CN114061604A - Passenger carrying route recommendation method, device and system based on movement track big data - Google Patents
Passenger carrying route recommendation method, device and system based on movement track big data Download PDFInfo
- Publication number
- CN114061604A CN114061604A CN202111190100.1A CN202111190100A CN114061604A CN 114061604 A CN114061604 A CN 114061604A CN 202111190100 A CN202111190100 A CN 202111190100A CN 114061604 A CN114061604 A CN 114061604A
- Authority
- CN
- China
- Prior art keywords
- data
- road network
- vehicle
- determining
- target
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 230000033001 locomotion Effects 0.000 title claims abstract description 36
- 238000009826 distribution Methods 0.000 claims abstract description 70
- 239000011159 matrix material Substances 0.000 claims abstract description 42
- 238000012545 processing Methods 0.000 claims description 23
- 230000006870 function Effects 0.000 claims description 19
- 239000003016 pheromone Substances 0.000 claims description 13
- 238000001914 filtration Methods 0.000 claims description 12
- 238000013467 fragmentation Methods 0.000 claims description 12
- 238000006062 fragmentation reaction Methods 0.000 claims description 12
- 238000005457 optimization Methods 0.000 claims description 11
- 238000012163 sequencing technique Methods 0.000 claims description 11
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 5
- 238000004140 cleaning Methods 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 abstract description 8
- 208000022417 sinus histiocytosis with massive lymphadenopathy Diseases 0.000 description 30
- 238000003860 storage Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 4
- 238000013500 data storage Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 241000257303 Hymenoptera Species 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 125000002015 acyclic group Chemical group 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000009024 positive feedback mechanism Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000029305 taxis Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3453—Special cost functions, i.e. other than distance or default speed limit of road segments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/18—File system types
- G06F16/182—Distributed file systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Automation & Control Theory (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- General Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Navigation (AREA)
- Traffic Control Systems (AREA)
Abstract
The embodiment of the application discloses a passenger carrying route recommending method, device and system based on moving track big data, and aims to improve timeliness of data transmission and accuracy of path recommendation. The method comprises the following steps: obtaining moving track data and urban road network data of vehicles in an HDFS file; converting the movement track data into a first elastic distribution data set based on RDD in Spark, and converting the urban road network data into a second elastic distribution data set based on RDD in Spark; determining a target field according to the first elastic distribution data set, wherein the target field comprises the identity information, the operation state, the time, the longitude and the latitude of the vehicle; determining road network node information according to the second elastic distribution data set; constructing a weighted undirected graph based on the longitude and latitude contained in the target field and the road network node information; determining a target adjacency matrix according to the weighted undirected graph; constructing a parallel BiA-ACO algorithm according to the target adjacency matrix; and executing BiA-ACO algorithm based on the RDD to generate the passenger carrying route recommendation result.
Description
Technical Field
The embodiment of the application relates to the field of data-driven intelligent transportation, in particular to a passenger carrying route recommendation method, device and system based on movement track big data.
Background
With the rapid development of smart cities and intelligent transportation, motor vehicles (such as taxis) have gradually become important transportation tools for residents to go out. In order to enable a driver to quickly arrive at a destination and avoid the problems of increased cost, energy waste and the like of the driver in the blind driving process, a vehicle is generally configured and provided with a global positioning navigation system so as to plan a path from a starting point to the destination and guide the driver to go out. In particular, route planning refers to the routing activity performed on a map during the navigation of a vehicle from a starting point to an ending point.
In addition to a global positioning navigation system, the traditional path planning method can also apply a serial algorithm to a single-machine centralized computing platform so as to plan and obtain a recommended path. However, with the explosive growth of traffic big data, the method needs to acquire and operate data in a huge scale, which is very easy to cause high memory consumption and high I/O overhead, thereby causing problems of time consuming data transmission, low path recommendation accuracy and the like.
Disclosure of Invention
The embodiment of the application provides a passenger carrying route recommending method, device and system based on big data of a moving track, so that the timeliness of data transmission is improved, and the accuracy of path recommendation is improved.
The application provides a passenger carrying route recommendation method based on movement track big data in a first aspect, which comprises the following steps:
obtaining moving track data and urban road network data of vehicles in an HDFS file;
converting the movement track data into a first elastic distribution data set based on RDD in Spark, and converting the urban road network data into a second elastic distribution data set based on RDD in Spark;
determining a target field according to the first elastic distribution data set, wherein the target field comprises the identity information, the operation state, the time, the longitude and the latitude of the vehicle;
determining road network node information according to the second elastic distribution data set;
constructing a weighted undirected graph based on the longitude and latitude contained in the target field and the road network node information;
determining a target adjacency matrix according to the weighted undirected graph;
constructing a parallel BiA-ACO algorithm according to the target adjacency matrix;
and executing the BiA star-ACO algorithm based on the RDD to generate a passenger carrying route recommendation result.
Optionally, the constructing a parallel BiA × ACO algorithm according to the target adjacency matrix includes:
optimizing a heuristic function of an ACO algorithm by a cost estimation function of BiA-algorithm with the target adjacency matrix as a weight;
and optimizing the pheromone updating rule by the fastest path length obtained by each circulation of the ACO algorithm to obtain BiA-ACO algorithm.
Optionally, after determining the road network node information according to the second elastic distribution data set, the recommendation method further includes:
respectively carrying out data fragmentation and filtering processing on the target field and the road network node information;
extracting the vehicle identification, the operation state, the time, the longitude and latitude of each field from the target fields subjected to the data fragmentation and the filtering processing, and sequencing each field according to the serial number of the vehicle identification;
determining data with the same serial number and continuous operation states of 1, 0 and 0, storing the identity, operation state, time, longitude and latitude of the latest vehicle with the operation state of 0, and sequencing according to time; or, determining the data with the same serial number and continuous operation states of 0, 1 and 1, storing the latest vehicle identity, operation state, time, longitude and latitude with the operation state of 1, and sequencing according to the time.
Optionally, the target field includes an empty location field, and the determining the target field according to the first elastic distribution data set specifically includes:
and determining the empty vehicle position field according to the data of the operation state of the vehicle changed from 1 to 0 in the first elastic distribution data set, and storing the movement track data of which the operation state is 0, wherein 0 represents an empty vehicle, and 1 represents a passenger.
Optionally, the target field includes a passenger location field, and determining the target field according to the first elastic distribution data set specifically includes:
and determining the passenger position field according to the data of the operation state of the vehicle changed from 0 to 1 in the first elastic distribution data set, and storing the movement track data of which the operation state is 1, wherein 0 represents an empty vehicle, and 1 represents a passenger.
Optionally, the determining road network node information according to the second elastic distribution data set includes:
and determining road network node information according to the intersection data of the urban road network region in the second elastic distribution data set.
The present application provides in a second aspect a passenger carrying route recommendation device based on movement trajectory big data, including:
the data acquisition unit is used for acquiring the moving track data of the vehicle and the urban road network data in the HDFS file;
the data conversion unit is used for converting the movement track data into a first elastic distribution data set based on RDD in Spark and converting the urban road network data into a second elastic distribution data set based on RDD in Spark;
a first determining unit, configured to determine a target field according to the first elastic distribution data set, where the target field includes identification information, an operation state, time, and latitude and longitude of the vehicle;
a second determining unit, configured to determine road network node information according to the second elastic distribution data set;
the data construction unit is used for constructing a weighted undirected graph based on the longitude and latitude contained in the target field and the road network node information;
a third determining unit, configured to determine a target adjacency matrix according to the weighted undirected graph;
an algorithm building unit, configured to build a parallel BiA-ACO algorithm according to the target adjacency matrix;
and the path recommendation unit is used for executing the BiA-ACO algorithm based on the RDD to generate a passenger carrying route recommendation result.
Optionally, the algorithm establishing unit includes:
a first optimization module for optimizing a heuristic function of an ACO algorithm by a cost estimation function of BiA-algorithm with the target adjacency matrix as a weight;
and the second optimization module is used for optimizing the pheromone updating rule for the fastest path length obtained by each circulation of the ACO algorithm to obtain BiA-ACO algorithm.
Optionally, the recommendation device further includes:
the data cleaning unit is used for respectively carrying out data fragmentation and filtering processing on the target field and the road network node information;
the data first sequencing unit is used for extracting the vehicle identity, the operation state, the time, the longitude and latitude of each field from the target fields subjected to the data fragmentation and the filtering processing so as to sequence each field according to the serial number of the vehicle identity;
the second data sorting unit is used for determining data with the same serial number and continuous operation states of 1, 0 and 0, storing the identity, the operation state, the time, the longitude and latitude of the vehicle with the latest operation state of 0 and sorting according to the time;
or the like, or, alternatively,
and the data are used for determining the data with the same serial number and continuous operation states of 0, 1 and 1, storing the latest vehicle identity, operation state, time, longitude and latitude with the operation state of 1, and sequencing according to the time.
Optionally, the target field of the first determining unit includes an empty location field, and the first determining unit specifically includes:
an empty location field determining module, configured to determine the empty location field according to data in the first elastic distribution data set, where an operation state of the vehicle changes from 1 to 0;
and the empty vehicle position data storage module is used for storing the movement track data with the operation state of 0, wherein 0 represents an empty vehicle, and 1 represents a passenger.
Optionally, the target field of the first determining unit includes a passenger position field, and the first determining unit specifically includes:
a passenger location field determination module for determining the passenger location field according to data in the first elastic distribution data set that the operating status of the vehicle changes from 0 to 1;
and the passenger position data storage module is used for storing the movement track data with the operation state of 1, wherein 0 represents empty vehicles, and 1 represents passenger carrying.
Optionally, the second determining unit is specifically configured to determine road network node information according to intersection data of the urban road network region in the second elastic distribution data set.
From a third aspect, the present application provides a passenger carrying route recommendation system based on movement trajectory big data, comprising:
the device comprises a processor, a memory, an input and output unit and a bus;
the processor is connected with the memory, the input and output unit and the bus;
the memory holds a program that the processor calls to perform the method of any of the method steps provided by the first aspect.
According to the technical scheme, the embodiment of the application has the following advantages:
according to the method, moving track data and urban road network data of a vehicle are obtained from an HDFS file, then the moving track data and the urban road network data are converted into elastic distribution data sets corresponding to Spark based on RDD, a target field is determined from the elastic distribution data sets converted from the moving track data, road network node information is determined from the elastic distribution data sets converted from the urban road network data, longitude and latitude contained in the target field are combined with road network nodes to generate a weighted undirected graph, so that a corresponding target adjacent matrix is obtained, and finally a passenger carrying route recommendation result is generated through an BiA-ACO algorithm constructed by the target adjacent matrix. The method and the device for processing the HDFS acquire the data from the HDFS file, so that the data processing speed can be improved; the moving track data of the vehicle and the urban road network data are combined to generate a target adjacency matrix of the weighted undirected graph, a corresponding BiA-ACO algorithm can be constructed according to the target adjacency matrix to generate a passenger carrying route recommendation result, compared with the original serial algorithm, the constructed BiA-ACO algorithm has fewer parameters used in the calculation process, and the route recommendation accuracy can be improved while the data transmission timeliness is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
Fig. 1 is a schematic flow chart of an embodiment of a passenger carrying route recommendation method based on big data of a movement track in the embodiment of the present application;
fig. 2 is a schematic flow chart of a passenger carrying route recommendation method based on big data of a movement track according to another embodiment of the present application;
fig. 3 is a schematic structural diagram of an embodiment of a passenger carrying route recommending device based on big data of a moving track in the embodiment of the application;
fig. 4 is a schematic structural diagram of another embodiment of a passenger carrying route recommending device based on big data of a moving track in the embodiment of the present application;
fig. 5 is a schematic structural diagram of an embodiment of a passenger carrying route recommendation system based on movement track big data in the embodiment of the present application;
FIG. 6 is a framework diagram of a parallel implementation of passenger carrying route recommendation in an embodiment of the present application;
FIG. 7 is a schematic diagram of an undirected graph with authority in an embodiment of the present application;
FIG. 8 is a schematic diagram of a road network according to an embodiment of the present application;
fig. 9 is a flow chart of BiA × ACO algorithm in the embodiment of the present application.
Detailed Description
In order to make those skilled in the art better understand the technical solution of the present invention, the technical solution in the embodiment of the present invention will be clearly and completely described below with reference to the drawings in the embodiment of the present invention, and it is obvious that the described embodiment is only a part of the embodiment of the present invention, and not all embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, shall fall within the scope of the present invention.
The embodiment of the application discloses a passenger carrying route recommending method, device and system based on moving track big data, and aims to improve timeliness of data transmission and accuracy of route recommendation.
It should be noted that the passenger carrying route recommendation method based on the big data of the moving track provided by the application can be applied to a terminal and also can be applied to a server, for example, the terminal can be a fixed terminal such as a smart phone or a computer, a tablet computer, a smart television, a smart watch, a portable computer terminal, and a desktop computer. For convenience of explanation, the present application is illustrated with a terminal as an execution subject.
Referring to fig. 1 and fig. 6, in a first aspect, an embodiment of the present application provides a passenger carrying route recommendation method based on movement trajectory big data, including:
101. the method comprises the steps that a terminal obtains moving track data and urban road network data of vehicles in an HDFS file;
the HDFS is a Hadoop distributed file system and manages files deployed on a plurality of independent physical machines, and has the characteristics of high fault tolerance, high throughput and large file storage besides the same characteristics of other distributed file systems. An HDFS cluster is mainly composed of one NameNode and several dataodes and cilents: the NameNode manages metadata of a file system, the Datanode stores actual data, the Cilent supports a service to access the HDFS, and data are obtained from the NameNode and the Datanode and returned to the service. HDFS is extremely configurable, while its default configuration can satisfy numerous installation environments. In most cases, these parameters need only be adjusted in large scale clustering environments. In addition, the HDFS has high efficiency, namely the Hadoop can transfer data among the nodes, the whole cluster resource can be transferred, the dynamic balance of each node is guaranteed, and the processing speed is high.
Therefore, in order to make the data have high configurability and make the terminal increase the data processing speed to some extent, the terminal may acquire the movement track data of the vehicle and the urban road network data from the HDFS file, so as to process the required vehicle movement track data and urban road network data in the following.
102. The terminal converts the movement track data into a first elastic distribution data set based on RDD in Spark, and converts the urban road network data into a second elastic distribution data set based on RDD in Spark;
RDDs, collectively referred to as resource Distributed data, are fault-tolerant, parallel data structures that allow users to explicitly store data to disk and memory and control the partitioning of data. When accessing the RDD, the pointer will only point to the part relevant to the operation. For example, there is a column-oriented data structure, where one is implemented as an array of Int and the other is implemented as an array of Float. If only the Int field is accessed, the pointer of the RDD may only access the Int array without scanning the entire data structure. In the internal implementation mechanism of RDD, the bottom layer interface is based on an iterator, so that data access becomes more efficient, and I/O operation of intermediate results is avoided, and the speed and the performance of data processing are improved.
Spark is a parallel distributed computing framework which can be used for solving big data analysis and mining, and is a parallel programming model which is based on memory computing and adopts a coarse-grained RDD mechanism.
Apache Hadoop is a reliable and extensible open source distributed computing architecture that can provide a stable and reliable interface for applications in a cluster consisting of a large amount of inexpensive hardware. The method makes full use of the computing and storing capability of the cluster, constructs a scalable and extensible large-data batch processing architecture with high reliability and strong fault tolerance, and realizes distributed storage and parallel computing of large-scale data. Thus, Spark can load data from any storage source supported by Hadoop to create RDDs, including file systems such as local file systems and HDFS. In the embodiment of the application, in order to realize large-scale data parallel computation and further improve the speed and performance of data processing, the terminal needs to convert the movement trajectory data and the urban road network data into an elastic distribution data set based on RDD in Spark.
103. The terminal determines a target field according to the first elastic distribution data set, wherein the target field comprises the identity information, the operation state, the time and the longitude and latitude of the vehicle;
in the embodiment of the application, the terminal needs to construct the weighted undirected graph according to the state information of the vehicle and the related road network data, so that the terminal can adopt the adjacent matrix generated by the weighted undirected graph to perform parallel computation on the path. Therefore, the terminal determines a target field from the first elastic distribution data set converted from the movement trace data, so as to obtain the required vehicle state information from the target field, for example, obtaining longitude and latitude information of a vacant position on the vehicle or longitude and latitude information of a position where a passenger sits on the vehicle, and the obtained specific vehicle state information is not limited herein.
104. The terminal determines road network node information according to the second elastic distribution data set;
in the embodiment of the application, the terminal needs to construct the weighted undirected graph according to the state information of the vehicle and the related road network node data, so that the terminal can adopt the adjacent matrix generated by the weighted undirected graph to perform parallel computation on the path. Therefore, after acquiring the required vehicle state information from the target field, the terminal needs to determine data of each intersection in the road network region from the second elastic distribution data set converted by the urban road network data, and use each intersection data as one road network node data, so as to integrate all the road network node data into the required road network node information.
105. The terminal establishes a weighted undirected graph based on the longitude and latitude contained in the target field and the road network node information;
in the weighted undirected graph, the graph is a data structure composed of a vertex set V and a relationship set E (a set of edges) between vertices, and is represented by a bigram G ═ V, E, and the weight can be represented by a node and a distance between nodes. For example, the vertex set V ═ is (V1, V2, V3, V4), and the edge set E ═ is (E12, E13, E14, E21, E23, E24, E31, E32, E34, E41, E42, E43), and the data associated with the edges of the graph are collectively referred to as weights; the weights can be expressed in terms of one node and the distance between nodes, and the graph with the weights is called a net. An undirected graph with weights (as shown in fig. 7), where the numbers represent the weights between two nodes.
In the embodiment of the application, the specific representation mode of constructing the weighted undirected graph based on the longitude and latitude contained in the target field and the road network node information is as follows: firstly, a road network graph is generated according to road network data, after a terminal determines a target field, longitude and latitude information of a passenger position/longitude and latitude information of an empty vehicle position in the target field are extracted as horizontal and vertical coordinates, so that coordinate information of the passenger position/empty vehicle position is obtained, and then the passenger position and the empty vehicle position in the road network are used as a road node, as shown in fig. 8. In fig. 8, the dots are intersections, and the passenger positions and the empty positions are added to the node set of the weighted undirected graph and are regarded as one node.
106. The terminal determines a target adjacency matrix according to the weighted undirected graph;
common storage methods for weighted undirected graphs include adjacency list representation and adjacency matrix representation, the adjacency list is suitable for storage of sparse matrix, but the disadvantage is that the operations of inserting operation or updating the weighted undirected graph are complex in practice, and the adjacency matrix is simpler than the adjacency list operation and more suitable for storage of dense matrix. Thus, the target adjacency matrix to which the weighted undirected graph relates can be determined using forms including, but not limited to, C-language code.
107. The terminal constructs a parallel BiA-ACO algorithm according to the target adjacency matrix;
in the embodiment of the present application, the parallel BiA × ACO algorithm constructed by the target adjacency matrix may be shown in formula (1) to formula (5).
Wherein the content of the first and second substances,
probability, η, for selecting the next nodeie(t) a heuristic function between the current node i and the end point e, replacing the original heuristic function with a cost estimation function of the A-algorithm, dijThe spherical distance between the current node i and the next node j is obtained; allk(k is 1,2, …, n) is the set of ant k to access the nodes of the road network, tauij(t) is the pheromone concentration transferred from road network node i to road network node j; alpha is the importance degree of the pheromone, and the larger the value of the alpha is, the larger the proportion of the concentration of the pheromone in probability transition is; beta is the importance degree of the heuristic function, and the larger the value of beta is, the larger the occupation ratio of the heuristic function in probability transition is.
Wherein rho is pheromone volatile molecules,
represents the fastest path distance of the kth ant in the current cycle as the updating rule of the pheromone, and delta tauijRepresenting the sum of the concentrations of pheromones released by all ants on a connection path from the current node i to the next node j, wherein Q is a constant and represents the total amount of the pheromones released by the ants in one cycle; dbestThe fastest path length obtained for the kth ant in this cycle.
108. And the terminal executes BiA-ACO algorithm based on the RDD to generate the passenger carrying route recommendation result.
When the same starting point is fixed, the terminal end point node data is input into a pre-configured BiA-ACO algorithm model to obtain the recommendation result of the passenger carrying path.
In the embodiment of the application, the moving track data and the urban road network data of the vehicle are obtained from the HDFS file, the data processing speed can be increased, then the moving track data and the urban road network data are combined to generate a target adjacent matrix of the weighted undirected graph, a corresponding BiA-ACO algorithm is constructed according to the target adjacent matrix, a passenger carrying route recommendation result is generated by executing a BiA-ACO algorithm based on RDD, and compared with an original serial algorithm, the BiA-ACO algorithm constructed has fewer parameters used in the calculation process, so that the time consumption of data transmission can be reduced, and the accuracy of the route recommendation can also be improved.
Referring to fig. 2, in a first aspect, an embodiment of the present application provides another passenger carrying route recommendation method based on big data of a moving trajectory, including:
201. the method comprises the steps that a terminal obtains moving track data and urban road network data of vehicles in an HDFS file;
202. the terminal converts the movement track data into a first elastic distribution data set based on RDD in Spark, and converts the urban road network data into a second elastic distribution data set based on RDD in Spark;
203. The terminal determines an empty vehicle position field according to data of the first elastic distribution data set, wherein the operation state of the vehicle is changed from 1 to 0, and stores moving track data with the operation state of 0, wherein 0 represents an empty vehicle, and 1 represents a passenger;
204. the terminal determines a passenger position field according to data of changing the operation state of the vehicle from 0 to 1 in the first elastic distribution data set, and stores the movement track data with the operation state of 1, wherein 0 represents empty vehicle and 1 represents passenger carrying;
specifically, after the terminal acquires the moving track data of a-B, sorting of each field is performed according to vehicle identification serial numbers such as vehicle ID1 and vehicle ID2 in the data, and then the operating state of the moving track data of vehicle ID1 is further analyzed.
For example, if the track of the vehicle ID1 at the point A-B is known, if the point A-A1 is empty, the point A1-A2 is passenger, the point A2-A3 is passenger, and the point A3-B is empty, the passenger carrying track data corresponding to the point A2-A3 or the moving track data of the point A-B is stored; if the vehicle ID1 is in the track of the points A-B, the points A-A1 are passenger carrying, the points A1-A2 are empty, the points A2-A3 are empty, and the points A3-B are passenger carrying, the empty track data corresponding to the points A2-A3 are stored.
205. The terminal determines road network node information according to intersection data of the urban road network region in the second elastic distribution data set;
206. the terminal carries out data fragmentation and filtering processing on the target field and the road network node information respectively;
207. the terminal extracts the vehicle identity, the operation state, the time, the longitude and latitude of each field from the target fields subjected to data fragmentation and filtering processing, and sorts each field according to the serial number of the vehicle identity;
208. the terminal determines data with the same serial number and continuous operation states of 1, 0 and 0, stores the latest vehicle identity, operation state, time and longitude and latitude with the operation state of 0 and sorts the data according to time, or determines data with the same serial number and continuous operation states of 0, 1 and 1, stores the latest vehicle identity, operation state, time and longitude and latitude with the operation state of 1 and sorts the data according to time;
when the GPS device fails, a taxi driver has wrong operations or signal delay, and the like, taxi GPS information may be wrong, for example: when a taxi passes through a tunnel, signals are weak, so that the condition that the message sending of the taxi is delayed, the longitude and latitude of the taxi are deviated and the like is caused, some drivers intentionally set the GPS operation state as a passenger carrying state in order to avoid disturbance during rest, but the taxi is actually in an idle load state. Therefore, in order to improve the accuracy and reliability of the model, data preprocessing is required to eliminate invalid and erroneous data.
For example, after the terminal stores passenger carrying track data corresponding to a2-A3, or moving track data of a-B, or stores empty vehicle track data corresponding to a2-A3, the track data corresponding to a2-A3 needs to be further filtered according to a selected target longitude range (39.8283918700-39.9909153300) and a selected target latitude range (116.2611551300-116.4954361600), track data not belonging to the target longitude range and the target latitude range is filtered, the filtered data is sorted according to time, and then road network node data in the range is combined to perform subsequent processing of constructing a weighted undirected graph, so that robustness and accuracy of passenger carrying route recommendation are improved.
209. The terminal establishes a weighted undirected graph based on the longitude and latitude contained in the target field and the road network node information;
210. the terminal determines a target adjacency matrix according to the weighted undirected graph;
211. The terminal optimizes a heuristic function of an ACO algorithm through a cost estimation function of BiA-star algorithm with the target adjacent matrix as the weight;
212. the terminal optimizes the pheromone updating rule with the fastest path length obtained by each circulation of the ACO algorithm to obtain BiA-ACO algorithm;
the ant colony optimization Algorithm (ACO) is a probabilistic algorithm for finding optimized paths. The algorithm has the characteristics of distribution calculation, information positive feedback and heuristic search, is a heuristic global optimization algorithm in evolutionary algorithms essentially, is easily influenced by a positive feedback mechanism, and has the defects of low convergence speed, difficulty in jumping out of local optimum after falling into local optimum and the like, so that the heuristic function of the ant colony algorithm is optimized by utilizing the BiA algorithm cost estimation function, and the global search capability of the algorithm is improved.
The expression of the specific verification is shown in fig. 9.
For example, the moving track data of the vehicle and the urban road network data are converted into an RDD elastic distribution data set in Spark, and the algorithm parameters are determined through a large number of experiments, as shown in table 1.
TABLE 1 Algorithm parameter set Table
When the data set is 14 road network nodes, BiA the experimental results of the ant colony optimization algorithm and the traditional ant colony optimization algorithm are shown in table 2.
Table 2 road network node result comparison table
It is known from table 2 that the ant colony optimization algorithm optimized by BiA is significantly higher than the conventional ant colony algorithm in efficiency under the same parameters, and since there are fewer data sets, at the same starting point, BiA is consistent with the fastest path recommended by the conventional ant colony algorithm, but the efficiency of the algorithm proposed in this application is improved by 54.57%, 47.05% and 61.57% respectively compared with the conventional ant colony algorithm.
In order to further verify the effectiveness of the algorithm in the aspect of path recommendation, the enlarged data set is used for verifying the effectiveness of the optimized ant colony algorithm, and the enlarged data set and the result are shown in table 3.
336 road network node result comparison tables
As shown in table 3, when the starting points are 10 and 27 when the data set is increased to 36 nodes, the BiA-ACO algorithm is superior to the traditional ant colony algorithm in terms of efficiency and recommended paths; although BiA A-ACO algorithm and Dijkstra algorithm, Bellman-Ford algorithm recommend the fastest path and the path length to be the same, the efficiency is respectively improved by 49.81% and 67.88% compared with the two algorithms; the BiA-ACO algorithm recommends a decrease in the fastest path length of 102.73m and 73.27m, respectively, when compared to the a algorithm and the Acyclic algorithm. The experimental result shows that the BiA-ACO algorithm is feasible to be applied to passenger carrying route recommendation.
213. And the terminal executes BiA-ACO algorithm based on the RDD to generate the passenger carrying route recommendation result.
Step 213 in this embodiment is similar to step 108 in the previous embodiment, and is not repeated here.
In the embodiment of the application, while the time consumption of data transmission can be reduced and the accuracy of path recommendation can be improved, the terminal can further obtain the empty vehicle position field from the first elastic distribution data set as an object for constructing the weighted undirected graph, or obtain the passenger position field from the first elastic distribution data set as an object for constructing the weighted undirected graph, so that the terminal has diversity in selection of the constructed objects when the parallel BiA-ACO algorithm is constructed. In addition, the obtained BiA-ACO algorithm is combined with the real road network node undirected graph adjacency matrix to carry out path recommendation, the real-time performance and the expandability of passenger carrying path recommendation can be improved, and the technical problem that the passenger carrying path recommendation accuracy is low due to the fact that the existing passenger carrying path recommendation algorithm is low in global search capability, low in convergence speed and the like is solved.
Referring to fig. 3, in a second aspect, the present application provides a passenger carrying route recommending apparatus based on big data of a moving track, including:
a data obtaining unit 301, configured to obtain moving trajectory data of a vehicle and city road network data in an HDFS file;
a data conversion unit 302, configured to convert the movement trajectory data into a first elastic distribution data set based on RDD in Spark, and convert the city road network data into a second elastic distribution data set based on RDD in Spark;
a first determining unit 303, configured to determine a target field according to the first elastic distribution data set, where the target field includes identification information, an operation state, time, and latitude and longitude of the vehicle;
a second determining unit 304, configured to determine road network node information according to the second elastic distribution data set;
the data construction unit 305 is configured to construct a weighted undirected graph based on the longitude and latitude contained in the target field and the road network node information;
a third determining unit 306, configured to determine a target adjacency matrix according to the weighted undirected graph;
an algorithm building unit 307, configured to build a parallel BiA × ACO algorithm according to the target adjacency matrix;
and the path recommendation unit 308 is used for executing BiA-ACO algorithm based on the RDD to generate a passenger carrying route recommendation result.
In the embodiment of the present application, the data obtaining unit 301 obtains the moving track data of the vehicle and the urban road network data from the HDFS file, then, the data conversion unit 302 converts the movement track data and the city road network data into elastic distribution data sets corresponding to Spark based on RDD, the first determination unit 303 determines a target field from the elastic distribution data set converted from the movement track data, the second determination unit 304 determines road network node information from the elastic distribution data set converted from the city road network data, the longitude and latitude contained in the target field is combined with the road network node by the data construction unit 305 to generate a weighted undirected graph, so as to obtain a corresponding target adjacency matrix, after the BiA x-ACO algorithm built by the target adjacency matrix by the algorithm building unit 307, the path recommendation unit 308 may execute BiA-ACO algorithm based on the RDD to generate a passenger-carrying route recommendation. In the whole calculation process, the original data are obtained from the HDFS file, the data processing speed can be improved, the used parameters are less than those of an original serial algorithm, the time consumption of data transmission can be reduced, and meanwhile the accuracy of path recommendation is improved.
Referring to fig. 4, the present application provides, from a second aspect, another passenger carrying route recommending apparatus based on big data of a moving track, including:
a data obtaining unit 401, configured to obtain moving trajectory data of a vehicle and city road network data in an HDFS file;
a data conversion unit 402, configured to convert the movement trajectory data into a first elastic distribution data set based on RDD in Spark, and convert the city road network data into a second elastic distribution data set based on RDD in Spark;
a first determining unit 403, configured to determine a target field according to the first elastic distribution data set, where the target field includes identification information, an operation state, time, and latitude and longitude of the vehicle;
a second determining unit 404, configured to determine road network node information according to the second elastic distribution data set;
the data cleaning unit 405 is configured to perform data fragmentation and filtering processing on the target field and the road network node information respectively;
a first data sorting unit 406, configured to extract vehicle identifiers, operating statuses, time, and latitudes and longitudes of the fields from target fields subjected to data fragmentation and filtering processing, so as to sort the fields according to serial numbers of the vehicle identifiers;
the second data sorting unit 407 is configured to determine data with the same serial number and consecutive operation states of 1, 0, and 0, store the latest vehicle identifier with the operation state of 0, the operation state, the time, the longitude and latitude, and sort the data according to the time; or, the system is used for determining data with the same serial number and continuous operation states of 0, 1 and 1, storing the latest vehicle identity, operation state, time, longitude and latitude with the operation state of 1, and sequencing according to the time;
the data construction unit 408 is configured to construct a weighted undirected graph based on the longitude and latitude and road network node information included in the target field;
a third determining unit 409, configured to determine a target adjacency matrix according to the weighted undirected graph;
an algorithm building unit 410 for building a parallel BiA-ACO algorithm from the target adjacency matrix;
and the path recommendation unit 411 is used for executing BiA × ACO algorithm based on the RDD to generate a passenger carrying route recommendation result.
In this embodiment of the present application, the algorithm establishing unit 410 includes:
a first optimization module 4101 for optimizing a heuristic function of the ACO algorithm by a cost estimation function of BiA × algorithm with the target adjacency matrix as a weight;
a second optimization module 4102, configured to optimize the pheromone update rule for the fastest path length obtained by each loop of the ACO algorithm, so as to obtain BiA × ACO algorithm.
In this embodiment of the application, the target field of the first determining unit 403 includes an empty location field, and the first determining unit 403 specifically includes:
an empty location field determining module 4031, configured to determine an empty location field according to data in the first elastic distribution data set, where the operation state of the vehicle changes from 1 to 0;
and an empty vehicle position data storage module 4032, configured to store movement trajectory data in an operation state of 0, where 0 denotes an empty vehicle and 1 denotes a passenger carrier.
Optionally, the target field of the first determining unit 403 may further include a passenger location field, and the first determining unit 406 specifically includes:
a passenger location field determining module 4033 for determining a passenger location field from data in the first elasticity distribution data set indicating that the operating status of the vehicle has changed from 0 to 1;
and a passenger position data storage module 4034, configured to store movement trajectory data in an operation state of 1, where 0 denotes an empty car and 1 denotes a passenger.
Optionally, the second determining unit 404 is specifically configured to determine road network node information according to intersection data of the urban road network region in the second elastic distribution data set.
Referring to fig. 5, the present application provides a passenger carrying route recommendation system based on big data of moving trajectory from a third aspect, including:
a processor 501, a memory 502, an input-output unit 503, and a bus 504;
the processor 501 is connected with the memory 502, the input/output unit 503 and the bus 504;
the memory 502 holds a program that the processor 501 calls to perform a secure launch method of an application as described in any of the first aspects.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus, and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical functional division, and there may be other divisions when actually implementing, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not implemented. Furthermore, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some interfaces, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a hardware form, and can also be realized in a software functional unit form.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, etc. that can store program codes.
Claims (10)
1. The passenger carrying route recommendation method based on the big data of the moving track is characterized by comprising the following steps:
obtaining moving track data and urban road network data of vehicles in an HDFS file;
converting the movement track data into a first elastic distribution data set based on RDD in Spark, and converting the urban road network data into a second elastic distribution data set based on RDD in Spark;
determining a target field according to the first elastic distribution data set, wherein the target field comprises the identity information, the operation state, the time, the longitude and the latitude of the vehicle;
determining road network node information according to the second elastic distribution data set;
constructing a weighted undirected graph based on the longitude and latitude contained in the target field and the road network node information;
determining a target adjacency matrix according to the weighted undirected graph;
constructing a parallel BiA-ACO algorithm according to the target adjacency matrix;
and executing the BiA star-ACO algorithm based on the RDD to generate a passenger carrying route recommendation result.
2. The passenger carrying route recommendation method according to claim 1, wherein said constructing a parallel BiA-ACO algorithm according to said target adjacency matrix comprises:
optimizing a heuristic function of an ACO algorithm by a cost estimation function of BiA-algorithm with the target adjacency matrix as a weight;
and optimizing the pheromone updating rule by the fastest path length obtained by each circulation of the ACO algorithm to obtain BiA-ACO algorithm.
3. The passenger carrying route recommendation method according to claim 2, wherein after determining road network node information according to the second elastic distribution data set, the recommendation method further comprises:
respectively carrying out data fragmentation and filtering processing on the target field and the road network node information;
extracting the vehicle identification, the operation state, the time, the longitude and latitude of each field from the target fields subjected to the data fragmentation and the filtering processing, and sequencing each field according to the serial number of the vehicle identification;
determining data with the same serial number and continuous operation states of 1, 0 and 0, storing the identity, operation state, time, longitude and latitude of the latest vehicle with the operation state of 0, and sequencing according to time;
or the like, or, alternatively,
and determining data with the same serial number and continuous operation states of 0, 1 and 1, storing the identity, the operation state, the time, the longitude and latitude of the vehicle with the latest operation state of 1, and sequencing according to the time.
4. A passenger carrying route recommendation method according to claim 3, wherein said target field comprises an empty car position field, and said determining a target field according to said first elastic distribution data set specifically comprises:
and determining the empty vehicle position field according to the data of the operation state of the vehicle changed from 1 to 0 in the first elastic distribution data set, and storing the movement track data of which the operation state is 0, wherein 0 represents an empty vehicle, and 1 represents a passenger.
5. A passenger carrying route recommendation method according to claim 3, wherein said target field comprises a passenger location field, said determining a target field according to said first elastic distribution data set comprising:
and determining the passenger position field according to the data of the operation state of the vehicle changed from 0 to 1 in the first elastic distribution data set, and storing the movement track data of which the operation state is 1, wherein 0 represents an empty vehicle, and 1 represents a passenger.
6. The passenger carrying route recommendation method according to any one of claims 4 to 5, wherein determining road network node information according to the second elastic distribution data set comprises:
and determining road network node information according to the intersection data of the urban road network region in the second elastic distribution data set.
7. Passenger carrying route recommendation device based on big data of movement track, characterized by including:
the data acquisition unit is used for acquiring the moving track data of the vehicle and the urban road network data in the HDFS file;
the data conversion unit is used for converting the movement track data into a first elastic distribution data set based on RDD in Spark and converting the urban road network data into a second elastic distribution data set based on RDD in Spark;
a first determining unit, configured to determine a target field according to the first elastic distribution data set, where the target field includes identification information, an operation state, time, and latitude and longitude of the vehicle;
a second determining unit, configured to determine road network node information according to the second elastic distribution data set;
the data construction unit is used for constructing a weighted undirected graph based on the longitude and latitude contained in the target field and the road network node information;
a third determining unit, configured to determine a target adjacency matrix according to the weighted undirected graph;
an algorithm building unit, configured to build a parallel BiA-ACO algorithm according to the target adjacency matrix;
and the path recommendation unit is used for executing the BiA-ACO algorithm based on the RDD to generate a passenger carrying route recommendation result.
8. The passenger carrying route recommending device based on big data of moving track according to claim 7, wherein said algorithm establishing unit comprises:
a first optimization module for optimizing a heuristic function of an ACO algorithm by a cost estimation function of BiA-algorithm with the target adjacency matrix as a weight;
and the second optimization module is used for optimizing the pheromone updating rule for the fastest path length obtained by each circulation of the ACO algorithm to obtain BiA-ACO algorithm.
9. The passenger carrying route recommending device based on big data of moving track according to claim 8, wherein said recommending system further comprises:
the data cleaning unit is used for respectively carrying out data fragmentation and filtering processing on the target field and the road network node information;
the data first sequencing unit is used for extracting the vehicle identity, the operation state, the time, the longitude and latitude of each field from the target fields subjected to the data fragmentation and the filtering processing so as to sequence each field according to the serial number of the vehicle identity;
the second data sorting unit is used for determining data with the same serial number and continuous operation states of 1, 0 and 0, storing the identity, the operation state, the time, the longitude and latitude of the vehicle with the latest operation state of 0 and sorting according to the time; or, the data is used for determining the data with the same serial number and continuous operation states of 0, 1 and 1, storing the latest vehicle identity, operation state, time, longitude and latitude with the operation state of 1, and sequencing according to the time.
10. Passenger carrying route recommendation system based on big data of movement track is characterized by comprising:
the device comprises a processor, a memory, an input and output unit and a bus;
the processor is connected with the memory, the input and output unit and the bus;
the memory holds a program that the processor calls to perform the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111190100.1A CN114061604A (en) | 2021-10-12 | 2021-10-12 | Passenger carrying route recommendation method, device and system based on movement track big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111190100.1A CN114061604A (en) | 2021-10-12 | 2021-10-12 | Passenger carrying route recommendation method, device and system based on movement track big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114061604A true CN114061604A (en) | 2022-02-18 |
Family
ID=80234499
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111190100.1A Pending CN114061604A (en) | 2021-10-12 | 2021-10-12 | Passenger carrying route recommendation method, device and system based on movement track big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114061604A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115049105A (en) * | 2022-05-16 | 2022-09-13 | 贵州民族大学 | Taxi track big data driven passenger carrying route recommendation method, device and medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110111575A (en) * | 2019-05-16 | 2019-08-09 | 北京航空航天大学 | A kind of Forecast of Urban Traffic Flow network analysis method based on Complex Networks Theory |
| CN112069229A (en) * | 2020-08-27 | 2020-12-11 | 贵州民族大学 | Optimal waiting point recommendation method and system for big data of moving track |
| CN112070529A (en) * | 2020-08-24 | 2020-12-11 | 贵州民族大学 | Passenger carrying hotspot parallel prediction method, system, terminal and computer storage medium |
| US20210094182A1 (en) * | 2019-09-26 | 2021-04-01 | Tata Consultancy Services Limited | Method and system for real-time path planning |
| US20210241625A1 (en) * | 2020-01-31 | 2021-08-05 | Here Global B.V. | Method and apparatus for providing large scale vehicle routing |
-
2021
- 2021-10-12 CN CN202111190100.1A patent/CN114061604A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110111575A (en) * | 2019-05-16 | 2019-08-09 | 北京航空航天大学 | A kind of Forecast of Urban Traffic Flow network analysis method based on Complex Networks Theory |
| US20210094182A1 (en) * | 2019-09-26 | 2021-04-01 | Tata Consultancy Services Limited | Method and system for real-time path planning |
| US20210241625A1 (en) * | 2020-01-31 | 2021-08-05 | Here Global B.V. | Method and apparatus for providing large scale vehicle routing |
| CN112070529A (en) * | 2020-08-24 | 2020-12-11 | 贵州民族大学 | Passenger carrying hotspot parallel prediction method, system, terminal and computer storage medium |
| CN112069229A (en) * | 2020-08-27 | 2020-12-11 | 贵州民族大学 | Optimal waiting point recommendation method and system for big data of moving track |
Non-Patent Citations (1)
| Title |
|---|
| 郑永玲，白宇，杨楠，蒋顺英, 现代信息科技, vol. 4, no. 22, pages 74 - 80 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115049105A (en) * | 2022-05-16 | 2022-09-13 | 贵州民族大学 | Taxi track big data driven passenger carrying route recommendation method, device and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10540611B2 (en) | Scalable complex event processing with probabilistic machine learning models to predict subsequent geolocations | |
| Tseng et al. | Congestion prediction with big data for real-time highway traffic | |
| Rong et al. | Du-parking: Spatio-temporal big data tells you realtime parking availability | |
| Huang et al. | An efficient passenger-hunting recommendation framework with multitask deep learning | |
| CN110520913B (en) | System and method for determining estimated time of arrival | |
| CN112766607B (en) | Travel route recommendation method and device, electronic device and readable storage medium | |
| US10119826B2 (en) | System and method for accelerating route search | |
| US20180240026A1 (en) | Method and apparatus for providing semantic-free traffic prediction | |
| CN101493329B (en) | Multiple target point path planning method and device | |
| CN110537212B (en) | System and method for determining estimated arrival time | |
| EP3410348A1 (en) | Method and apparatus for building a parking occupancy model | |
| Jiang et al. | Deep ROI-based modeling for urban human mobility prediction | |
| CN110442662B (en) | Method for determining user attribute information and information push method | |
| US10809080B2 (en) | System and method for determining routing by learned selective optimization | |
| CN102298608A (en) | Information processing apparatus, information processing method and program | |
| WO2021082464A1 (en) | Method and device for predicting destination of vehicle | |
| CN110741225B (en) | System and method for determining target site | |
| CN113763700B (en) | Information processing method, information processing device, computer equipment and storage medium | |
| Shang et al. | Finding traffic-aware fastest paths in spatial networks | |
| CN102735239A (en) | Navigation device, method and system | |
| CN111047130B (en) | Method and system for traffic analysis and management | |
| CN104636457B (en) | A kind of method and device of location finding cognition | |
| CN112069229A (en) | Optimal waiting point recommendation method and system for big data of moving track | |
| CN114061604A (en) | Passenger carrying route recommendation method, device and system based on movement track big data | |
| Amirat et al. | Nextroute: a lossless model for accurate mobility prediction |
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 |