and weather on the vehicle density P is analyzed by the logistic regression method, and the density index PM is generated. The weight values ​​obtained by logical analysis are respectively , after dimensionless processing, the evaluation model of the dense index PM is constructed by weighted average method, and the formula is as follows:

[0022]

[0023] in, , C1 is the constant correction coefficient, ;

[0024] The date mean D in the information collected by the environment module includes the working day mean G and the holiday mean J. Through the data collection of several days, the influence of the working day mean G and the holiday mean J on the vehicle density P is obtained according to the logistic regression analysis. The corresponding weight coefficients are constructed based on the influence degree, which are: and ;

[0025] The time mean T in the information collected by the environment module includes the mean F during the travel peak period and the mean NF during the non-travel peak period. Through data collection over several days, the influence of the mean F during the travel peak period and the mean NF during the non-travel peak period on the vehicle density P is obtained based on the logistic regression analysis. The corresponding weight coefficients are constructed based on the influence degree, which are: ;

[0026] The weather mean W in the information collected by the environment module includes the mean H of suitable weather and the mean NH of unsuitable weather. Through data collection for several days, the influence of the mean H of suitable weather and the mean NH of unsuitable weather on the vehicle density P is obtained according to the logistic regression analysis. The corresponding weight coefficients are constructed based on the influence degree, which are: ;

[0027] The detection unit detects whether the current date is a weekday or a holiday, the time is a travel peak period or a non-travel peak period, and the weather is suitable weather or unsuitable weather. The corresponding weight coefficient is determined based on the information obtained from the detection, and is substituted into the formula of the density index PM to obtain the density index value.

[0028] Preferably, the preset congestion threshold is divided into low-level congestion and high-level congestion according to the degree of congestion, the current environmental information is collected and substituted into the formula to calculate the density index PM, and the relationship between the density index PM and the congestion threshold is compared, where

[0029] , indicating that the congestion degree is low-level congestion, which is fed back to the logistics personnel terminal through the feedback unit;

[0030] , indicating that the congestion level is high, and is fed back to the logistics personnel terminal through the feedback unit;

[0031] , indicating that the degree of congestion is not congested, and is fed back to the logistics personnel terminal through the feedback unit.

[0032] Preferably, a path and multiple groups of vehicle samples are determined, and the speed value of the vehicle at each position on the path is detected by the speed detection module according to a preset time period, and the corresponding multiple groups of average vehicle speed value data sets are obtained. , the average vehicle speed of the speed data set is obtained through linear normalization And the vehicle speed fluctuation value PV, the formula is as follows:

[0033]

[0034] in, is the i-th value in the velocity data set, is the average value of the speed data set, and n is the number of data in the speed data set.

[0035] Preferably, the threshold module is preset with a vehicle smooth average speed threshold and a vehicle speed fluctuation threshold, which are respectively recorded as a first threshold and a second threshold.

[0036] like , indicating that the traffic condition on the path is severely congested and the feedback is that it is impassable;

[0037] like , indicating that vehicles on the path are running smoothly, and the feedback is level 1 smooth;

[0038] like , indicating that the average speed of vehicles on the path fluctuates greatly, indicating that the speed difference between vehicles is large, and the feedback is the second level of smoothness;

[0039] like , indicating that vehicles on the path are moving slowly, and the feedback is the third level of smooth traffic.

[0040] Preferably, after several days of testing, the vehicle density P and average vehicle speed are obtained by analytic hierarchy process. The correlation effects of the three factors, namely, and vehicle speed fluctuation value PV, on the degree of traffic smoothness are calculated, and the corresponding weight coefficients are obtained, which are recorded as , the traffic index WL is generated according to the traffic flow, and the formula of the traffic index WL is as follows:

[0041]

[0042] in, , is a constant correction factor, .

[0043] Preferably, the threshold module is preset with a third threshold value set according to the degree of traffic flow, and the traffic index WL is calculated and obtained, and the magnitude relationship between the traffic index WL and the third threshold value is compared, wherein:

[0044] like , indicating that the path is not conducive to traffic, and the feedback is fed back to the logistics personnel terminal through the feedback unit;

[0045] like , indicating that the path is conducive to passage, and is fed back to the logistics personnel terminal through the feedback unit.

[0046] To achieve the above objectives, the present invention is implemented through the following technical solutions: determining the working area of ​​the logistics vehicle, dividing it into multiple paths according to traffic lights and guide arrows, collecting information of the path and the vehicle through the detection unit, drawing an electronic map from a bird's-eye view, and calculating the vehicle density P of the path by the processing unit;

[0047] Through several days of testing, the vehicle density P under the corresponding environmental conditions is obtained according to the environmental information of date, time and weather collected by the environmental module, and the mean under the corresponding environmental information is obtained through the variance and mean formula. The processing unit uses the logistic regression method to obtain the influence of date, time and weather on the vehicle density P, and constructs an evaluation model of the density index PM;

[0048] Dates in the logistics system are divided into working days and holidays, time is divided into travel peak hours and non-travel peak hours, and weather is divided into unsuitable weather and suitable weather. Logistic regression is used to obtain the degree of influence of the information on vehicle density P, obtain the weight coefficient, collect current environmental information, substitute it into the evaluation model of density index PM, and evaluate the results;

[0049] Determine a certain path, obtain the speed of multiple groups of vehicles on the path, collect vehicle speed information according to time periods, and calculate the average vehicle speed The vehicle speed fluctuation value PV is used to set the vehicle smooth average speed threshold and the vehicle speed fluctuation threshold, which are respectively recorded as the first threshold and the second threshold. , the vehicle speed fluctuation value PV is compared with the first threshold value and the second threshold value respectively, and the result is evaluated;

[0050] Through the hierarchical analysis method, the vehicle density P and average speed are obtained. The correlation between the speed fluctuation value PV and the degree of traffic smoothness is collected, the current data information is substituted into the formula to obtain the result and evaluate the result, the traffic index WL of all paths in the working area is calculated and obtained, and they are sorted by size to finally obtain the most suitable traffic route.

[0051] (III) Beneficial effects

[0052] The present invention provides a method having the following beneficial effects:

[0053] (1) Obtain parameter information in the external logistics system through the detection unit, namely date, time and weather, obtain vehicle information corresponding to the parameter information, and calculate the vehicle density of the route by drawing an electronic map. The date is divided into weekdays and holidays, the time is divided into travel peak hours and non-travel peak hours, and the weather is divided into unsuitable weather and suitable weather. In the actual route planning, the corresponding vehicle density is obtained according to the corresponding parameter information, and the vehicle density data group is sorted and the route is planned in combination with the actual departure and destination.

[0054] (2) By collecting the current vehicle speed and time information, the next time period is predicted. If the next route of the vehicle enters the travel peak period and the vehicle density is expected to increase, the route selection is changed to a route with a smaller vehicle density, thereby achieving the effect of predicting and selecting the best route in real time, thereby improving work efficiency.

[0055] (3) By detecting the speed of multiple groups of vehicles on the path, the average vehicle speed and speed fluctuation value are obtained, and a threshold suitable for passage is pre-set. When the vehicle density at the two end paths is the same, the average vehicle speed is compared with the first threshold, and the speed fluctuation value is compared with the second threshold, and the best passage path is selected.

[0056] (4) By combining the three parameters of vehicle density, average speed and speed fluctuation, the correlation effect of the three parameters on the degree of traffic smoothness is analyzed through the hierarchical analysis method, and the current path information and future path information are collected. The size is determined and sorted to obtain the best path, thereby achieving the effect of improving work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 This is a schematic diagram of the structure of a path planning system for smart logistics in the present invention;

[0058] Figure 2 This is a structural schematic diagram of a path planning method for smart logistics according to the present invention. DETAILED DESCRIPTION

[0059] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0060] See also Figure 1 The present invention provides a path planning system for smart logistics, comprising:

[0061] The detection unit detects the traffic information data in the working area of ​​the logistics vehicle.

[0062] The processing unit receives the traffic information data outputted by the detection unit and calculates and analyzes the data.

[0063] Feedback unit, which receives data information output from the detection unit and the processing unit and provides feedback to the logistics personnel;

[0064] The detection unit includes an image detection module, a speed detection module and an environment module. The image detection module is used to capture information about the path and vehicles on the path within the working area. The speed detection module is used to detect the speed V of the vehicle on the path. The environment module is used to receive weather information, date information and time information from the outside.

[0065] The processing unit includes a two-dimensional model module, a calculation and analysis module and a transmission module, wherein the two-dimensional model module analyzes the image information transmitted by the detection unit, divides the working area into several paths according to the traffic information of traffic lights, road signs and turn arrows, and draws an electronic map and a vehicle image; the calculation and analysis module obtains the information collected from the environment module, calculates the area S1 of the path and the total area S2 of all vehicles on the path according to the drawn electronic map and vehicle image, and calculates the vehicle density P; the calculation and analysis module is used to calculate and count the vehicle density P of the path under different environmental information; the transmission module is used to transmit the corresponding path and the calculation result to the feedback unit;

[0066] The feedback unit includes a threshold module and an early warning module. The threshold module is preset with a congestion threshold, which is used to compare the size relationship between the vehicle density P and the congestion threshold to determine whether the road condition is congested. The early warning module is used to output road condition information to the logistics personnel terminal.

[0067] The image transmitted by the image detection module is processed by the two-dimensional model module, and the electronic map and vehicle image are drawn from a bird's-eye view. The calculation and analysis module determines the length L1 and width W1 of each path according to the moving direction and the guide arrow. After cleaning the data, Let it be the area S1 of the path;

[0068] According to the number of vehicles in the navigation and the total length L2 and total width W2 of all vehicles captured by image detection technology, the data will be cleaned and Recorded as the total area occupied by vehicles The formula for the vehicle density P of each path segment is obtained from the path area S1 of each segment and the total area occupied by vehicles on the path S2:

[0069]

[0070] in, , thereby calculating the vehicle density of each path in the working area, and transmitting the result to the feedback unit through the transmission module. The transmission module can also be used to receive the signal fed back by the feedback unit.

[0071] By calculating and analyzing the vehicle density P in several days, the information in the environment module of several days, including date, weather and time information, is collected, the dates are divided into working days and holidays, the weather is divided into unsuitable weather and suitable weather, the time is divided into travel peak hours and non-travel peak hours, and the corresponding vehicle density P is determined;

[0072] According to the logistic regression analysis, the relationship between the vehicle density P corresponding to the environmental information and the congestion threshold is confirmed, and the weight value of the corresponding environmental information on the numerical change of the vehicle density P is obtained, and the density index PM is generated, and an evaluation model of the density index PM is constructed by the weighted average method.

[0073] Through the road condition records of several days, three sets of environmental information data are obtained, namely, the vehicle density P data information under the single weather environment, the single date environment and the single time environment. The change value of the vehicle density P under a single environmental information is obtained through the variance formula, and then the average value of the change value under a single environmental information is determined through the mean formula, including the date mean D, the time mean T and the weather mean W. The influence of date, time and weather on vehicle density P is analyzed by the logistic regression method, and the density index PM is generated. The weight values ​​obtained by logical analysis are , after dimensionless processing, the evaluation model of the dense index PM is constructed by weighted average method, and the formula is as follows:

[0074]

[0075] in, , C1 is the constant correction coefficient, ;

[0076] The date mean D in the information collected by the environment module includes the working day mean G and the holiday mean J. Through the data collection of several days, the influence of the working day mean G and the holiday mean J on the vehicle density P is obtained according to the logistic regression analysis. The corresponding weight coefficients are constructed based on the influence degree, which are:

[0077] and ;

[0078] When working, collect the current date information. If the current date is a working day, substitute the working day mean G into the date mean D in the formula, and the working day weight Substitute the weight b1 in the formula; if the current date is a holiday, substitute the holiday mean J into the date mean D in the formula, and the working day weight Substituting the weights into the formula ;

[0079] The time mean T in the information collected by the environment module includes the mean F during the travel peak period and the mean NF during the non-travel peak period. Through data collection over several days, the influence of the mean F during the travel peak period and the mean NF during the non-travel peak period on the vehicle density P is obtained based on the logistic regression analysis. The corresponding weight coefficients are constructed based on the influence degree, which are: ;

[0080] Similarly, when working, collect the current time information. If the current time is the peak travel period, substitute the peak travel period mean F into the time mean T in the formula, and the peak travel period weight Substitute the weight b2 in the formula; if the current time is not a peak travel period, substitute the mean value NF of the non-peak travel period into the time mean T in the formula, and the peak travel period weight Substitute the weight b2 into the formula;

[0081] The weather mean W in the information collected by the environment module includes the mean H of suitable weather and the mean NH of unsuitable weather. Through data collection for several days, the influence of the mean H of suitable weather and the mean NH of unsuitable weather on the vehicle density P is obtained according to the logistic regression analysis. The corresponding weight coefficients are constructed based on the influence degree, which are: ;

[0082] Similarly, when working, collect the current weather information. If the current weather is suitable for travel, substitute the suitable weather mean H into the weather mean W in the formula, and the suitable weather weight Substitute the weight b3 in the formula; if the current time is unsuitable weather, substitute the unsuitable weather mean NH into the weather mean W in the formula, and the unsuitable weather weight Substitute the weight b3 into the formula;

[0083] The detection unit detects whether the current date is a weekday or a holiday, the time is a travel peak period or a non-travel peak period, and the weather is suitable weather or unsuitable weather. The corresponding weight coefficient is determined based on the information obtained from the detection, and is substituted into the formula of the density index PM to obtain the density index value.

[0084] According to the degree of congestion, the preset congestion threshold is divided into low-level congestion and high-level congestion. The current environmental information is collected and substituted into the formula to calculate the density index PM. The relationship between the density index PM and the congestion threshold is compared.

[0085] , indicating that the congestion degree is low-level congestion, which is fed back to the logistics personnel terminal through the feedback unit;

[0086] , indicating that the congestion level is high, and is fed back to the logistics personnel terminal through the feedback unit;

[0087] , indicating that the degree of congestion is not congested, and is fed back to the logistics personnel terminal through the feedback unit.

[0088] Determine the path and multiple groups of vehicle samples, use the speed detection module to detect the speed value of the vehicle at each position on the path according to the preset time period, and obtain the corresponding multiple groups of average vehicle speed value data sets , the average vehicle speed of the speed data set is obtained through linear normalization And the vehicle speed fluctuation value PV, the formula is as follows:

[0089]

[0090] in, is the ith value in the velocity data set, is the average value of the speed data set, and n is the number of data in the speed data set.

[0091] The threshold module is preset with a vehicle smooth average speed threshold and a vehicle speed fluctuation threshold, which are respectively recorded as the first threshold and the second threshold.

[0092] like , indicating that the traffic condition on the path is severely congested and the feedback is that it is impassable;

[0093] like , indicating that the vehicles on the path are running smoothly, and the feedback is first-level smooth; this data indicates that the average speed is large, that is, the vehicles are running faster, and the fluctuation value is small, that is, the speed difference between vehicles is small, indicating that all vehicles are running faster.

[0094] like , indicating that the average speed of vehicles on the path fluctuates greatly, indicating that the speed difference between vehicles is large, and the feedback is the second level of smoothness;

[0095] This data indicates that the fluctuation value between vehicles is large, that is, the speed difference between vehicles is large, and vehicles cannot move smoothly on the path. Such road conditions are likely to cause congestion.

[0096] like , indicating that the vehicles on the path are moving slowly, and the feedback is level 3 smooth;

[0097] This data indicates that the average speed of vehicles is small, that is, the vehicles are traveling slowly, and the fluctuation value is small, that is, the speed difference between vehicles is also small, indicating that the driving speed of all vehicles is full, that is, a traffic jam has occurred.

[0098] After several days of testing, the vehicle density P and average speed were obtained through the hierarchical analysis method. The correlation effects of the three factors, namely, and vehicle speed fluctuation value PV, on the degree of traffic smoothness are calculated, and the corresponding weight coefficients are obtained, which are recorded as , the traffic index WL is generated according to the traffic flow, and the formula of the traffic index WL is as follows:

[0099]

[0100] in, , is a constant correction factor, .

[0101] The threshold module is preset with a third threshold value set according to the degree of traffic flow, and the traffic index WL is calculated and obtained, and the magnitude relationship between the traffic index WL and the third threshold value is compared, wherein,

[0102] like , indicating that the path is not conducive to traffic, and the feedback is fed back to the logistics personnel terminal through the feedback unit;

[0103] like , indicating that the path is conducive to passage, and is fed back to the logistics personnel terminal through the feedback unit;

[0104] Determine the departure and destination of logistics vehicles in the work area, determine multiple paths through which they pass, and obtain pre-planned routes after permutations and combinations. During actual work, obtain information on the next time period and selectable paths based on the current time information and the current speed of the logistics vehicles, calculate the traffic index WL of the selectable paths respectively, and adjust them at any time according to the appropriate plan to achieve the effect of predicting road conditions, greatly improving work efficiency.

[0105] See also Figure 2 The present invention provides a path planning method for smart logistics, comprising the following steps:

[0106] Determine the working area of ​​the logistics vehicle, divide it into multiple paths according to traffic lights and guide arrows, collect information about the path and vehicles through the detection unit, draw an electronic map from a bird's-eye view, and calculate the vehicle density P of the path through the processing unit. After several days of detection, obtain the vehicle density P under the corresponding environmental conditions based on the environmental information of date, time and weather collected by the environmental module, and obtain the mean under the corresponding environmental information through the variance and mean formula. The processing unit uses the logistic regression method to determine the degree of influence of date, time and weather on vehicle density P, and construct an evaluation model for the density index PM;

[0107] Dates in the logistics system are divided into working days and holidays, time is divided into travel peak hours and non-travel peak hours, and weather is divided into unsuitable weather and suitable weather. Logistic regression is used to obtain the degree of influence of the information on vehicle density P, obtain the weight coefficient, collect current environmental information, substitute it into the evaluation model of density index PM, and evaluate the results;

[0108] Determine a certain path, obtain the speed of multiple groups of vehicles on the path, collect vehicle speed information according to time periods, and calculate the average vehicle speed The vehicle speed fluctuation value PV is used to set the vehicle smooth average speed threshold and vehicle speed fluctuation threshold. Compare the vehicle speed fluctuation value PV with the corresponding threshold value and evaluate the result;

[0109] Through the hierarchical analysis method, the vehicle density P and average speed are obtained. The correlation between the speed fluctuation value PV and the degree of traffic smoothness is collected, the current data information is substituted into the formula to obtain the result and evaluate the result, the traffic index WL of all paths in the working area is calculated and obtained, and they are sorted by size to finally obtain the most suitable traffic route.

[0110] The analytic hierarchy process, referred to as AHP, is a decision-making method that decomposes elements related to decision-making into levels such as goals, criteria, and plans, and then conducts qualitative and quantitative analysis. This method is particularly suitable for target systems with hierarchical and staggered evaluation indicators, and decision-making problems whose target values ​​are difficult to describe quantitatively.

[0111] The core of the hierarchical analysis method is to decompose complex decision-making problems into different hierarchical structures, including the target layer, criterion layer, sub-criterion layer and solution layer. By solving the eigenvector of the judgment matrix, the priority weight of each element at each level to an element at the previous level can be determined, and then the final weight of each alternative plan to the overall goal can be recursively merged through the weighted sum method. The one with the largest final weight is the optimal plan.

[0112] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. A person of ordinary skill in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution.

[0113] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0114] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A path planning system for smart logistics, characterized by: include: The detection unit detects the traffic information data in the working area of ​​the logistics vehicle. The processing unit receives the traffic information data outputted by the detection unit and calculates and analyzes the data. Feedback unit, which receives data information output from the detection unit and the processing unit and provides feedback to the logistics personnel; The detection unit includes an image detection module, a speed detection module and an environment module, wherein the image detection module is used to capture information about the path within the working area and the vehicles on the path, the speed detection module is used to detect the speed V of the vehicles on the path, and the environment module is used to receive weather information, date information and time information from the outside; The processing unit includes a two-dimensional model module, a calculation and analysis module and a transmission module, wherein the two-dimensional model module analyzes the image information transmitted by the detection unit, divides the working area into a plurality of paths according to the traffic information of the traffic lights, road signs and turn arrows, and draws an electronic map and a vehicle image, the calculation and analysis module obtains the information collected from the environment module, calculates the area S1 of the path and the total area S2 of all vehicles on the path according to the drawn electronic map and vehicle image, and calculates the vehicle density P, the calculation and analysis module is used to calculate and count the vehicle density P of the path under different environmental information, and the transmission module is used to transmit the corresponding path and the calculation result to the feedback unit; The feedback unit includes a threshold module and an early warning module. The threshold module is preset with a congestion threshold for comparing the size relationship between the vehicle density P and the congestion threshold to determine whether the road condition is congested. The early warning module is used to output road condition information to the logistics personnel terminal.

2. A path planning system for smart logistics according to claim 1, characterized in that: The image transmitted by the image detection module is processed by the two-dimensional model module, and the electronic map and vehicle image are drawn from a bird's-eye view. The calculation and analysis module determines the length L1 and width W1 of each path according to the moving direction and the guide arrow. After cleaning the data, Let it be the area S1 of the path; According to the number of vehicles in the navigation and the total length L2 and total width W2 of all vehicles captured by image detection technology, the data will be cleaned and The total area occupied by vehicles is S2. The formula for the vehicle density P of each path is obtained from the path area S1 of each segment and the total area occupied by vehicles on the path S2: in, , thereby calculating the vehicle density of each path in the working area, and transmitting the result to the feedback unit through the transmission module. The transmission module can also be used to receive the signal fed back by the feedback unit.

3. A path planning system for smart logistics according to claim 2, characterized in that: By calculating and analyzing the vehicle density P in several days, the information in the environment module of several days, including date, weather and time information, is collected, the dates are divided into working days and holidays, the weather is divided into unsuitable weather and suitable weather, the time is divided into travel peak hours and non-travel peak hours, and the corresponding vehicle density P is determined; According to the logistic regression analysis, the relationship between the vehicle density P corresponding to the environmental information and the congestion threshold is confirmed, and the weight value of the corresponding environmental information on the numerical change of the vehicle density P is obtained, and the density index PM is generated, and an evaluation model of the density index PM is constructed by the weighted average method.

4. A path planning system for smart logistics according to claim 3, characterized in that: Through the road condition records of several days, three sets of environmental information data are obtained, namely, vehicle density P data information under a single weather environment, a single date environment, and a single time environment. The change value of vehicle density P under a single environmental information is obtained through the variance formula, and then the average value of the change value under a single environmental information is determined through the mean formula, including the date mean D, the time mean T, and the weather mean W. The influence of date, time, and weather on vehicle density P is analyzed by the logistic regression method, and the density index PM is generated. The weight values ​​are b1, b2, and b3 respectively through logical analysis. After dimensionless processing, the evaluation model of the density index PM is constructed by the weighted average method. The formula is as follows: in, , , , is a constant correction factor, ; The date mean D in the information collected by the environment module includes the working day mean G and the holiday mean J. Through the data collection of several days, the influence of the working day mean G and the holiday mean J on the vehicle density P is obtained according to the logistic regression analysis. The corresponding weight coefficients are constructed based on the influence degree, which are: and ; The time mean T in the information collected by the environment module includes the mean F during the travel peak period and the mean NF during the non-travel peak period. Through data collection over several days, the influence of the mean F during the travel peak period and the mean NF during the non-travel peak period on the vehicle density P is obtained based on the logistic regression analysis. The corresponding weight coefficients are constructed based on the influence degree, which are: and ; The weather mean W in the information collected by the environment module includes the mean H of suitable weather and the mean NH of unsuitable weather. Through data collection for several days, the influence of the mean H of suitable weather and the mean NH of unsuitable weather on the vehicle density P is obtained according to the logistic regression analysis. The corresponding weight coefficients are constructed based on the influence degree, which are: and ; The detection unit detects whether the current date is a weekday or a holiday, the time is a travel peak period or a non-travel peak period, and the weather is suitable weather or unsuitable weather. The corresponding weight coefficient is determined based on the information obtained from the detection, and is substituted into the formula of the density index PM to obtain the density index value.

5. A path planning system for smart logistics according to claim 4, characterized in that: According to the degree of congestion, the preset congestion threshold is divided into low-level congestion and high-level congestion. The current environmental information is collected and substituted into the formula to calculate the density index PM. The relationship between the density index PM and the congestion threshold is compared. , indicating that the congestion degree is low-level congestion, which is fed back to the logistics personnel terminal through the feedback unit; , , indicating that the congestion level is high, and is fed back to the logistics personnel terminal through the feedback unit; , indicating that the degree of congestion is not congested, and is fed back to the logistics personnel terminal through the feedback unit.

6. The path planning system for smart logistics according to claim 1 is characterized by: Determine the path and multiple groups of vehicle samples, use the speed detection module to detect the speed value of the vehicle at each position on the path according to the preset time period, and obtain the corresponding multiple groups of average vehicle speed value data sets , the average vehicle speed of the speed data set is obtained through linear normalization And the vehicle speed fluctuation value PV, the formula is as follows: in, is the i-th value in the velocity data set, is the average value of the speed data set, and n is the number of data in the speed data set.

7. A path planning system for smart logistics according to claim 6, characterized in that: The threshold module is preset with a vehicle smooth average speed threshold and a vehicle speed fluctuation threshold, which are respectively recorded as the first threshold and the second threshold. like , indicating that the traffic condition on the path is severely congested and the feedback is that it is impassable; like , indicating that vehicles on the path are running smoothly, and the feedback is level 1 smooth; like or , indicating that the average speed of vehicles on the path fluctuates greatly, indicating that the speed difference between vehicles is large, and the feedback is the second level of smoothness; like , indicating that vehicles on the path are moving slowly, and the feedback is the third level of smooth traffic.

8. The path planning system for smart logistics according to claim 7 is characterized by: After several days of testing, the vehicle density P and average speed were obtained through the hierarchical analysis method. The correlation effects of the three factors, namely, and vehicle speed fluctuation value PV, on the degree of traffic smoothness are calculated, and the corresponding weight coefficients are obtained, which are recorded as , the traffic index WL is generated according to the traffic flow, and the formula of the traffic index WL is as follows: in, , is a constant correction factor, .

9. A path planning system for smart logistics according to claim 8, characterized in that: The threshold module is preset with a third threshold value set according to the degree of traffic flow, and the traffic index WL is calculated and obtained, and the magnitude relationship between the traffic index WL and the third threshold value is compared, wherein, like , indicating that the path is not conducive to traffic, and the feedback is fed back to the logistics personnel terminal through the feedback unit; like , indicating that the path is conducive to passage, and is fed back to the logistics personnel terminal through the feedback unit.

10. A path planning system for smart logistics, using a path planning method for smart logistics as described in any one of claims 1 to 9, characterized in that: Determine the working area of ​​the logistics vehicle, divide it into multiple paths according to traffic lights and guide arrows, collect path and vehicle information through the detection unit, draw an electronic map from a bird's-eye view, and the processing unit calculates the vehicle density P of the path; Through several days of testing, the vehicle density P under the corresponding environmental conditions is obtained according to the environmental information of date, time and weather collected by the environmental module, and the mean under the corresponding environmental information is obtained through the variance and mean formula. The processing unit uses the logistic regression method to obtain the influence of date, time and weather on the vehicle density P, and constructs an evaluation model of the density index PM; Dates in the logistics system are divided into working days and holidays, time is divided into travel peak hours and non-travel peak hours, and weather is divided into unsuitable weather and suitable weather. Logistic regression is used to obtain the degree of influence of the information on vehicle density P, obtain the weight coefficient, collect current environmental information, substitute it into the evaluation model of density index PM, and evaluate the results; Determine a certain path, obtain the speed of multiple groups of vehicles on the path, collect vehicle speed information according to time periods, and calculate the average vehicle speed The vehicle speed fluctuation value PV is used to set the vehicle smooth average speed threshold and the vehicle speed fluctuation threshold, which are respectively recorded as the first threshold and the second threshold. , the vehicle speed fluctuation value PV is compared with the first threshold value and the second threshold value respectively, and the result is evaluated; Through the hierarchical analysis method, the vehicle density P and average speed are obtained. The correlation between the speed fluctuation value PV and the degree of traffic smoothness is collected, the current data information is substituted into the formula to obtain the result and evaluate the result, the traffic index WL of all paths in the working area is calculated and obtained, and they are sorted by size to finally obtain the most suitable traffic route.

Images