CN114358448B - Driving route planning method and device - Google Patents
Driving route planning method and device Download PDFInfo
- Publication number
- CN114358448B CN114358448B CN202210275576.3A CN202210275576A CN114358448B CN 114358448 B CN114358448 B CN 114358448B CN 202210275576 A CN202210275576 A CN 202210275576A CN 114358448 B CN114358448 B CN 114358448B
- Authority
- CN
- China
- Prior art keywords
- banknote
- training
- route planning
- adding time
- route
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Navigation (AREA)
- Traffic Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention provides a driving route planning method and a device, which can be used in the technical field of artificial intelligence, and the method comprises the following steps: training the deep learning network according to historical transaction data, historical cash adding time, acquired road information and historical routes of all network points, and constructing a cash adding route planning model; the generated current banknote time sequence data and road information of each network point are subjected to route planning through the banknote adding route planning model, an optimal running route is obtained, the banknote adding requirements and timeliness requirements of each network point can be met, the stability, flexibility and usability of the system are improved, the time, manpower and material resources are saved, and the running route is efficiently planned.
Description
Technical Field
The invention relates to the technical field of computers, in particular to the technical field of artificial intelligence, and particularly relates to a driving route planning method and device.
Background
In daily operation, in order to ensure that the capital of each branch is normally operated, the money of each branch needs to be added regularly. In order to save time, manpower and material resources, the driving route of the securicar needs to be planned in advance, so that not only can the banknotes of each network point be ensured not to be in short supply, but also the time cost needs to be saved as much as possible. In the related technology, the search efficiency of the heuristic search technology of the planning algorithm is improved by constructing the relevance between the road condition information and the money adding sequence and generating the dependence rule of the money adding sequence by utilizing the road condition. However, in the related technology, only the road condition information and the money adding condition of each network point are considered, and the requirement of timeliness cannot be met; an expert system based on rules is adopted to carry out heuristic search, new factors cannot be added in time, the flexibility is poor, and the system is weak; the searching time and the searching round are manually controlled by a user to search out a better money adding plan, and the usability is poor.
Disclosure of Invention
One object of the present invention is to provide a driving route planning method, which can meet the demand of money adding and the demand of timeliness of each network node, improve the stability, flexibility and usability of the system, save time and cost of manpower and material resources, and efficiently plan the driving route. Another object of the present invention is to provide a driving route planning apparatus. It is yet another object of the present invention to provide a computer readable medium. It is a further object of the present invention to provide a computer apparatus.
In order to achieve the above object, the present invention discloses a driving route planning method, including:
training the deep learning network according to historical transaction data, historical cash adding time, acquired road information and historical routes of all network points, and constructing a cash adding route planning model;
and carrying out route planning on the generated current banknote time sequence data and road information of each network point through a banknote adding route planning model to obtain an optimal driving route.
Preferably, the deep learning network is trained according to historical transaction data, historical cash adding time, acquired road information and historical routes of all network points, and a cash adding route planning model is constructed, and comprises the following steps:
training the deep learning network according to historical transaction data, and constructing a banknote adding time sequence prediction model;
training the deep learning network according to historical cash adding time, road information and a historical route, and constructing a route planning model;
and generating a money adding route planning model according to the money adding time sequence prediction model and the route planning model.
Preferably, the historical transaction data comprises historical banknote timing data and historical optimal banknote adding time;
training the deep learning network according to historical transaction data, and constructing a banknote adding time sequence prediction model, wherein the banknote adding time sequence prediction model comprises the following steps:
determining the historical optimal banknote adding time as a first training label;
determining historical banknote timing sequence data as first training data;
and training the deep learning network according to the first training label and the first training data to construct a banknote adding time sequence prediction model.
Preferably, the deep learning network is trained according to historical cash adding time, road information and historical routes, and a route planning model is constructed, wherein the route planning model comprises the following steps:
determining the historical route as a second training label;
determining the historical cash adding time and the road information as second training data;
and training the deep learning network according to the second training labels and the second training data to construct a route planning model.
Preferably, before performing route planning on the generated current banknote time sequence data and road information of each network point through the banknote adding route planning model to obtain an optimal driving route, the method further includes:
screening out the required amount of the banknotes in each time period in a specified time period from the obtained current cash transaction running water;
and generating current banknote time sequence data according to the banknote demand of each time period.
Preferably, the money adding route planning model comprises a money adding time sequence prediction model and a route planning model;
the method comprises the following steps of carrying out route planning on the generated current banknote time sequence data and road information of all network points through a banknote adding route planning model to obtain an optimal driving route, wherein the route planning comprises the following steps:
predicting according to the current banknote time sequence data through a banknote adding time sequence prediction model to obtain the predicted banknote adding time of each network point;
and carrying out convolution calculation on the predicted cash adding time and the road information through a route planning model to obtain an optimal driving route.
Preferably, the road information comprises a regional traffic static control structure and road live information of each network point;
carrying out convolution calculation on the predicted cash adding time and road information through a route planning model to obtain an optimal driving route, wherein the convolution calculation comprises the following steps:
respectively extracting the characteristics of the predicted cash adding time, the regional traffic static spatial structure and the road live information of each network point through a detector node to obtain the predicted cash adding time characteristics, the regional traffic static spatial structure characteristics and the road live characteristics of each network point;
carrying out convolution calculation on the predicted cash adding time characteristic and the regional traffic static space structure characteristic to obtain a dynamic characteristic of the cash adding time;
performing convolution calculation on the regional traffic static spatial structure characteristics and the road live characteristics of all network points to obtain the dynamic characteristics of the segmented path;
and carrying out fusion calculation on the dynamic characteristics of the money adding time and the dynamic characteristics of the sectional paths to obtain the optimal driving route.
Preferably, the method further comprises:
acquiring first feedback information input by website personnel, wherein the first feedback information is feedback on the predicted money adding time;
if the first feedback information is satisfactory, updating and training the banknote adding time sequence prediction model according to the predicted banknote adding time and the current banknote time sequence data of each network point to obtain an updated banknote adding time sequence prediction model;
and if the first feedback information is unsatisfactory, updating and training the banknote adding time sequence prediction model according to the recommended banknote adding time input by personnel at the network points and the current banknote time sequence data of each network point to obtain the updated banknote adding time sequence prediction model.
Preferably, the updating training of the banknote adding time sequence prediction model is performed according to the predicted banknote adding time and the current banknote time sequence data of each network point, so as to obtain the updated banknote adding time sequence prediction model, and the updating training comprises the following steps:
determining the predicted banknote adding time as a first updated training label;
determining the current banknote time sequence data of each network point as first updated training data;
and updating and training the banknote adding time sequence prediction model according to the first updating training label and the first updating training data to obtain an updated banknote adding time sequence prediction model.
Preferably, the updating training of the banknote adding time sequence prediction model is performed according to the recommended banknote adding time input by personnel at the network nodes and the current banknote time sequence data of each network node, so as to obtain the updated banknote adding time sequence prediction model, and the updating training comprises the following steps:
determining the recommended cash adding time input by website personnel as a second updated training label;
determining the current banknote time sequence data of each network point as second updated training data;
and updating and training the banknote adding time sequence prediction model according to the second updating training label and the second updating training data to obtain an updated banknote adding time sequence prediction model.
Preferably, the method further comprises:
acquiring second feedback information input by a driver, wherein the second feedback information is feedback on the optimal driving route;
if the second feedback information is satisfactory, updating and training the route planning model according to the optimal running route, the predicted money adding time and the road information to obtain an updated route planning model;
and if the second feedback information is unsatisfactory, updating and training the route planning model according to the recommended driving route, the predicted money adding time and the road information input by the driving personnel to obtain an updated route planning model.
Preferably, the updating training of the route planning model is performed according to the optimal driving route, the predicted money adding time and the road information, so as to obtain an updated route planning model, and the method comprises the following steps:
determining the optimal driving route as a third updated training label;
determining the predicted banknote adding time and the road information as third updating training data;
and updating and training the route planning model according to the third updated training label and the third updated training data to obtain an updated route planning model.
Preferably, the updating training of the route planning model is performed according to the recommended travel route, the predicted money adding time and the road information input by the travel personnel, so as to obtain the updated route planning model, and the method comprises the following steps:
determining the recommended driving route as a fourth updated training label;
determining the predicted banknote adding time and the road information as fourth updated training data;
and updating and training the route planning model according to the fourth updating training label and the fourth updating training data to obtain an updated route planning model.
The invention also discloses a driving route planning device, which comprises:
the model building unit is used for training the deep learning network according to the historical transaction data, the historical cash adding time, the acquired road information and the historical route of each network point and building a cash adding route planning model;
and the route planning unit is used for carrying out route planning on the generated current banknote time sequence data and road information of each network point through the banknote adding route planning model to obtain an optimal driving route.
The invention also discloses a computer-readable medium, on which a computer program is stored which, when executed by a processor, implements a method as described above.
The invention also discloses a computer device comprising a memory for storing information comprising program instructions and a processor for controlling the execution of the program instructions, the processor implementing the method as described above when executing the program.
The invention also discloses a computer program product comprising computer programs/instructions which, when executed by a processor, implement the method as described above.
According to historical transaction data, historical cash adding time, acquired road information and historical routes of all network points, training a deep learning network, and constructing a cash adding route planning model; the generated current banknote time sequence data and road information of each network point are subjected to route planning through the banknote adding route planning model, an optimal driving route is obtained, the banknote adding requirement and the timeliness requirement of each network point can be met, the stability, the flexibility and the usability of the system are improved, the time, the labor and the material cost are saved, and the driving route is planned efficiently.
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 embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of a driving route planning method according to an embodiment of the present invention;
fig. 2 is a flowchart of another driving route planning method according to an embodiment of the present invention;
fig. 3 is a flowchart of updating a money adding route planning model according to feedback optimization of network personnel according to an embodiment of the present invention;
fig. 4 is a flowchart of an embodiment of updating the money charging route planning model according to feedback optimization of transportation personnel;
fig. 5 is a schematic structural diagram of a driving route planning apparatus according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a computer device according to an embodiment of the present invention.
Detailed Description
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 only a part of the embodiments of the present invention, and not all of the embodiments. 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.
It should be noted that the driving route planning method and device disclosed by the application can be used in the technical field of artificial intelligence, and can also be used in any field except the technical field of artificial intelligence.
In order to facilitate understanding of the technical solutions provided in the present application, the following first describes relevant contents of the technical solutions in the present application. The invention obtains the optimal money adding time through a historical transaction record deep learning model of all money adding points in a pre-training area, flexibly processes all factors influencing a money transporting route through a deep learning network (transform) graph convolution deep learning mode, and provides the intelligent route planning method of the money transporting vehicle without manual control.
The following describes an implementation process of the driving route planning method provided by the embodiment of the present invention, taking the driving route planning device as an execution subject. It can be understood that the execution subject of the driving route planning method provided by the embodiment of the invention includes, but is not limited to, a driving route planning device.
Fig. 1 is a flowchart of a driving route planning method according to an embodiment of the present invention, and as shown in fig. 1, the method includes:
And 102, carrying out route planning on the generated current banknote time sequence data and road information of each network point through a banknote adding route planning model to obtain an optimal driving route.
In the technical scheme provided by the embodiment of the invention, a deep learning network is trained according to historical transaction data, historical cash adding time, acquired road information and historical routes of all network points, and a cash adding route planning model is constructed; the generated current banknote time sequence data and road information of each network point are subjected to route planning through the banknote adding route planning model, an optimal running route is obtained, the banknote adding requirements and timeliness requirements of each network point can be met, the stability, flexibility and usability of the system are improved, the time, manpower and material resources are saved, and the running route is efficiently planned.
Fig. 2 is a flowchart of another driving route planning method according to an embodiment of the present invention, as shown in fig. 2, the method includes:
In the embodiment of the invention, each step is executed by the driving route planning device.
And step 2011, training the deep learning network according to historical transaction data, and constructing a money adding time sequence prediction model.
In the embodiment of the invention, the historical transaction data is stored in the database and can be acquired from the database. The historical transaction data includes historical banknote timing data and historical optimal banknote loading times. The banknote time sequence data is the required quantity of banknotes in the time sequence, and the optimal banknote adding time is the time point before the banknote quantity of the network points is alarmed.
Specifically, determining the historical optimal banknote adding time as a first training label; determining historical banknote timing sequence data as first training data; and training a deep learning network (transform) according to the first training label and the first training data to construct a banknote adding time sequence prediction model. The training process comprises the steps of taking first training data as input data, taking a first training label as correct output data, training a transformer until the accuracy of the model reaches a preset first threshold value, and constructing to obtain a banknote adding time sequence prediction model.
It should be noted that the first threshold may be set according to actual situations, and the embodiment of the present invention does not limit this.
Step 2012, training the deep learning network according to the historical cash adding time, the road information and the historical route, and constructing a route planning model.
In the embodiment of the invention, the historical cash adding time and the historical route are stored in the database and can be acquired from the database. The road information belongs to external source data and can be acquired from a third-party platform, and the third-party platform can be a map related platform capable of acquiring road structure and live information.
Specifically, the historical route is determined as a second training label; determining the historical cash adding time and the road information as second training data; and training the deep learning network according to the second training label and the second training data to construct a route planning model. And in the training process, the second training data is used as input data, the second training labels are used as correct output data, the transformer is trained until the model accuracy reaches a preset second threshold value, and the route planning model is constructed.
It is worth to be noted that the training process of the route planning model includes training of internal modules of the model, and the internal modules include a feature extraction module, a money adding time dynamic feature module, a segment path dynamic feature module and a fusion module.
It should be noted that the second threshold may be set according to actual situations, and the embodiment of the present invention does not limit this.
And 2013, generating a money adding route planning model according to the money adding time sequence prediction model and the route planning model.
As an alternative scheme, the established money adding time sequence prediction model and the route planning model are combined to form a money adding route planning model, the money adding route planning model can accurately predict the optimal money adding time and the optimal form route, and can be used for subsequent securicar driving route planning, so that the cost is saved, and the planning efficiency is improved.
In the embodiment of the present invention, the time period and the time period may be set according to actual situations, which is not limited in the embodiment of the present invention. The current cash transaction flow includes, but is not limited to, a sheet number, time, bill data information, remaining amount of bills, required amount of bills, and user information, and the required amount of bills for each time period is extracted from the current cash transaction flow.
And step 203, generating current banknote time sequence data according to the banknote demand of each time period.
In the embodiment of the invention, the banknote demand of each time period is summarized to generate the banknote demand under the time sequence, namely: current banknote timing data.
And step 204, carrying out route planning on the generated current banknote time sequence data and road information of each network point through a banknote adding route planning model to obtain an optimal driving route.
In the embodiment of the invention, the money adding route planning model comprises a money adding time sequence prediction model and a route planning model.
In the embodiment of the present invention, step 204 specifically includes:
and 2041, predicting according to the current banknote timing sequence data through a banknote adding timing sequence prediction model to obtain the predicted banknote adding time of each network point.
Specifically, the current banknote timing sequence data is input into the banknote adding timing sequence prediction model, and the predicted banknote adding time of each network point is output.
Step 2042, carrying out convolution calculation on the predicted cash adding time and the road information through a route planning model to obtain an optimal driving route.
In the embodiment of the invention, the road information comprises a regional traffic static control structure and road live information of each network point. The road information belongs to external source data and can be obtained from a third-party platform. Specifically, the traffic static control structure and the road live information of each network point can be acquired according to a preset time interval, so as to provide a reliable road information basis for route planning. It should be noted that the third-party platform may be a map-related platform capable of acquiring road structure and live information, and the specific selection of the third-party platform is not limited in the embodiment of the present invention.
In the embodiment of the invention, the characteristics of the predicted cash adding time, the regional traffic static spatial structure and the road live information of each network point are respectively extracted to obtain the predicted cash adding time characteristics, the regional traffic static spatial structure characteristics and the road live characteristics of each network point.
Specifically, the transformer comprises a detector node, and the detector node is used for carrying out feature extraction on the predicted banknote adding time to obtain the predicted banknote adding time feature; performing feature extraction on the regional traffic static space structure through a detector node to obtain regional traffic static space structure features; and performing feature extraction on the road live information of each network point through a detector node to obtain the road live feature of each network point. And predicting the banknote adding time characteristic, the regional traffic static space structure characteristic and the road live characteristic of each network point as the feature representation after convolution for subsequent processing of a route planning model.
In the embodiment of the invention, the predicted cash adding time characteristic and the regional traffic static space structure characteristic are subjected to convolution calculation to obtain a dynamic cash adding time characteristic, and the dynamic cash adding time characteristic is used for planning the initial path and the total distance of the whole driving route of the securicar.
In the embodiment of the invention, the convolution calculation is carried out on the regional traffic static spatial structure characteristics and the road live characteristics of all network points to obtain the dynamic characteristics of the segmented path. The road condition characteristics of each network point are road condition information among the network points in the area, and the road condition characteristics among the network points and the static spatial structure characteristics of the area traffic are processed to obtain the dynamic characteristics of the segmented paths among the network points so as to reflect the dynamic change relationship of the road and obtain the optimal route among the network points.
In the embodiment of the invention, the dynamic characteristics of the money adding time and the dynamic characteristics of the sectional paths are fused and calculated to obtain the optimal driving route.
Specifically, the banknote adding time dynamic characteristic and the subsection path dynamic characteristic are subjected to fusion calculation through two layers of convolution layers, and an optimal driving route is obtained.
And further, the traveling personnel travel the securicar according to the predicted optimal traveling route and bill adding is carried out on each branch according to the predicted bill adding time. After the money adding is finished, the money adding situation is fed back by the network point personnel and the traveling personnel so as to optimize and update the money adding route planning model subsequently.
Fig. 3 is a flowchart of optimizing and updating a money adding route planning model according to feedback of network personnel according to an embodiment of the present invention, as shown in fig. 3, including:
In the embodiment of the invention, after the money adding is finished, the personnel at the network site inputs the first feedback information, and the first feedback information is satisfied or unsatisfied.
In the embodiment of the invention, if the first feedback information is satisfactory, the website personnel is satisfied with the current money adding time, and the step 303 is continuously executed; if the first feedback information is unsatisfactory, it indicates that the staff at the outlet is unsatisfactory for the current bill adding time, and step 304 is executed.
Further, if the first feedback information is unsatisfactory, it indicates that the money adding time is unsatisfactory, and the money adding time is required to be input by the personnel at the network point.
And 303, updating and training the banknote adding time sequence prediction model according to the predicted banknote adding time and the current banknote time sequence data of each network point to obtain an updated banknote adding time sequence prediction model, and ending the process.
In the embodiment of the invention, if the first feedback information is satisfactory, the predicted cash adding time is the optimal cash adding time of the time. Specifically, the predicted banknote adding time is determined as a first updated training label; determining the current banknote time sequence data of each network point as first updated training data; and updating and training the banknote adding time sequence prediction model according to the first updating training label and the first updating training data to obtain an updated banknote adding time sequence prediction model. And in the training process, the first updating data is used as input data, the first updating label is used as correct output data, the banknote adding time sequence prediction model is updated and trained until the model accuracy reaches a preset first updating threshold value, and the updated banknote adding time sequence prediction model is constructed.
It should be noted that the first update threshold may be set according to actual situations, which is not limited in the embodiment of the present invention.
And step 304, updating and training the banknote adding time sequence prediction model according to the recommended banknote adding time input by personnel at the network nodes and the current banknote time sequence data of each network node to obtain the updated banknote adding time sequence prediction model.
In the embodiment of the invention, if the first feedback information is unsatisfactory, the predicted cash adding time cannot be used as the optimal cash adding time of the time. Specifically, the recommended banknote adding time input by the website personnel is determined as a second updated training label; determining the current banknote time sequence data of each network point as second updated training data; and updating and training the banknote adding time sequence prediction model according to the second updating training label and the second updating training data to obtain an updated banknote adding time sequence prediction model. And in the training process, the second updating data is used as input data, the second updating label is used as correct output data, the banknote adding time sequence prediction model is updated and trained until the model accuracy reaches a preset second updating threshold value, and the updated banknote adding time sequence prediction model is constructed.
It should be noted that the second update threshold may be set according to actual situations, which is not limited in the embodiment of the present invention.
In the embodiment of the invention, the cash adding time sequence prediction model is updated in time according to the feedback of the personnel at the network points, so that the accuracy of the cash adding time sequence prediction model can be further improved.
Fig. 4 is a flowchart of an embodiment of the present invention for optimizing and updating a money charging route planning model according to feedback of a transport person, and as shown in fig. 4, the flowchart includes:
In the embodiment of the invention, after the money is added, the driving personnel inputs the second feedback information, and the second feedback information is satisfactory or unsatisfactory.
In the embodiment of the invention, if the second feedback information is satisfactory, the transportation personnel is satisfied with the planned driving route, and the step 403 is continuously executed; if the second feedback information is unsatisfactory, it indicates that the transportation personnel is unsatisfactory on the planned driving route, and step 404 is executed.
Further, if the second feedback information is unsatisfactory, it indicates that the transportation staff is unsatisfactory to the planned driving route, and the transportation staff is required to input the recommended driving route.
And 403, updating and training the route planning model according to the optimal driving route, the predicted money adding time and the road information to obtain an updated route planning model.
In the embodiment of the invention, if the second feedback information is satisfactory, the planned driving route is the optimal driving route. Specifically, the optimal driving route is determined as a third updated training label; determining the predicted banknote adding time and the road information as third updating training data; and updating and training the route planning model according to the third updated training label and the third updated training data to obtain an updated route planning model. And in the training process, the third updating data is used as input data, the third updating label is used as correct output data, the route planning model is updated and trained until the model accuracy reaches a preset third updating threshold, and the updated route planning model is constructed.
It should be noted that the third update threshold may be set according to actual situations, which is not limited in the embodiment of the present invention.
And step 404, updating and training the route planning model according to the recommended driving route, the predicted money adding time and the road information input by the driving personnel to obtain an updated route planning model.
In the embodiment of the invention, if the second feedback information is unsatisfactory, the planned driving route cannot be used as the optimal driving route. Specifically, the recommended travel route is determined as a fourth updated training label; determining the predicted banknote adding time and the road information as fourth updated training data; and updating and training the route planning model according to the fourth updating training label and the fourth updating training data to obtain an updated route planning model. And in the training process, the fourth updating data is used as input data, the fourth updating label is used as correct output data, the route planning model is updated and trained until the model accuracy reaches a preset fourth updating threshold, and the updated route planning model is constructed.
It should be noted that the fourth update threshold may be set according to actual situations, which is not limited in the embodiment of the present invention.
In the embodiment of the invention, the optimal cash adding time is generated by considering the historical transaction data of each network point, so that the cash adding requirements of each network point in various aspects such as the cash adding time, the cash demand and the like can be better met; training and constructing a banknote adding time sequence prediction model and a route planning model through a transformer, so that a complex scene can be processed, and the method is flexible and stable; the optimal driving route can be generated in an end-to-end deep learning mode, an available algorithm can be called out only by a large amount of training, parameters such as a search range and a return number do not need to be manually controlled, and the usability is high.
In the technical scheme of the driving route planning method provided by the embodiment of the invention, a deep learning network is trained according to historical transaction data, historical cash adding time, acquired road information and historical routes of all network points, and a cash adding route planning model is constructed; the generated current banknote time sequence data and road information of each network point are subjected to route planning through the banknote adding route planning model, an optimal driving route is obtained, the banknote adding requirement and the timeliness requirement of each network point can be met, the stability, the flexibility and the usability of the system are improved, the time, the labor and the material cost are saved, and the driving route is planned efficiently.
Fig. 5 is a schematic structural diagram of a driving route planning apparatus according to an embodiment of the present invention, the apparatus is configured to execute the driving route planning method, and as shown in fig. 5, the apparatus includes: a model building unit 11 and a route planning unit 12.
The model building unit 11 is used for training the deep learning network according to the historical transaction data, the historical cash adding time, the acquired road information and the historical route of each website, and building a cash adding route planning model.
The route planning unit 12 is configured to perform route planning on the generated current banknote time sequence data and road information of each network point through a banknote adding route planning model to obtain an optimal driving route.
In the embodiment of the invention, the model construction unit 11 is specifically used for training the deep learning network according to historical transaction data and constructing a banknote adding time sequence prediction model; training the deep learning network according to historical cash adding time, road information and a historical route, and constructing a route planning model; and generating a money adding route planning model according to the money adding time sequence prediction model and the route planning model.
In the embodiment of the invention, the historical transaction data comprises historical banknote timing sequence data and historical optimal banknote adding time; the model construction unit 11 is specifically configured to determine the historical optimal banknote adding time as a first training label; determining historical banknote timing sequence data as first training data; and training the deep learning network according to the first training label and the first training data to construct a banknote adding time sequence prediction model.
In the embodiment of the present invention, the model building unit 11 is specifically configured to determine the historical route as a second training label; determining the historical cash adding time and the road information as second training data; and training the deep learning network according to the second training label and the second training data to construct a route planning model.
In the embodiment of the present invention, the apparatus further includes: a screening unit 13 and a generating unit 14.
The sorting unit 13 is configured to sort out a required amount of bills for each time period in a specified time period from the obtained current cash transaction flow.
The generation unit 14 is used for generating the current banknote timing sequence data according to the banknote demand amount of each time period.
In the embodiment of the invention, the money adding route planning model comprises a money adding time sequence prediction model and a route planning model; the route planning unit 12 is specifically configured to predict, according to the current banknote timing data, the banknote adding timing sequence prediction model to obtain the predicted banknote adding time of each network point; and carrying out convolution calculation on the predicted cash adding time and the road information through a route planning model to obtain an optimal driving route.
In the embodiment of the invention, the road information comprises a regional traffic static control structure and road live information of each network point; the route planning unit 12 is specifically configured to perform feature extraction on the predicted banknote adding time, the regional traffic static spatial structure, and the road condition information of each network point through the detector node, to obtain predicted banknote adding time features, regional traffic static spatial structure features, and road condition features of each network point; carrying out convolution calculation on the predicted cash adding time characteristic and the regional traffic static space structure characteristic to obtain a dynamic characteristic of the cash adding time; performing convolution calculation on the regional traffic static spatial structure characteristics and the road live characteristics of all network points to obtain the dynamic characteristics of the segmented path; and carrying out fusion calculation on the dynamic characteristics of the money adding time and the dynamic characteristics of the sectional paths to obtain the optimal driving route.
In the embodiment of the present invention, the apparatus further includes: a first obtaining unit 15, a first updating unit 16 and a second updating unit 17.
The first obtaining unit 15 is configured to obtain first feedback information input by a website worker, where the first feedback information is feedback of the predicted cash adding time.
The first updating unit 16 is configured to, if the first feedback information is satisfactory, update and train the banknote adding timing sequence prediction model according to the predicted banknote adding time and the current banknote timing sequence data of each network point, so as to obtain an updated banknote adding timing sequence prediction model.
And the second updating unit 17 is configured to update and train the banknote adding time sequence prediction model according to the recommended banknote adding time input by the personnel at the network nodes and the current banknote time sequence data of each network node if the first feedback information is unsatisfactory, so as to obtain an updated banknote adding time sequence prediction model.
In the embodiment of the present invention, the first updating unit 16 is specifically configured to determine the predicted banknote adding time as a first updated training label; determining the current banknote time sequence data of each network point as first updated training data; and updating and training the banknote adding time sequence prediction model according to the first updating training label and the first updating training data to obtain an updated banknote adding time sequence prediction model.
In the embodiment of the present invention, the second updating unit 17 is specifically configured to determine a recommended banknote adding time input by website personnel as a second updated training label; determining the current banknote time sequence data of each network point as second updated training data; and updating and training the banknote adding time sequence prediction model according to the second updating training label and the second updating training data to obtain an updated banknote adding time sequence prediction model.
In the embodiment of the present invention, the apparatus further includes: a second obtaining unit 18, a third updating unit 19 and a fourth updating unit 20.
The second obtaining unit 18 is configured to obtain second feedback information input by the driver, where the second feedback information is feedback on the optimal driving route.
And the third updating unit 19 is configured to, if the second feedback information is satisfactory, perform updating training on the route planning model according to the optimal driving route, the predicted cash adding time and the road information to obtain an updated route planning model.
The fourth updating unit 20 is configured to, if the second feedback information is unsatisfactory, perform updating training on the route planning model according to the recommended travel route, the predicted cash adding time, and the road information input by the travel staff, so as to obtain an updated route planning model.
In the embodiment of the present invention, the third updating unit 19 is specifically configured to determine the optimal driving route as a third updated training label; determining the predicted banknote adding time and the road information as third updating training data; and updating and training the route planning model according to the third updated training label and the third updated training data to obtain an updated route planning model.
In the embodiment of the present invention, the fourth updating unit 20 is specifically configured to determine the recommended driving route as a fourth updated training label; determining the predicted banknote adding time and the road information as fourth updated training data; and updating and training the route planning model according to the fourth updating and training label and the fourth updating and training data to obtain an updated route planning model.
In the scheme of the embodiment of the invention, a deep learning network is trained according to historical transaction data, historical cash adding time, acquired road information and historical routes of all network points, and a cash adding route planning model is constructed; the generated current banknote time sequence data and road information of each network point are subjected to route planning through the banknote adding route planning model, an optimal driving route is obtained, the banknote adding requirement and the timeliness requirement of each network point can be met, the stability, the flexibility and the usability of the system are improved, the time, the labor and the material cost are saved, and the driving route is planned efficiently.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. A typical implementation device is a computer 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.
Embodiments of the present invention provide a computer device, including a memory and a processor, where the memory is configured to store information including program instructions, and the processor is configured to control execution of the program instructions, and the program instructions are loaded and executed by the processor to implement the steps of the embodiment of the driving route planning method, and specific descriptions may refer to the embodiment of the driving route planning method.
Referring now to FIG. 6, shown is a schematic diagram of a computer device 600 suitable for use in implementing embodiments of the present application.
As shown in fig. 6, the computer apparatus 600 includes a Central Processing Unit (CPU) 601 which 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 computer apparatus 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 section 607 including a Cathode Ray Tube (CRT), a liquid crystal feedback (LCD), and the like, and a speaker and the like; 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, the processes described above with reference to the flowcharts may be implemented as a computer software program according to an embodiment of the present invention. For example, embodiments of the invention include a computer program product comprising a computer program tangibly embodied on a machine-readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. 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.
According to the technical scheme, the data acquisition, storage, use, processing and the like meet relevant regulations of national laws and regulations.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application 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.
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 (14)
1. A method of travel route planning, the method comprising:
training a deep learning network according to historical transaction data, historical cash adding time, acquired road information and historical routes of all network points, and constructing a cash adding route planning model, wherein the cash adding route planning model comprises a cash adding time sequence prediction model and a route planning model;
carrying out route planning on the generated current banknote time sequence data and road information of each network point through the banknote adding route planning model to obtain an optimal driving route, wherein the road information comprises a regional traffic static control structure and road live information of each network point;
the method for carrying out route planning on the generated current banknote time sequence data and road information of each network point through the banknote adding route planning model to obtain the optimal driving route comprises the following steps:
predicting according to the current banknote timing sequence data through the banknote adding timing sequence prediction model to obtain the predicted banknote adding time of each network point;
carrying out convolution calculation on the predicted cash adding time and road information through the route planning model to obtain the optimal driving route;
the obtaining the optimal driving route by performing convolution calculation on the predicted cash adding time and the road information through the route planning model comprises the following steps:
respectively extracting the characteristics of the predicted cash adding time, the regional traffic static space structure and the road condition information of each network point through a detector node to obtain predicted cash adding time characteristics, regional traffic static space structure characteristics and road condition characteristics of each network point;
carrying out convolution calculation on the predicted banknote adding time characteristic and the regional traffic static space structure characteristic to obtain a banknote adding time dynamic characteristic;
performing convolution calculation on the regional traffic static spatial structure characteristics and road live characteristics of all network points to obtain dynamic characteristics of a segmented path;
and performing fusion calculation on the dynamic characteristics of the cash adding time and the dynamic characteristics of the sectional paths to obtain the optimal driving route, wherein the time sequence data of the cash is the required amount of the cash in time sequence, and the optimal cash adding time is the time point before the cash amount of the website is alarmed.
2. The method for planning a driving route according to claim 1, wherein the training of the deep learning network and the construction of the money-added route planning model according to the historical transaction data, the historical money-added time, the acquired road information and the historical route of each website comprises:
training a deep learning network according to the historical transaction data, and constructing a banknote adding time sequence prediction model;
training a deep learning network according to the historical cash adding time, the road information and the historical route, and constructing a route planning model;
and generating a money adding route planning model according to the money adding time sequence prediction model and the route planning model.
3. The travel route planning method according to claim 2, wherein the historical transaction data includes historical banknote timing data and historical optimal banknote adding time;
training a deep learning network according to the historical transaction data to construct a banknote adding time sequence prediction model, wherein the method comprises the following steps:
determining the historical optimal banknote adding time as a first training label;
determining the historical banknote timing data as first training data;
and training the deep learning network according to the first training label and the first training data to construct a banknote adding time sequence prediction model.
4. The method for planning a driving route according to claim 2, wherein the training of the deep learning network according to the historical cash adding time, the road information and the historical route to construct a route planning model comprises:
determining the historical route as a second training label;
determining the historical cash adding time and the road information as second training data;
and training the deep learning network according to the second training label and the second training data to construct a route planning model.
5. The method for planning a driving route according to claim 1, wherein before the generating the current banknote timing sequence data and the road information of each website by the banknote adding route planning model to obtain the optimal driving route, the method further comprises:
screening out the required amount of the banknotes in each time period in a specified time period from the obtained current cash transaction running water;
and generating current banknote time sequence data according to the banknote demand of each time period.
6. The travel route planning method according to claim 1, characterized in that the method further comprises:
acquiring first feedback information input by website personnel, wherein the first feedback information is feedback on the predicted money adding time;
if the first feedback information is satisfactory, updating and training the banknote adding time sequence prediction model according to the predicted banknote adding time and the current banknote time sequence data of each network point to obtain an updated banknote adding time sequence prediction model;
and if the first feedback information is unsatisfactory, updating and training the banknote adding time sequence prediction model according to the recommended banknote adding time input by personnel at the network points and the current banknote time sequence data of each network point to obtain the updated banknote adding time sequence prediction model.
7. The method for planning a travel route according to claim 6, wherein the updating and training of the banknote adding time sequence prediction model according to the predicted banknote adding time and the current banknote time sequence data of each network point to obtain an updated banknote adding time sequence prediction model comprises:
determining the predicted banknote adding time as a first updated training label;
determining the current banknote time sequence data of each network point as first updated training data;
and updating and training the banknote adding time sequence prediction model according to the first updating training label and the first updating training data to obtain an updated banknote adding time sequence prediction model.
8. The method for planning a driving route according to claim 6, wherein the updating and training of the banknote adding time sequence prediction model according to the recommended banknote adding time input by personnel at network points and the current banknote time sequence data of each network point to obtain an updated banknote adding time sequence prediction model comprises:
determining the recommended banknote adding time input by the website personnel as a second updated training label;
determining the current banknote time sequence data of each network point as second updated training data;
and updating and training the banknote adding time sequence prediction model according to the second updating training label and the second updating training data to obtain an updated banknote adding time sequence prediction model.
9. The travel route planning method according to claim 1, characterized in that the method further comprises:
acquiring second feedback information input by a driver, wherein the second feedback information is feedback on the optimal driving route;
if the second feedback information is satisfactory, updating and training the route planning model according to the optimal running route, the predicted cash adding time and the road information to obtain an updated route planning model;
and if the second feedback information is unsatisfactory, updating and training the route planning model according to the recommended driving route, the predicted cash adding time and the road information input by the driving personnel to obtain an updated route planning model.
10. The method for planning a driving route according to claim 9, wherein the updating and training of the route planning model according to the optimal driving route, the predicted cash adding time and the road information to obtain an updated route planning model comprises:
determining the optimal driving route as a third updated training label;
determining the predicted banknote adding time and the road information as third updating training data;
and updating and training the route planning model according to the third updated training labels and the third updated training data to obtain an updated route planning model.
11. The method for planning a driving route according to claim 9, wherein the step of performing update training on the route planning model according to the recommended driving route, the predicted cash adding time and the road information input by the driving personnel to obtain an updated route planning model comprises:
determining the recommended travel route as a fourth updated training label;
determining the predicted banknote adding time and the road information as fourth updated training data;
and updating and training the route planning model according to the fourth updating and training label and the fourth updating and training data to obtain an updated route planning model.
12. A travel route planning apparatus, characterized in that the apparatus comprises:
the system comprises a model building unit, a money adding unit and a money adding unit, wherein the model building unit is used for training a deep learning network according to historical transaction data, historical money adding time, acquired road information and historical routes of all network points and building a money adding route planning model, and the money adding route planning model comprises a money adding time sequence prediction model and a route planning model;
the route planning unit is used for carrying out route planning on the generated current banknote time sequence data and road information of each network point through the banknote adding route planning model to obtain an optimal driving route, wherein the road information comprises a regional traffic static control structure and road live information of each network point;
the route planning unit is specifically used for predicting according to the current banknote timing sequence data through the banknote adding timing sequence prediction model to obtain the predicted banknote adding time of each network point; carrying out convolution calculation on the predicted cash adding time and road information through the route planning model to obtain the optimal driving route;
the route planning unit is specifically used for respectively extracting the characteristics of the predicted cash adding time, the regional traffic static spatial structure and the road live information of each network point through the detector node to obtain the predicted cash adding time characteristics, the regional traffic static spatial structure characteristics and the road live characteristics of each network point; carrying out convolution calculation on the predicted banknote adding time characteristic and the regional traffic static space structure characteristic to obtain a banknote adding time dynamic characteristic; performing convolution calculation on the regional traffic static spatial structure characteristics and the road live characteristics of all network points to obtain dynamic characteristics of the segmented paths; and performing fusion calculation on the banknote adding time dynamic characteristics and the segmentation path dynamic characteristics to obtain the optimal driving route, wherein the banknote time sequence data is the banknote demand amount under the time sequence, and the optimal banknote adding time is the time point before the banknote amount alarm of the network point.
13. A computer-readable medium, on which a computer program is stored which, when being executed by a processor, carries out a method for driving route planning according to any one of claims 1 to 11.
14. A computer device comprising a memory for storing information including program instructions and a processor for controlling the execution of the program instructions, characterized in that the program instructions are loaded and executed by the processor to implement a method of travel route planning according to any of claims 1 to 11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210275576.3A CN114358448B (en) | 2022-03-21 | 2022-03-21 | Driving route planning method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210275576.3A CN114358448B (en) | 2022-03-21 | 2022-03-21 | Driving route planning method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114358448A CN114358448A (en) | 2022-04-15 |
| CN114358448B true CN114358448B (en) | 2022-05-24 |
Family
ID=81095177
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210275576.3A Active CN114358448B (en) | 2022-03-21 | 2022-03-21 | Driving route planning method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114358448B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI847492B (en) * | 2023-01-11 | 2024-07-01 | 永豐商業銀行股份有限公司 | Decision-making assistance system and method for intelligent scheduling |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106022600A (en) * | 2016-05-18 | 2016-10-12 | 上海鼎数信息技术有限公司 | Method for determining cash supplement strategy of multiple cash flow stations in specific period |
| CN109447354A (en) * | 2018-10-31 | 2019-03-08 | 中国银行股份有限公司 | A kind of intelligent bank note distribution method and device based on GA-BP neural network |
| CN109615760A (en) * | 2018-12-17 | 2019-04-12 | 山东省城市商业银行合作联盟有限公司 | Intelligently add the method and system of clear paper money to ATM in bank based on machine learning |
| CN110222739A (en) * | 2019-05-23 | 2019-09-10 | 中国银行股份有限公司 | Model construction, site cash Demand Forecast method, apparatus and storage medium |
| CN110363357A (en) * | 2019-07-17 | 2019-10-22 | 中国银行股份有限公司 | A kind of intelligence bank note distribution method and system |
| CN110415462A (en) * | 2019-07-31 | 2019-11-05 | 中国工商银行股份有限公司 | Atm device adds paper money optimization method and device |
| CN110490392A (en) * | 2019-09-20 | 2019-11-22 | 中国银行股份有限公司 | Site bank note distribution method and device |
| CN110633863A (en) * | 2019-09-20 | 2019-12-31 | 中国银行股份有限公司 | Bank note distribution prediction method and device based on GBDT algorithm |
| CN111507536A (en) * | 2020-04-26 | 2020-08-07 | 中国工商银行股份有限公司 | Bank escort vehicle line planning method and device |
| CN112749842A (en) * | 2021-01-11 | 2021-05-04 | 中国工商银行股份有限公司 | Escort path planning method and device |
| CN112926787A (en) * | 2021-03-15 | 2021-06-08 | 中国工商银行股份有限公司 | Route planning method and device for cash truck |
| CN113191880A (en) * | 2021-05-24 | 2021-07-30 | 中国工商银行股份有限公司 | Bank teller terminal cash adding suggestion determination method and device |
| CN113205227A (en) * | 2021-05-28 | 2021-08-03 | 中国工商银行股份有限公司 | Vehicle route optimization method and device |
| WO2021169009A1 (en) * | 2020-02-27 | 2021-09-02 | 中车唐山机车车辆有限公司 | Cargo management system for rail train |
| CN113418533A (en) * | 2021-06-22 | 2021-09-21 | 中国银行股份有限公司 | Route planning method and device for securicar |
| CN114066180A (en) * | 2021-10-29 | 2022-02-18 | 上海浦东发展银行股份有限公司 | Banknote distribution method, banknote distribution device, computer equipment and storage medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7590589B2 (en) * | 2004-09-10 | 2009-09-15 | Hoffberg Steven M | Game theoretic prioritization scheme for mobile ad hoc networks permitting hierarchal deference |
| MX2020013312A (en) * | 2018-06-07 | 2021-06-08 | Deka Products Lp | System and method for distributed utility service execution. |
-
2022
- 2022-03-21 CN CN202210275576.3A patent/CN114358448B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106022600A (en) * | 2016-05-18 | 2016-10-12 | 上海鼎数信息技术有限公司 | Method for determining cash supplement strategy of multiple cash flow stations in specific period |
| CN109447354A (en) * | 2018-10-31 | 2019-03-08 | 中国银行股份有限公司 | A kind of intelligent bank note distribution method and device based on GA-BP neural network |
| CN109615760A (en) * | 2018-12-17 | 2019-04-12 | 山东省城市商业银行合作联盟有限公司 | Intelligently add the method and system of clear paper money to ATM in bank based on machine learning |
| CN110222739A (en) * | 2019-05-23 | 2019-09-10 | 中国银行股份有限公司 | Model construction, site cash Demand Forecast method, apparatus and storage medium |
| CN110363357A (en) * | 2019-07-17 | 2019-10-22 | 中国银行股份有限公司 | A kind of intelligence bank note distribution method and system |
| CN110415462A (en) * | 2019-07-31 | 2019-11-05 | 中国工商银行股份有限公司 | Atm device adds paper money optimization method and device |
| CN110490392A (en) * | 2019-09-20 | 2019-11-22 | 中国银行股份有限公司 | Site bank note distribution method and device |
| CN110633863A (en) * | 2019-09-20 | 2019-12-31 | 中国银行股份有限公司 | Bank note distribution prediction method and device based on GBDT algorithm |
| WO2021169009A1 (en) * | 2020-02-27 | 2021-09-02 | 中车唐山机车车辆有限公司 | Cargo management system for rail train |
| CN111507536A (en) * | 2020-04-26 | 2020-08-07 | 中国工商银行股份有限公司 | Bank escort vehicle line planning method and device |
| CN112749842A (en) * | 2021-01-11 | 2021-05-04 | 中国工商银行股份有限公司 | Escort path planning method and device |
| CN112926787A (en) * | 2021-03-15 | 2021-06-08 | 中国工商银行股份有限公司 | Route planning method and device for cash truck |
| CN113191880A (en) * | 2021-05-24 | 2021-07-30 | 中国工商银行股份有限公司 | Bank teller terminal cash adding suggestion determination method and device |
| CN113205227A (en) * | 2021-05-28 | 2021-08-03 | 中国工商银行股份有限公司 | Vehicle route optimization method and device |
| CN113418533A (en) * | 2021-06-22 | 2021-09-21 | 中国银行股份有限公司 | Route planning method and device for securicar |
| CN114066180A (en) * | 2021-10-29 | 2022-02-18 | 上海浦东发展银行股份有限公司 | Banknote distribution method, banknote distribution device, computer equipment and storage medium |
Non-Patent Citations (3)
| Title |
|---|
| ThibautVidal 等.A concise guide to existing and emerging vehicle routing problem variants.《European Journal of Operational Research》.2020,第286卷(第2期), * |
| 刘晓 等.运钞车车辆路径规划策略.《计算机应用》.2011,第31卷(第04期),第1121-1124页. * |
| 徐呈康.银行ATM加钞路径及金额管理优化的研究与实现.《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑》.2019,第2019年 卷(第2期),第I138-1006页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114358448A (en) | 2022-04-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111768030B (en) | Bank transportation distribution line planning method, device, equipment and medium | |
| Yao et al. | Parallel hyper-heuristic algorithm for multi-objective route planning in a smart city | |
| CN108694673A (en) | A kind of processing method, device and the processing equipment of insurance business risk profile | |
| CN104050512A (en) | Transport time estimation based on multi-granular map | |
| Phiboonbanakit et al. | A hybrid reinforcement learning-based model for the vehicle routing problem in transportation logistics | |
| Shayanfar et al. | Prioritizing interrelated road projects using metaheuristics | |
| CN114358448B (en) | Driving route planning method and device | |
| Chmiel et al. | Intelligent route planning system based on interval computing | |
| Haliem et al. | AdaPool: A diurnal-adaptive fleet management framework using model-free deep reinforcement learning and change point detection | |
| Junta et al. | Predictive Analysis of Urban Planning for through the Operation of Artificial Cloud Network | |
| Halim et al. | On finding optimum commuting path in a road network: a computational approach for smart city traveling | |
| CN108171605A (en) | A kind of vehicle secondary mortgage alarm method, device, server and storage medium | |
| Mahdavian et al. | A universal automated data-driven modeling framework for truck traffic volume prediction | |
| Chuwang et al. | Short-term urban rail transit passenger flow forecasting based on fusion model methods using univariate time series | |
| Zheng et al. | Dynamic multi-objective balancing for online food delivery via fuzzy logic system-based supply–demand relationship identification | |
| CN118195341A (en) | Regional carbon emission prediction method and device based on road network and travel demand data | |
| CN116662815B (en) | Training method of time prediction model and related equipment | |
| CN116698075B (en) | Road network data processing method and device, electronic equipment and storage medium | |
| CN113344277A (en) | Prediction model training method, state updating method, device, equipment and medium | |
| CN110858355A (en) | Project budget balance prediction method and device | |
| Rodríguez-Rueda et al. | Origin–Destination matrix estimation and prediction from socioeconomic variables using automatic feature selection procedure-based machine learning model | |
| Hassannayebi et al. | A data analytics framework for reliable bus arrival time prediction using artificial neural networks | |
| Provoost et al. | Short term prediction of parking area states using real time data and machine learning techniques | |
| CN115983456A (en) | Method for global optimization of coal mine assisted transport and computer readable storage medium | |
| CN116468210A (en) | Vehicle dispatching method and device for coal mine auxiliary transportation and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |