CN112749842A

CN112749842A - Escort path planning method and device

Info

Publication number: CN112749842A
Application number: CN202110032348.9A
Authority: CN
Inventors: 惠杨凌; 钟其; 凌浩盛; 张卫东; 王疏艳
Original assignee: Industrial and Commercial Bank of China Ltd ICBC
Current assignee: Industrial and Commercial Bank of China Ltd ICBC
Priority date: 2021-01-11
Filing date: 2021-01-11
Publication date: 2021-05-04
Anticipated expiration: 2041-01-11
Also published as: CN112749842B

Abstract

The invention belongs to the technical field of artificial intelligence, and provides a escort path planning method and a device, wherein the escort path planning method comprises the following steps: acquiring the geographical positions of the nodes served by a plurality of vehicles to be planned escort, the service time and the service times of each node and the carrying capacity of each vehicle to be escorted; planning an escort path according to the geographical positions of the nodes served by a plurality of cars to be planned escort, the service time and the service times of each node, the carrying capacity of the cars to be escort and a pre-generated VRP (virtual router redundancy protocol) line optimization model; and training a VRP line optimization model periodically in preset time according to preset constraint conditions and optimization operators. The escort vehicle can be managed more intelligently by using the escort path planning method provided by the invention, the working efficiency is improved, and the whole risk of cash circulation is reduced.

Description

Escort path planning method and device

Technical Field

The invention relates to the technical field of banking services, in particular to a method and a device for planning escort paths.

Background

It can be understood that the escort vehicle plays an important role in the cash circulation and business development of banks, and the key for enhancing the management of the cash-transporting vehicle is the prevention and control risk and cost control and efficiency enhancement of the banking industry. In the prior art, a escort vehicle lacks a special monitoring management system, an escort line is mainly arranged by depending on a manual experience value, and no technical means is used for carrying out rationality evaluation on the line; meanwhile, managers cannot monitor and master the real running condition of the vehicle in real time, cannot capture conditions such as line deviation or abnormal events in time, and only can count and manage the driving mileage and the running time in a manual recording mode. The escort route is arranged by means of manual experience, and great manpower is required to be input when the adjustment caused by increase and decrease of stations, holidays or emergencies is dealt with, and the efficiency needs to be improved.

Disclosure of Invention

The invention belongs to the technical field of artificial intelligence, and aims to solve the problems in the prior art, the escort path planning method and the escort path planning device provided by the invention have the advantages that the historical data is used as the basis, the simulation verification capability is realized by means of an intelligent line planning algorithm, the service arrival time can be measured and calculated more accurately, and the line execution time and the mileage are analyzed, so that the purposes of balancing the cost and the benefit are achieved.

In order to solve the technical problems, the invention provides the following technical scheme:

in a first aspect, the present invention provides a method for planning an escort path, including:

acquiring the geographical positions of the nodes served by a plurality of vehicles to be planned escort, the service time and the service times of each node and the carrying capacity of each vehicle to be escorted;

planning an escort path according to the geographical positions of the points served by the plurality of escort automobiles to be planned, the service time and the service times of each point, the carrying capacity of the automobiles to be escort and a pre-generated VRP (virtual router redundancy protocol) line optimization model;

training the VRP line optimization model periodically according to a preset constraint condition and an optimization operator in a preset time, wherein the training of the VRP line optimization model comprises the following steps:

abstracting the actual service problem to generate an optimization objective equation;

and periodically training the optimization objective equation in preset time according to preset constraint conditions and optimization operators.

In one embodiment, the step of generating the VRP route optimization model comprises:

generating an initial model of the VRP route optimization model according to historical path data of a plurality of escorting automobiles, the geographical positions of the nodes, the historical service time of each node, the historical service times of each node and the carrying capacity of each automobile to be escorting by utilizing a VRP algorithm;

generating constraint conditions of the initial model according to the vehicle leaving times of escort vehicles and the total number of the driving mileage of all escort vehicles;

and training the initial model according to the constraint condition and a preset training end condition to generate the VRP route optimization model.

In an embodiment, the training the initial model according to the constraint condition and a preset training end condition to generate the VRP route optimization model includes:

and training the VRP route optimization model for multiple times in a preset time period according to the historical path data of a plurality of escort automobiles, the historical service time of each network point and the historical service times of each network point.

In one embodiment, the escort path planning method further includes:

and acquiring historical path data of the escort automobiles, historical service time of each network point and historical service times of each network point according to a GPS positioning device on the escort automobiles.

In one embodiment, the escort path planning method further includes: carrying out early warning on escort risks according to the VRP line optimization model, and the method comprises the following steps:

generating a path to be traveled of the escort automobile according to the VRP route optimization model;

monitoring the running path of the escort automobile in real time;

and when the running path deviates from the path to be run, and at least one of the situations that the escort automobile stops overtime and arrives at the destination point occurs, giving out early warning to the escort automobile.

In an embodiment, the planning an escort path according to the geographical locations of the nodes served by the plurality of escort automobiles to be planned, the service time and the service times of each node, the capacity of the automobiles to be escort, and a pre-generated VRP route optimization model includes:

based on a geographic information system, generating a driving route map of the escort automobile according to the geographic positions of the network points served by the plurality of escort automobiles to be planned;

and planning an escort path according to the driving route map, the service time and the service times of each network point, the carrying capacity of the automobile to be escorted and a pre-generated VRP (virtual router redundancy protocol) line optimization model.

In one embodiment, the escort path planning method further includes:

storing the path to be traveled;

and comparing the path to be traveled with the travel path, and generating a comparison report.

In a second aspect, the present invention provides a device for planning escort route, including:

the system comprises a data acquisition unit, a data processing unit and a control unit, wherein the data acquisition unit is used for acquiring the geographic positions of the nodes served by a plurality of vehicles to be planned escorted, the service time and the service times of each node and the carrying capacity of each vehicle to be escorted;

the route planning unit is used for planning escort routes according to the geographical positions of the nodes served by the plurality of escort automobiles to be planned, the service time and the service times of each node, the carrying capacity of the automobiles to be escort and a pre-generated VRP (virtual router redundancy protocol) route optimization model;

the model training unit is used for training the VRP line optimization model periodically in preset time according to preset constraint conditions and optimization operators, and comprises:

the target equation generation module is used for abstracting the actual service problem so as to generate an optimized target equation;

and the target equation training module is used for periodically training the optimized target equation in preset time according to preset constraint conditions and the optimization operator.

In a third aspect, the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the escort path planning method when executing the program.

In a fourth aspect, the present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of a method for planning an escort path.

As can be seen from the above description, the method and apparatus for planning an escort path according to the embodiments of the present invention first obtain geographic locations of nodes served by a plurality of escort automobiles to be planned, service time and service times of each node, and a capacity of each escort automobile; planning an escort path according to the geographical positions of the nodes served by a plurality of cars to be planned escort, the service time and the service times of each node, the carrying capacity of the cars to be escort and a pre-generated VRP (virtual router redundancy protocol) line optimization model; in addition, the method also comprises the following steps: training a VRP (virtual router redundancy protocol) line optimization model periodically according to a preset constraint condition and an optimization operator for a preset time, wherein the training VRP line optimization model comprises the following steps: abstracting the actual service problem to generate an optimization objective equation; and periodically training an optimization objective equation in preset time according to preset constraint conditions and optimization operators. The invention has the advantages that: the operation data of escort vehicles are automatically collected, and the real operation condition of the vehicles is mastered. On the other hand, an intelligent line planning algorithm is introduced, manual fine adjustment is added, and escort line arrangement is more scientific and reasonable.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.

Fig. 1 is a first schematic flow chart illustrating a method for planning an escort path according to an embodiment of the present invention;

FIG. 2 is a flow chart illustrating step 300 according to an embodiment of the present invention;

fig. 3 is a schematic flow chart illustrating a method for planning an escort path according to an embodiment of the present invention;

FIG. 4 is a flowchart illustrating a step 400 according to an embodiment of the present invention;

FIG. 5 is a schematic flow chart of a method for optimizing a problem to be solved in practice according to an embodiment of the present invention;

FIG. 6 is a flowchart illustrating step 403 in accordance with an embodiment of the present invention;

fig. 7 is a third schematic flow chart illustrating a method for planning an escort path according to an embodiment of the present invention;

fig. 8 is a fourth schematic flowchart illustrating a method for planning an escort path according to an embodiment of the present invention;

FIG. 9 is a flowchart of step 200 in an embodiment of the present invention;

FIG. 10 is a flowchart illustrating a method for planning escort route according to an embodiment of the present invention;

FIG. 11 is a diagram of a escort vehicle system with intelligent routing algorithm and risk control in accordance with an embodiment of the present invention;

FIG. 12 is a block diagram of a path planning algorithm engine module according to an embodiment of the present invention;

FIG. 13 is a block diagram of a map algorithm engine module according to an embodiment of the present invention;

FIG. 14 is a flow chart illustrating a vehicle scheduling algorithm optimization method according to an embodiment of the present invention;

FIG. 15 is a first schematic diagram illustrating a driving time limit condition according to an embodiment of the present invention;

FIG. 16 is a second schematic diagram illustrating a driving time limit condition according to an embodiment of the present invention;

FIG. 17 is a schematic diagram illustrating the components of the dot type in an embodiment of the present invention;

FIG. 18 is a schematic diagram illustrating the components of escort vehicles in an exemplary embodiment of the present invention;

FIG. 19 is a diagram illustrating the composition of elements of libraries in an embodiment of the present invention;

fig. 20 is a block diagram of a device for planning escort route according to an embodiment of the present invention;

fig. 21 is a schematic structural diagram of an electronic device in an embodiment of the invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

It should be noted that the terms "comprises" and "comprising," and any variations thereof, in the description and claims of this application and the above-described drawings, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.

The embodiment of the present invention provides a specific implementation manner of a method for planning an escort path, and referring to fig. 1, the method specifically includes the following steps:

step 100: the geographical positions of the network points served by a plurality of vehicles to be scheduled for escort, the service time and the service times of each network point and the carrying capacity of each vehicle to be escorted are obtained.

Preferably, it is also necessary to acquire vault information (website information), website type, service type, priority level, service date, service time (including appropriate service and service duration), service times, return time, and the like.

Step 200: planning an escort path according to the geographical positions of the points served by the plurality of escort automobiles to be planned, the service time and the service times of each point, the carrying capacity of the automobiles to be escort and a pre-generated VRP (virtual router redundancy protocol) line optimization model.

It can be understood that the Vehicle Routing Problem (VRP) is given a set of vehicles with capacity limit, a logistics center (or a supply place), a plurality of customers with supply demand, and organizes a proper driving route to enable the vehicle to orderly pass through all the customers, and under the condition of meeting certain constraint conditions (such as demand, service time limit, vehicle capacity limit, driving mileage limit, etc.), a certain target (such as shortest distance, extremely small cost, as little as possible, as few as possible number of vehicles used, etc.) is reached. The objective is to provide a minimum cost vehicle route to and from the warehouse for a group of customers with known needs.

Further, the input data of step 100 is input into the VRP route optimization model, so that more detailed service arrival time can be obtained, and cost and benefit can be balanced based on the planned route, thereby providing scientific basis for management decision.

Step 300: and training the VRP route optimization model periodically according to preset constraint conditions and optimization operators in preset time.

Referring to fig. 2, step 300 further comprises:

step 301: abstracting the actual service problem to generate an optimization objective equation;

specifically, a plurality of variables (including hard limiting conditions which are required to be met; soft limiting conditions which are required to be met) are abstracted from the escort business problem, a plurality of participating elements in a scene are abstracted into object types (service points, treasury and escort vehicles), and correlation operation is carried out to generate an optimization objective equation.

Step 302: and periodically training the optimization objective equation in preset time according to preset constraint conditions and optimization operators.

In order to improve the calculation speed of the algorithm, the algorithm needs to be optimized and upgraded when used, and the method is carried out from two dimensions:

(1) the scheduling route is optimized regularly, the training of the historical scheduling route is increased, and the time consumption of the regular optimization is reduced;

(2) and the temporary adding and dispatching service points are inserted into the service points in a rationalized and regionalized manner to perform global optimization, so that the time consumption in a temporary adding and dispatching scene is reduced.

As can be seen from the above description, in the method for planning an escort path provided in the embodiment of the present invention, first, the geographic locations of the nodes served by a plurality of escort automobiles to be planned, the service time and the service times of each node, and the capacity of each escort automobile are obtained; then, according to the geographical position of the network points served by a plurality of vehicles to be escorted, the service time and the service times of each network point, the carrying capacity of the vehicles to be escorted and a pre-generated VRP line optimization model, the invention plans the escorted path, which has the advantages that:

the method comprises the steps of (I) automatically collecting operation data of escort vehicles, mastering the real operation conditions of the vehicles and providing data support for fine management. Due to the lack of necessary technical means, the driving mileage data of escort vehicles can be obtained only by a manual boarding meter reading mode at present, the actual operation data of the vehicles cannot be mastered, and the management personnel lack first-hand data for operation risk prevention and control, operation line rationality evaluation, vehicle overtime and overtime cost evaluation and the like. The system is established to change the situation, automatically acquires GPS real-time positioning data of escorted vehicles, restores real-time running tracks of the vehicles after calculation processing, automatically generates key running indexes such as mileage, service time and the like, and provides comprehensive data support for monitoring and management functions such as real-time monitoring, abnormal early warning, arrival reminding, cost accounting, line planning, report analysis and the like.

And (II) an intelligent line planning algorithm is introduced, manual fine adjustment is added, and escort line arrangement is more scientific and reasonable. The escort route is arranged by means of manual experience, and great manpower is required to be input when the adjustment caused by station increase and decrease, holidays or emergencies is dealt with, so that the efficiency is to be improved. According to the system, an intelligent line planning algorithm is introduced, a corresponding planned line template is generated according to the time characteristics of working days and holidays based on historical data, manual experience fine adjustment is added, an optimal planned line is generated, the arranging efficiency can be improved, the manual workload is reduced, the arranged line is promoted to be more scientific and reasonable, and a technical support is provided for the optimization of the whole operation capacity.

In an embodiment, referring to fig. 3, the method for planning escort path further includes:

step 400: and generating the VRP route optimization model. Further, referring to fig. 4, step 400 includes:

step 401: generating an initial model of the VRP route optimization model according to historical path data of a plurality of escorting automobiles, the geographical positions of the nodes, the historical service time of each node, the historical service times of each node and the carrying capacity of each automobile to be escorting by utilizing a VRP algorithm;

in this embodiment, the VRP problem can be described by the following mathematical rules:

it should be noted that, the formula (1) represents that the optimization target is to minimize the number of used vehicles; equation (2) indicates that each point and only one vehicle is responsible for delivering the goods it needs; formula (3) indicates that each vehicle is responsible for at most one distribution line; equation (4) represents a traffic balance condition in the network; the formula (5) indicates that the cargo which is distributed by each vehicle does not exceed the bearing capacity limit; formula (6) is a constraint that prevents the appearance of soliton rings; equation (7) represents nodes in the distribution network (ij ∈ {0,1,2, …, N }) by i, j, where 0 represents a warehouse point and others represent customer points, K represents a vehicle (K ∈ {1,2, …, K }), and xijk represents whether the vehicle K travels from i to j.

Specifically, the VRP problem description method is utilized to convert historical path data, carrying capacity, geographic position of each website, historical service time and historical service times of each website of a plurality of escorted automobiles into a VRP problem, and then a VRP route optimization model is generated.

Step 402: generating constraint conditions of the initial model according to the vehicle leaving times of escort vehicles and the total number of the driving mileage of all escort vehicles;

adding time window constraints on the basis of the VRP problem derives from a time windowed Vehicle Routing Problem (VRPTW), which is similar to the VRP problem, with the additional constraint that each customer is associated with a time window that defines the time interval in which the customer must be served. The time window of the warehouse is called the scheduling scope. The VRPTW optimization objective is to minimize the number of vehicles, and a secondary objective is to minimize the sum of travel time and wait time required to service all customers in a given time. On the basis of VRPTW, constraint conditions related to services need to be added, and consideration of reasonableness factors such as road network accessibility, road condition information, experience paths and the like is combined, so that the problem is actually faced. The optimization procedure is shown in fig. 5. In fig. 5, CVRP: capacitated VRP, DCVRP that limits the carrying volume, weight, etc. of the delivery vehicle: distance-rated VRP, CVRP considering driving time cost (road condition, Distance). VRPB: VRP with Back, the vehicle will have a rest in the safe after finishing the delivery task.

Step 403: and training the initial model according to the constraint condition and a preset training end condition to generate the VRP route optimization model.

In one embodiment, referring to fig. 6, step 403 further includes:

step 4031: and training the VRP route optimization model for multiple times in a preset time period according to the historical path data of a plurality of escort automobiles, the historical service time of each network point and the historical service times of each network point.

Specifically, various constraint conditions are input, self-learning is performed, and an optimal routing route is given. It should be noted that the process is a repeatedly executed process, and various constraint conditions can be newly added according to the actual situation, for example, the optimization target is added with fairness consideration, and the mean square error of the driving range of each vehicle is multiplied by a certain coefficient and added into the optimization target; and dividing each vehicle into subareas according to the shift scheduling plan of the whole network point, wherein the shift scheduling plan of each day can further optimize multiple network points of a single vehicle. On the basis, the functions can be further improved, and the scene can be further refined. On the basis of the core framework of the original algorithm, the detailed optimization of the problems of the types such as unloading the super package, dispatching the vehicles in multiple passes and the like is added; and different types of optimization objective equations (such as the total cost of minimizing ladder pricing) and the increase of constraint conditions (such as the limitation of the number of service points distributed by vehicles, the limitation of the number of sub-parcel areas of vehicles across the safe, and the like) are summarized through abstracting the actual business problem, so that the problem which can be solved by the solving engine is more comprehensive and extensive. On the other hand, operators can be enriched, and the effect is improved. In order to improve the solving effect and stability of the engine, it can be considered to add richer optimization operators in the engine subsequently, such as different types of local search operators (e.g., Two-Opt, Three-Opt, Cross-Exchange, etc.), different types of intermediate result acceptance strategies (e.g., Greedy, Simulated analysis, etc.). (3) And the temporary adding and dispatching service points are inserted into the service points in a rationalized and regionalized manner to perform global optimization, so that the time consumption in a temporary adding and dispatching scene is reduced.

In an embodiment, referring to fig. 7, the method for planning escort path further includes:

step 500: and acquiring historical path data of the escort automobiles, historical service time of each network point and historical service times of each network point according to a GPS positioning device on the escort automobiles.

Specifically, the automatically acquired GPS real-time positioning data of the escort vehicle is calculated and processed to restore the real-time running track of the vehicle, and key running indexes such as the driving mileage, the service time and the like are automatically generated, so that comprehensive data support is provided for monitoring and management functions such as real-time monitoring, abnormal early warning, arrival reminding, cost accounting, line planning, report analysis and the like.

In an embodiment, referring to fig. 8, the method for planning escort path further includes:

step 600: generating a path to be traveled of the escort automobile according to the VRP route optimization model;

step 700: monitoring the running path of the escort automobile in real time;

step 800: and when the running path deviates from the path to be run, and at least one of the situations that the escort automobile stops overtime and arrives at the destination point occurs, giving out early warning to the escort automobile.

In steps 600 to 800, after the optimal route is generated, the escort vehicle completes each task according to the route. During this time, a condition monitoring and early warning function is performed on the line. Specifically, the monitoring and early warning types include:

(1) and (5) early warning of line deviation.

(2) And (5) parking overtime early warning.

(3) Whether a site is reached is automatically identified.

(4) Whether the vault is reached or not is automatically identified.

And (3) business constraint rules: (1) the real-time position (vehicle shape pattern + line number + predicted return time) and the running condition of each vehicle in the map can be inquired, displayed and monitored in real time. Including travel speed, mileage data and whether it deviates from a predetermined route. If the deviation is beyond the planned route and exceeds the allowable range, the early warning is triggered in real time and is pushed to a business operation post and a business management post. (2) When the escort vehicle is in a stop state, the parking timing function is automatically triggered, when the stop time exceeds the preset parameter threshold value, the stop time is displayed in a highlight mode to generate a record of the overtime stop, and information is pushed to prompt designated personnel. (3) The service points that the line has arrived and has not arrived can be automatically distinguished, and monitoring personnel can distinguish through the change of the service line and the site icon (the change of the size, the highlight or the gray display). (4) Preferably, after the escort vehicle arrives at a certain service site, the short message is automatically pushed to the contact personnel at the next service site to inform the contact personnel of the expected arrival information. (5) After the return of the day-end escort vehicle is completed, the system automatically compares the data according to the line, records the line data of the planned mileage/time exceeding 10 percent (the parameters can be set), generates a line comparison graph, and generates a related list and a report. A summary of all records over a period of time may then be queried.

In one embodiment, referring to fig. 9, step 200 further comprises:

step 201: based on a geographic information system, generating a driving route map of the escort automobile according to the geographic positions of the network points served by the plurality of escort automobiles to be planned;

specifically, various point location information upper maps including a cash center and a service site are restored and mapped onto a map by a map engine through a multi-map-layer superposition rendering method, a GPS running track of an escort vehicle is restored and mapped onto the map, the map presenting capability of complex information including site information, vehicle positioning, abnormal running and track return visit is realized by combining road network characteristics and planning lines, comprehensive information monitoring is realized through one map, all abnormal information is mastered, and risk prevention is strengthened.

Step 202: and planning an escort path according to the driving route map, the service time and the service times of each network point, the carrying capacity of the automobile to be escorted and a pre-generated VRP (virtual router redundancy protocol) line optimization model.

Specifically, the service time, the service times and the carrying capacity of each car to be escorted of each network are input into a VRP (virtual router protocol) line optimization model, and a line planning map, travel time, homing time, required service network, the service times for serving the network and the like of each car to be escorted are generated based on a driving route map, so that data support is provided for fine management, and escorted line arrangement is more scientific and reasonable.

The escort path planning method further comprises the following steps:

step 900: storing the path to be traveled;

the specific contents to be stored include: and recording the accurate time points of leaving and returning of the escort vehicle during the period by setting the electronic fence of the safe as a complete working day period after the vehicle leaves the safe and the vehicle returns to the safe after the task of the current day is completed. And based on the distance calculation function of the map, calculating the actual driving distance of each vehicle according to the actual driving route of the escort vehicle, and generating a distance record according to the kilometers of the planned route and the kilometers of the actual driving at the end of the day. Based on the distance calculation function of the map, the actual driving distance of each vehicle is calculated according to the actual driving route of the escort vehicle, and a distance record is generated according to the kilometer number of the planned route and the kilometer number of the actual driving at the end of the day.

Step 1000: and comparing the path to be traveled with the travel path, and generating a comparison report.

And generating a comparison report of whether the escort vehicle is matched with the original planned route. Preferably, the report further includes the working hours mileage, the working hours mileage information can be counted according to different time dimensions (day, month, season, half year, year), different administration ranges (treasury, vehicle) and the like, the operation data can be analyzed according to the constraint rules (the vehicle stipulated driving mileage and driving time), abnormal conditions can be automatically identified, and the information and the accounting cost can be counted.

As can be seen from the above description, the escort path planning method provided in the embodiment of the present invention introduces an intelligent line planning algorithm strategy, and assists with manual fine adjustment, so that escort line arrangement becomes more scientific and reasonable, thereby further shortening the waiting time of the service site receiving and delivering library, and improving the satisfaction of the service site and the escort service efficiency. By means of an offline Geographic Information System (GIS), cash centers, service sites and escort vehicle running data graphs are displayed, real-time monitoring of vehicle lines can be achieved, operation data and various durations are automatically collected, bases are provided for accurate judgment of expenses such as overtime, kilometers and the like, and operation cost is effectively controlled. On the basis of intelligent line planning and map information, management functions such as station arrival reminding, electronic fence, deviation early warning, operation track playback, data import and export, information prompt pushing and the like are developed, functions such as mobile phone APP management and the like are supported, management personnel can intervene in real time conveniently, execution prejudgment can be made in time, and escort service risks are prevented and controlled. After the project is built and put into operation, the escort transportation capacity planning capacity is expected to be effectively improved, the time for the network to wait for the warehouse is compressed, the escort service quality is improved, the risk prevention and control capacity is improved through real-time monitoring, and a scientific management basis is provided for cost reduction, efficiency improvement and risk control. In conclusion, the escort path planning method provided by the embodiment of the invention can be used for more intelligently managing the escort vehicle, improving the working efficiency and reducing the risk of whole cash circulation.

To further illustrate the present solution, the present invention provides a specific application example of the escort path planning method, which specifically includes the following contents, see fig. 10.

In the specific application example, the escort vehicle system with the route intelligent planning algorithm and the risk control thereof is also provided, and mainly comprises a Geographic Information System (GIS)101, a path planning algorithm engine 102, a map algorithm engine 103, a escort vehicle tracking management system 104, an APP control console 105 and a Web control console 106. The structural composition is shown in fig. 11.

Geographic Information System (GIS)101 is a set of computer-space information systems that are responsible for collecting, storing, managing, analyzing and describing data on the entire or part of the earth's surface that is relevant to spatial and geographic distribution, and is the fundamental information of the entire system. The path planning algorithm engine 102 is a core device of the system, and mainly functions to provide route planning and schedule lists for all escort vehicles. The map algorithm engine 103 mainly includes map data management, trajectory data management, and the like. The escort vehicle tracking management system 104 collects various data in the path planning algorithm engine 102 and the map algorithm engine 103 for report presentation and decision support, and also manages users and parameters of the system. The APP console 105 acquires various information and then displays the information on the collection side. The Web console 106 provides various information and management functions on the PC side.

Referring to fig. 12, the path planning algorithm engine 102 includes three main modules, a vehicle scheduling data model 201, a vehicle scheduling algorithm engine 202, and a route analysis module 203. All vehicle information and service site information are stored in the vehicle scheduling data model 201. The vehicle scheduling algorithm engine 202 is based on the "vehicle routing problem" VRP, which is at the heart of the need to determine the routing (from one or more origins) of a fleet of vehicles to serve customers dispersed over multiple geographic locations. The purpose of the VRP is to provide a minimum cost vehicle route to and from the warehouse for a group of customers with known requirements.

Referring to fig. 13, the map algorithm engine 103 includes a map base map data management 501, a map track data management 502, and a map route planning and analysis 503, where the map base map data management 501 is responsible for extracting map data, the map track data management 502 is responsible for processing road information of a map, and the map route planning and analysis 503 is responsible for providing route planning according to the road information and traffic conditions.

Fig. 10 shows a method for planning escort route provided by this embodiment.

S1: and acquiring the vault information, the site type, the service type, the priority level, the service date, the service time, the service times, the service duration and the return time.

Specifically, after the escort vehicle system with the route intelligent planning algorithm and the risk control device is built, the administrator inputs related parameters: the system comprises the following steps of vault information, site types, service types, priority levels, service dates, service time, service times, service duration, return time and the like. The system provides a site marking function, displays all site information in a visual mode, and can display address information, longitude and latitude information and the like;

s2: an initial model of the VRP route optimization model is generated.

After the optimization of the problem is completed, a plurality of variables (including hard limiting conditions which need to be met; soft limiting conditions which need to be met, and optimization balance) need to be abstracted from the escort vehicle service scene, a plurality of participating elements in the scene are abstracted into object types (service network points, treasury and escort vehicle), and correlation operation is carried out by utilizing a VRP algorithm so as to generate an initial model.

S3: the initial model is trained to generate a VRP route optimization model.

Referring to fig. 14, the initial model is trained based on the constraint, and in fig. 14, the initial model, i.e., the initial solution, is shifted, for example, users visited by vehicles with similar exchange trajectories and the initial solution is selected according to a local search algorithm, such as a tabu search. Preferably, the termination condition is that the solution-optimized mileage such as search within 5 minutes is less than 1km, and the search is stopped. Hard constraints and soft constraints, the hard constraints including:

vehicle capacity: vehicles have a rated capacity limit.

Driving time: the time cost from one location to the next. The driving time matrix between all the dots, see fig. 15 and fig. 16, needs to be calculated, for example, 500 dots, 500 × 500 times. The topological connectivity, road grade, historical road conditions and other empty attributes of the road network need to be considered. In addition, real-time road condition factors (scheduling of temporarily distributed network points), empirical path factors for escort vehicle running (path planning is more in line with driving habits), predicted weather factors (especially rain and fog weather, important factors influencing road conditions), traffic event factors (analyzing running time delay and improving a safety evaluation system) and the like need to be added.

Time window: mesh point service period (serviceDuration): the escort volume must be serviced within a specified service period. For the network, the escort vehicle must complete the service in a given time period, currently set for a money transfer time of 5 minutes. The network point services for multiple times: in the case of multiple services for the same network, such as money removal and discharge, the algorithm will split the service into different time windows, which is equivalent to splitting the service into multiple clients at the same location. Mesh point earliest service time (readyTime): a mesh point can only be served at a certain time. Particularly, the earliest serviceable time of the morning branch line is directly related to the time length of the store waiting of the morning branch line. If the available service time in the morning is too early, the storage waiting time is long, and the total number of vehicles is small; if the morning serviceable time is too late, the morning garage waiting time is short, and the total number of vehicles is large. Mesh point latest service time (dueTime): the vehicle must complete the service before the latest service time. Particularly, the latest service available time of the network points in the rows at night is directly related to the time length of waiting for storage of the network points at night. And (3) carrying out afternoon break of the escort vehicle: the vehicle needs to return to the national treasury for 2 hours of noon break. When the arrival time of the customer is updated, if the time for returning the vehicle to the safe from the current website exceeds 12 points, the vehicle is appointed to return to the safe from the previous website for rest, and then the vehicle starts from the safe to arrive at the current website.

Soft limiting conditions: the primary goal of minimizing the number of vehicles and the secondary goal of reducing the overtime supercharge number. (the optimization objective is adjusted to minimize the total vehicle mileage (in meters) +5 × total vehicle waiting time (in seconds)). The different points of each day of service need to ensure that the driving route of the driver is not changed too much (firstly, the scheduling plan of all the points of service is generated, and then the current-day journey of the driver is screened out according to the points of each day of service). Referring to fig. 17 to 19, according to the elements participating in the calculation, the abstract object classes include: the website, escort vehicle and vault, wherein the website includes: number, actual time, expected time, service duration, arrival time, departure time, latitude and longitude. Escort vehicles include: number, actual time, expected time. The treasury class includes: number, latitude and longitude.

Further, abstracting and modeling the algorithm according to the business logic, extracting 4 mature escort lines, extracting relevant parameters for calculation, comparing the algorithm result with the actual business scene, and if the conclusion obtained by the algorithm is larger than the actual scene, continuously increasing the optimization points:

(1) adding the optimization target into fairness consideration, for example, adding the mean square error of the driving range of each vehicle multiplied by a certain coefficient into the optimization target;

(2) and dividing each vehicle into subareas according to the shift scheduling plan of the whole network point, wherein the shift scheduling plan of each day can further optimize multiple network points of a single vehicle.

(3) On the basis of the core framework of the original algorithm, the detailed optimization of the problems of the types such as unloading the super package, dispatching the vehicles in multiple passes and the like is added; and different types of optimization objective equations (such as the total cost of minimizing ladder pricing) and the increase of constraint conditions (such as the limitation of the number of vehicle distribution network points, the limitation of the number of sub-parcel areas of vehicles across the safe, and the like) are summarized through abstracting the actual business problem, so that the problem which can be solved by the solving engine is more comprehensive and extensive.

(4) Operators are enriched, and the effect is improved. In order to improve the solving effect and stability of the engine, it is considered to add richer optimization operators in the engine, such as different types of local search operators (e.g., Two-Opt, Three-Opt, Cross-Exchange, etc.), different types of intermediate result acceptance strategies (e.g., Greedy, Simulated Annealing, etc.).

With the addition of various optimization factors, the calculation result of the algorithm is closer to the actual service scene, and the algorithm training is considered to be basically completed at the moment. In addition, in order to increase the calculation speed of the algorithm, the algorithm needs to be optimized and upgraded in time, and the method is performed from two dimensions: the scheduling route is optimized regularly, the training of the historical scheduling route is increased, and the time consumption of the regular optimization is reduced; and the temporary adding and dispatching network points are reasonably and regionally inserted into the network points to carry out global optimization, so that the time consumption in a temporary adding and dispatching scene is reduced. Through the optimization process, the path planning algorithm can meet the actual requirement.

It should be noted that, the process is a repeatedly executed process, and the administrator can add various constraint conditions according to the actual situation, for example, 1, the optimization target adds fairness consideration, and the mean square error of the driving range of each vehicle can be multiplied by a certain coefficient and added into the optimization target; 2. and dividing each vehicle into subareas according to the shift scheduling plan of the whole network point, wherein the shift scheduling plan of each day can further optimize multiple network points of a single vehicle.

On the basis, the functions can be improved, and the scene can be refined. On the basis of the core framework of the original algorithm, the detailed optimization of the problems of the types such as unloading the super package, dispatching the vehicles in multiple passes and the like is added; and different types of optimization objective equations (such as the total cost of minimizing ladder pricing) and the increase of constraint conditions (such as the limitation of the number of vehicle distribution network points, the limitation of the number of sub-parcel areas of vehicles across the safe, and the like) are summarized through abstracting the actual business problem, so that the problem which can be solved by the solving engine is more comprehensive and extensive. Operators are enriched, and the effect is improved. In order to improve the solving effect and stability of the engine, it can be considered to add richer optimization operators in the engine subsequently, such as different types of local search operators (e.g., Two-Opt, Three-Opt, Cross-Exchange, etc.), different types of intermediate result acceptance strategies (e.g., Greedy, Simulated analysis, etc.). The temporary adding and dispatching network points are reasonably and regionally inserted into the network points to carry out global optimization, and time consumption under a temporary adding and dispatching scene is reduced.

S4: and marking the optimized route on a map.

Specifically, basic information is input into a VRP route optimization model after training to generate an optimal path, so that initial scheduling information is given, and all routes are marked on a map.

S5: and monitoring and early warning the line execution condition based on the optimal line.

After the optimal line arrangement is finished, the escort vehicle finishes various tasks according to the line. During the period, the system provides a function of monitoring and early warning the line execution condition.

Monitoring and early warning types:

(1) and (5) early warning of line deviation.

(2) And (5) parking overtime early warning.

(3) Whether a site is reached is automatically identified.

(4) Whether the vault is reached or not is automatically identified.

And (3) business constraint rules:

(1) the real-time position (vehicle shape pattern + line number + predicted return time) and the running condition of each vehicle in the map can be inquired, displayed and monitored in real time. Including travel speed, mileage data and whether it deviates from a predetermined route. If the deviation is beyond the planned route and exceeds the allowable range, the early warning is triggered in real time and is pushed to a business operation post and a business management post.

(2) When the escort vehicle is in a stop state, the parking timing function is automatically triggered, when the stop time exceeds the preset parameter threshold value, the system displays in a highlight mode to generate a record of the overtime stop, and pushes information to prompt designated personnel.

(3) The system can automatically distinguish the network points which arrive and do not arrive on the line, and monitoring personnel can distinguish the network points by the change of the service line and the site icon (the change of size, highlight or grey display).

(4) After the escort vehicle arrives at a certain service site, the short message is automatically pushed to the contact personnel of the next network site to inform the contact personnel of the expected arrival information.

(5) After the return of the day-end escort vehicle is completed, the system automatically compares the data according to the line, records the line data of the planned mileage/time exceeding 10 percent (the parameters can be set), generates a line comparison graph, and generates a related list and a report. A summary of all records over a period of time may then be queried.

S6: and providing a statistical analysis function for the management personnel to make analysis decisions.

(1) And (6) comparing routes.

The system provides a route comparison and analysis function and displays the route on a map in a visual mode. Contrasting routing information supports the use of different colored depictions. The comparison types include: A. planning a route and actually walking the route. B. Actual walking routes on different dates.

(2) And (5) counting time.

The system provides the functions of collecting, inquiring and counting the daily driving time of the escort vehicle. Constraint conditions are as follows:

A. and recording the accurate time points of leaving and returning of the escort vehicle during the period by setting the electronic fence of the safe as a complete working day period after the vehicle leaves the safe and the vehicle returns to the safe after the task of the current day is completed.

B. Considering that the escort personnel still need to carry out handover confirmation work with bank storeroom personnel in the actual work, the working hour calculation of the escort personnel still needs to add a time parameter which can be set by the operating personnel of the coffer according to the actual situation of each coffer on the basis of the working hour of the vehicle.

(3) And (5) mileage statistics.

The system provides the functions of collecting and inquiring the daily driving mileage of the escort vehicle. The constraint conditions comprise:

B. Based on the distance calculation function of the map, the actual driving distance of each vehicle is calculated according to the actual driving route of the escort vehicle, and a distance record is generated according to the kilometer number of the planned route and the kilometer number of the actual driving at the end of the day.

C. And generating a comparison report of whether the escort vehicle is matched with the original planned route.

(4) And (5) carrying out working hour mileage accounting.

The system provides a working hour mileage accounting function, can count working hour mileage information according to different time dimensions (day, month, season, half year, year), different administration ranges (a vault and a vehicle) and the like, analyzes operation data according to constraint rules (the specified driving mileage and driving time of the vehicle), automatically identifies abnormal conditions, and counts information and accounting cost. And (3) business constraint rules: A. the inquiry and the accounting of the operating hours and the mileage of each escort vehicle are realized, the summarized data of time elements such as day, month, season, half year, year and the like are formed, and the summarized data of the operating hours and the mileage of all escort vehicles in the jurisdiction according to the time elements can be formed in a vault. B. Calculating a period of time of the super kilometer cost, and calculating a rule: the suburb line runs for 120 kilometers every day, the urban line runs for 100 kilometers every day, whether the total running mileage of all lines in a period of time exceeds the limit is calculated by taking a national treasury as a unit, and if the total running mileage of all lines in the period of time exceeds the limit, the overtime charge amount in the period of time is directly displayed according to the overtime charge set in each kilometer. And simultaneously displaying the difference value with the planned kilometer number.

(5) And (4) track playback.

The system provides a running track playback function, and can play back the running track information of the escorting vehicle according to the selected date, the escorting vehicle, the service time period and other constraint conditions. And (3) business constraint rules: A. the factors such as escort route, time, personnel information and the like of the escort vehicle with the scheduled date completing the escort vehicle task can be restored. On one hand, the problems and unreasonable places of the escort line can be found through playback, and analysis basis is provided for better optimizing the line arrangement; on the other hand, support is provided for escort risk prevention and clue inquiry after risk generation.

As can be seen from the above description, the method for planning an escort path provided by the specific application example of the present invention includes first obtaining geographic locations of the nodes served by a plurality of escort automobiles to be planned, service time and service times of each node, and a capacity of each escort automobile; planning an escort path according to the geographical positions of the nodes served by a plurality of cars to be planned escort, the service time and the service times of each node, the carrying capacity of the cars to be escort and a pre-generated VRP (virtual router redundancy protocol) line optimization model; in addition, the method further comprises the following steps: training a VRP route optimization model periodically according to a preset constraint condition and an optimization operator in a preset time, and further comprising: abstracting the actual service problem to generate an optimization objective equation; and periodically training an optimization objective equation in preset time according to preset constraint conditions and optimization operators. Specifically, the escort path planning method provided by the specific application example has the following beneficial effects:

and (I) information comprehensive monitoring is realized by relying on an advanced Geographic Information System (GIS), and the risk prevention capability is improved. By utilizing a multi-layer superposition rendering technology, various point location information upper maps including cash centers and service sites are restored and mapped onto a map through a map engine, the GPS running track of an escort vehicle is restored and mapped onto the map, the map presenting capability of complex information including site information, vehicle positioning, abnormal running and track return visit is realized by combining road network characteristics and planning lines, the comprehensive monitoring of the information is realized through one map, all abnormal information is mastered, and risk prevention is strengthened.

And (II) providing scientific basis for escort service management through circuit planning simulation verification. As the price of escort outsourcing services increases year by year, escort services need to better balance the relationship between service quantity, service quality and vehicle cost, especially the large quantity of home services that play an important role in enhancing the core customer stickiness. After the system is established, historical data is used as a basis, the simulation verification capability is realized by means of an intelligent line planning algorithm, the service arrival time can be measured and calculated more accurately, the line execution time and mileage are analyzed, the cost and income are balanced, and a scientific basis is provided for management decision making.

And thirdly, the time for the personnel at the network site to wait for the warehouse is reduced, and the escort service quality is improved. After the system is established, through the combination of an intelligent line planning algorithm, the electronic fence and the arrival reminding technology, more reasonable route planning and more accurate line execution are realized, the time of site personnel for storage is shortened, the work pressure of sites is reduced, and the escort service quality is improved.

And (IV) a complete vehicle service quality evaluation system can be established, and cost reduction and efficiency improvement can be realized. With the continuous accumulation of the operation data of escort vehicles, more and more service indexes can be counted and summarized, and a foundation is laid for establishing a vehicle service quality evaluation system. Through comparison and analysis of different dimensions of vehicles, time and regions, the common and individual problems of route planning can be found, and the final purposes of cost reduction and efficiency improvement are achieved by further optimizing a route planning algorithm or controlling the cost of a single vehicle to improve the efficiency of the single vehicle.

Based on the same inventive concept, the embodiment of the present application further provides a planning device for escort path, which can be used to implement the method described in the above embodiment, such as the following embodiments. Because the principle of solving the problems of the escort path planning device is similar to that of the escort path planning method, the implementation of the escort path planning device can be implemented by referring to the escort path planning method, and repeated parts are not described again. As used hereinafter, the term "unit" or "module" may be a combination of software and/or hardware that implements a predetermined function. While the system described in the embodiments below is preferably implemented in software, implementations in hardware, or a combination of software and hardware are also possible and contemplated.

An embodiment of the present invention provides a specific implementation of an escort path planning apparatus capable of implementing the escort path planning method, and referring to fig. 20, the escort path planning apparatus specifically includes the following contents:

the data acquisition unit 10 is configured to acquire geographic locations of nodes served by a plurality of escort automobiles to be planned, service time and service times of each node, and a capacity of each escort automobile;

the route planning unit 20 is configured to plan an escort route according to the geographic locations of the nodes served by the plurality of escort automobiles to be planned, the service time and the service times of each node, the capacity of the escort automobiles to be planned, and a pre-generated VRP route optimization model;

a model training unit 30, configured to train the VRP line optimization model periodically according to a preset constraint condition and an optimization operator in a preset time, where the model training unit 30 includes:

the objective equation generation module 301 is configured to abstract an actual service problem to generate an optimized objective equation;

and the target equation training module 302 is configured to periodically train the optimized target equation for a preset time according to a preset constraint condition and an optimization operator.

As can be seen from the above description, the device for planning an escort path according to the embodiment of the present invention first obtains the geographic locations of the nodes served by a plurality of escort vehicles to be planned, the service time and the service times of each node, and the capacity of each escort vehicle; secondly, planning an escort path according to the geographical positions of the nodes served by a plurality of escort automobiles to be planned, the service time and the service times of each node, the carrying capacity of the automobiles to be escort and a pre-generated VRP (virtual router redundancy protocol) line optimization model; the device also trains a VRP line optimization model periodically according to preset constraint conditions and optimization operators in preset time, and comprises the following steps: abstracting the actual service problem to generate an optimization objective equation; and periodically training an optimization objective equation in preset time according to preset constraint conditions and optimization operators. The invention has the advantages that: firstly, the operation data of escort vehicles are automatically collected, the real operation conditions of the vehicles are mastered, and data support is provided for fine management. Secondly, an intelligent line planning algorithm is introduced, manual fine adjustment is added, and escort line arrangement is more scientific and reasonable.

The apparatuses, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or implemented by a product with certain functions. A typical implementation device is an electronic device, which may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

In a typical example, the electronic device specifically includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the computer program, the processor implements the steps of the escort path planning method, where the steps include:

step 100: acquiring the geographical positions of the nodes served by a plurality of vehicles to be planned escort, the service time and the service times of each node and the carrying capacity of each vehicle to be escorted;

step 200: planning an escort path according to the geographical positions of the points served by the plurality of escort automobiles to be planned, the service time and the service times of each point, the carrying capacity of the automobiles to be escort and a pre-generated VRP (virtual router redundancy protocol) line optimization model;

step 300: training the VRP line optimization model periodically according to a preset constraint condition and an optimization operator in a preset time, wherein the training of the VRP line optimization model comprises the following steps:

Referring now to FIG. 21, shown is a schematic diagram of an electronic device 600 suitable for use in implementing embodiments of the present application.

As shown in fig. 21, the electronic apparatus 600 includes a Central Processing Unit (CPU)601 that can perform various appropriate works and processes according to a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage section 608 into a Random Access Memory (RAM)) 603. In the RAM603, various programs and data necessary for the operation of the system 600 are also stored. The CPU601, ROM602, and RAM603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.

The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, a mouse, and the like; an output portion 607 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The driver 610 is also connected to the I/O interface 605 as needed. A removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 610 as necessary, so that a computer program read out therefrom is mounted as necessary on the storage section 608.

In particular, according to an embodiment of the present invention, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, an embodiment of the present invention includes a computer-readable storage medium, on which a computer program is stored, the computer program, when executed by a processor, implementing the steps of the escort path planning method described above, the steps including:

In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 609, and/or installed from the removable medium 611.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functionality of the units may be implemented in one or more software and/or hardware when implementing the present application.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A escort path planning method is characterized by comprising the following steps:

2. The escort path planning method of claim 1, wherein the step of generating the VRP route optimization model comprises:

3. The escort path planning method according to claim 2, wherein the training the initial model according to the constraint condition and a preset training end condition to generate the VRP route optimization model comprises:

4. The escort path planning method according to claim 2, further comprising:

5. The escort path planning method according to claim 2, further comprising: carrying out early warning on escort risks according to the VRP line optimization model, and the method comprises the following steps:

monitoring the running path of the escort automobile in real time;

6. The escort path planning method according to any one of claims 1 to 5, wherein the planning of the escort path according to the geographical locations of the nodes served by the plurality of escort vehicles to be planned, the service time and the service times of each node, the capacity of the vehicle to be escorted, and a pre-generated VRP route optimization model comprises:

7. The escort path planning method according to claim 5, further comprising:

storing the path to be traveled;

8. A escort path planning device is characterized by comprising:

9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the escort path planning method of any one of claims 1 to 7 when executing the program.

10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the escort path planning method of any one of claims 1 to 7 when executing the program.