CN111192451B - Vehicle arrival time prediction method and device, computer equipment and storage medium - Google Patents
Vehicle arrival time prediction method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN111192451B CN111192451B CN201911369725.7A CN201911369725A CN111192451B CN 111192451 B CN111192451 B CN 111192451B CN 201911369725 A CN201911369725 A CN 201911369725A CN 111192451 B CN111192451 B CN 111192451B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- time
- destination
- arrival
- final
- 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
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
- G08G1/0145—Measuring and analyzing of parameters relative to traffic conditions for specific applications for active traffic flow control
Abstract
The application provides a prediction method and device of vehicle arrival time, computer equipment and a storage medium, and belongs to the technical field of traffic prediction. The method is used for accurately predicting all vehicles which possibly arrive at the destination and the arrival time of the vehicles arriving at the destination end. The method comprises the following steps: acquiring the running track data of each vehicle according to a GPS data packet sent by the vehicle; calculating the probability of the corresponding vehicle reaching the same preset destination; determining the vehicles with the calculated probability larger than a preset probability threshold value as alternative arrival vehicles; calculating a predicted arrival time of each candidate arriving vehicle; selecting a front preset vehicle with the maximum probability in a preset time period away from the current time from the candidate arriving vehicles as a final arriving vehicle, and acquiring the predicted arrival time of the final arriving vehicle; calculating the congestion time between the final arrival vehicle and the destination in real time; and calculating the final arrival time of the final arrival vehicle according to the predicted arrival time, the congestion time and the weight coefficient.
Description
Technical Field
The present invention relates to the field of traffic prediction technologies, and in particular, to a method and an apparatus for predicting vehicle arrival time, a computer device, and a storage medium.
Background
Based on the riding demand of a user, the time of the user reaching a destination needs to be estimated, and the time of the user reaching the destination is estimated in the current mainstream taxi taking software and map route searching tools in the market.
The method is only suitable for the user to estimate the arrival time of the current user, and cannot be applied in some special scenes.
For example, many container trucks travel to the same port from all sides, need unload in this port, then the port needs to carry out preliminary statistics to the container truck that arrives at the port to the arrival time of the container truck that arrives at the port is counted, in order to arrange discharge staff and loading equipment, avoids waiting time overlength to lead to the wasting of resources. In consideration of the situation that port congestion is caused by the queuing condition of container trucks discharging at port, the congestion condition is large in area, is different from the congestion condition of a single user and a single route in the traditional scene and is different from a data acquisition mode, and therefore the existing prediction method of arrival time cannot be directly applied to the scene.
There is a need to provide a method for a destination that can accurately predict all possible vehicles and arrival times at the destination.
Disclosure of Invention
The embodiment of the invention provides a method and a device for predicting vehicle arrival time, computer equipment and a storage medium, which are applied to a destination and can accurately predict all vehicles which are possible to arrive at the destination and the arrival time of the vehicles arriving at the destination.
According to one aspect of the present invention, there is provided a method for predicting vehicle arrival time, the method comprising:
receiving GPS data packets sent by a plurality of vehicles in real time, and analyzing vehicle identification and coordinate information in the GPS data packets;
generating a coordinate sequence corresponding to each vehicle identification according to the time sequence to obtain the running track data of the corresponding vehicle;
calculating the probability of the corresponding vehicle reaching the same preset destination through a probability distribution function and the traveling track data, wherein the probability distribution function is obtained by solving the stored historical vehicle track data and whether the vehicle reaches the destination;
determining the vehicles with the calculated probability larger than a preset probability threshold value as alternative arrival vehicles;
calculating the predicted arrival time of each alternative arrival vehicle according to the historical vehicle track data and the historical arrival time;
selecting a front preset vehicle with the maximum probability in a preset time period away from the current time from the candidate arriving vehicles as a final arriving vehicle, and acquiring the predicted arrival time of the final arriving vehicle;
calculating the congestion time between the final arrival vehicle and the destination in real time, and acquiring a weight coefficient of the congestion time;
and calculating the final arrival time of the final arrival vehicle according to the predicted arrival time, the congestion time and the weight coefficient.
According to another aspect of the present invention, there is provided a vehicle arrival time prediction apparatus comprising:
the data receiving module is used for receiving GPS data packets sent by a plurality of vehicles in real time and analyzing vehicle identifications and coordinate information in the GPS data packets;
the coordinate sequence generating module is used for generating a coordinate sequence corresponding to each vehicle identifier according to the time sequence to obtain the running track data of the corresponding vehicle;
the first calculation module is used for calculating the probability of the corresponding vehicle reaching the same preset destination through a probability distribution function and the traveling track data, wherein the probability distribution function is obtained by solving the stored historical vehicle track data and whether the vehicle reaches the destination;
the vehicle determining module is used for determining the vehicle with the calculated probability larger than a preset probability threshold value as an alternative arrival vehicle;
the second calculation module is used for calculating the predicted arrival time of each alternative arrival vehicle according to the historical vehicle track data and the historical arrival time;
the time acquisition module is used for selecting a front preset vehicle with the maximum probability in a preset time period away from the current time from the candidate arriving vehicles as a final arriving vehicle and acquiring the predicted arrival time of the final arriving vehicle;
the third calculation module is used for calculating the congestion time between the final arrival vehicle and the destination in real time and acquiring the weight coefficient of the congestion time;
and the time calculation module is used for calculating the final arrival time of the final arrival vehicle according to the predicted arrival time, the congestion time and the weight coefficient.
According to yet another aspect of the present invention, there is provided a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the above-mentioned method for predicting vehicle arrival time when executing the program.
According to still another aspect of the present invention, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps in the above-described method for predicting vehicle arrival time.
The invention provides a method, a device, a computer device and a storage medium for predicting vehicle arrival time, which are used for receiving GPS data packets sent by a plurality of vehicles in real time, analyzing vehicle identification and coordinate information in the GPS data packets to obtain the driving track data of the corresponding vehicle, then calculating the probability of the corresponding vehicle arriving at the same preset destination through a probability distribution function and the driving track data, determining the vehicles with the calculated probability being greater than a preset probability threshold value as alternative arriving vehicles, wherein the vehicles which can be accommodated in the same time period of the destination are limited, the alternative arriving vehicles determined according to the probability can not always arrive, and the number of the maximum vehicles which can be accommodated in the destination is also required to be considered, so the scheme also sets that the front preset vehicles with the maximum probability in the preset time period separated from the current time are selected from the alternative arriving vehicles as final arriving vehicles, and acquiring the predicted arrival time of the final arrival vehicle from the pre-calculated predicted arrival time of each candidate arrival vehicle, then calculating the congestion time between the final arrival vehicle and the destination in real time, acquiring the weight coefficient of the congestion time, calculating the final arrival time of the final arrival vehicle according to the predicted arrival time, the congestion time and the weight coefficient, and considering the accommodation situation of the destination, namely the real-time congestion situation between the vehicle and the destination according to the final arrival time of the final arrival vehicle and the final arrival vehicle calculated according to the method of the application, so that the method is applied to the destination and can accurately predict all vehicles which are possible to finally arrive at the destination and the arrival time at the destination.
Drawings
FIG. 1 is a schematic diagram of an application environment of a method for predicting vehicle arrival time according to an embodiment of the present invention;
FIG. 2 is a flow diagram of a method of predicting vehicle arrival time according to one embodiment of the present invention;
FIG. 3 is a flow chart of a method of predicting vehicle arrival time according to another embodiment of the present invention;
FIG. 4 is a flow chart of a method of predicting vehicle arrival time according to yet another embodiment of the present invention;
FIG. 5 is a schematic diagram of an applicable environment for a method for calculating congestion time according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of an applicable environment of a method for calculating congestion time according to another embodiment of the present invention;
fig. 7 is a block diagram illustrating an exemplary configuration of a vehicle arrival time prediction apparatus according to an embodiment of the present invention;
fig. 8 is a schematic diagram of the internal structure 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 some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The vehicle arrival time prediction method provided by the application can be applied to the application environment shown in fig. 1, wherein the computer device is communicated with the vehicle-mounted system of each vehicle through a network. Computer devices include, but are not limited to, various personal computers, servers, laptops, smartphones, tablets, and portable wearable devices, among others. The server may be implemented by an independent server or a server cluster composed of a plurality of servers. The computer device is used for receiving GPS (Global Positioning System) data packets sent by a plurality of vehicles, judging which vehicles are the vehicles arriving at the preset destination according to the GPS data packets and the prediction method of the arrival time of the vehicles, and predicting the arrival time of the vehicles arriving at the preset destination.
Fig. 2 is a flowchart of a vehicle arrival time prediction method according to an embodiment of the present invention, which includes the following steps S101 to S108, as shown in fig. 2.
S101, receiving GPS data packets sent by a plurality of vehicles in real time, and analyzing vehicle identification and coordinate information in the GPS data packets.
In one embodiment, the vehicle identifier is used to identify different vehicles, and the vehicle identifier may be a license plate number of the vehicle and may also be a unique identification code of an engine of the vehicle.
The vehicle is a container truck, and the type of the vehicle is stored in the GPS data packet. The data contents stored in different fields of the data in the GPS data packet and the historical vehicle track data packet are, for example:
| license plate number | Type of vehicle | Name of business user | Latitude and longitude | GPS velocity | Direction |
Further, the GPS data packet and the historical vehicle trajectory data packet further include license plate color information, and further, different colors may be referred to by numerical codes, for example:
| digital code | 1 | 2 | 3 | 4 | 9 |
| Colour(s) | Blue color | Yellow colour | Black color | White colour | Others |
And S102, generating a coordinate sequence corresponding to each vehicle identification according to the time sequence to obtain the running track data of the corresponding vehicle.
The driving track data of the corresponding vehicle can be represented by the following vectors:
Fk(t)＝{ak(t1)，ak(t2)，ak(t3)，……，ak(tn)}；
where k denotes a vehicle index in one-to-one correspondence with the vehicle identification, tnDenotes a time index, ak(tn) denotes the kth container truck at tnGPS coordinates of time of day.
S103, calculating the probability of the corresponding vehicle reaching the same preset destination through a probability distribution function and the running track data, wherein the probability distribution function is obtained by solving the stored historical vehicle track data and whether the vehicle reaches the destination.
In one embodiment, the destination includes a port, the probability distribution function may analyze historical vehicle trajectory data, and it is within the prior art of those skilled in the art to obtain the probability distribution function according to discrete coordinate points through an EM (Expectation-maximization algorithm) maximum Expectation algorithm and a gaussian mixture distribution model, and details of implementation thereof are not described herein.
In one embodiment, before the step of S103, the method further comprises:
and respectively carrying out data cleaning, data filtering and null value insertion processing on the running track data to obtain the preprocessed running track data.
In step S103, the probability of the corresponding vehicle reaching the preset same destination is further calculated according to the probability distribution function and the preprocessed traveling track data.
And S104, determining the vehicle with the calculated probability larger than a preset probability threshold value as a candidate arrival vehicle.
In one embodiment, the probability threshold is artificially set. The candidate arriving vehicle selected in the step is a vehicle which is predicted to arrive at the destination preliminarily, and the selection process does not consider the largest vehicle of the destination.
And S105, calculating the predicted arrival time of each candidate arrival vehicle according to the historical vehicle track data and the historical arrival time.
In one embodiment, the step S105 further includes:
acquiring a minimum preset number of historical arriving vehicles, the distance between which and the current position of the candidate arriving vehicle is less than a preset value, from the historical vehicle track data, and acquiring the arrival time of each historical arriving vehicle;
and calculating the average arrival time according to the arrival time of each historical arrival vehicle, and taking the average arrival time as the predicted arrival time of the alternative arrival vehicle.
The obtaining of the vehicle whose distance from the current position of the candidate arrival vehicle is smaller than the preset value from the historical vehicle trajectory data may be understood as: judging whether vehicles with a certain coordinate value and a coordinate value of the current position of the vehicle, which are less than a preset value, exist in the track data of all the arrival history vehicles arriving at the destination, if so, acquiring the arrival time of the history arrival vehicles, polling the step until the arrival time of each history arrival vehicle meeting the requirement is acquired, inquiring a minimum preset history arrival vehicle with a distance from the coordinate point of the current position of the vehicle to the preset value from all the acquired history arrival vehicles, calculating the average arrival time of the preset history arrival vehicles, and taking the average arrival time as the predicted arrival time of the candidate arrival vehicle.
S106, selecting a front preset vehicle with the maximum probability in a preset time period away from the current time from the candidate arriving vehicles as a final arriving vehicle, and obtaining the predicted arrival time of the final arriving vehicle.
In one embodiment, the time interval from the current time may be set by a predetermined time period, which may be 20 minutes, for example. The number of the front preset vehicles may be understood as the maximum number of vehicles that can be accommodated by the destination, and the number of the preset vehicles may be 100.
And S107, calculating the congestion time between the final arrival vehicle and the destination in real time, and acquiring a weight coefficient of the congestion time.
In one embodiment, the weight coefficient of the congestion time may be set manually or may be obtained by analyzing and calculating historical vehicle trajectory data.
The congestion time may be represented as a congestion situation in a circular area with the destination as an origin and a radius of a distance between the final arrival vehicle and the destination.
And S108, calculating the final arrival time of the final arrival vehicle according to the predicted arrival time, the congestion time and the weight coefficient.
In one embodiment, the relationship between the final arrival time T and the predicted arrival time, the congestion time and the weighting factor may be embodied by a weighted summation.
In the embodiment, GPS data packets sent by a plurality of vehicles are received in real time, vehicle identification and coordinate information in the GPS data packets are analyzed to obtain running track data of the corresponding vehicle, then the probability of the corresponding vehicle reaching the same preset destination is calculated through a probability distribution function and the running track data, the vehicle with the calculated probability being greater than a preset probability threshold is determined as an alternative arriving vehicle, because the vehicles which can be accommodated in the same time period of the destination are limited, the alternative arriving vehicles determined according to the probability cannot necessarily reach all the vehicles, and therefore the number of the maximum vehicles which can be accommodated in the destination is also required to be considered, the embodiment further sets that a front preset vehicle with the maximum probability in a preset time period which is separated from the current time is selected from the alternative arriving vehicles as a final arriving vehicle, and the predicted arriving time of the final arriving vehicle is obtained from the pre-calculated predicted arriving time of each alternative arriving vehicle, and then calculating the congestion time between the final arrival vehicle and the destination in real time, acquiring a weight coefficient of the congestion time, and calculating the final arrival time of the final arrival vehicle according to the predicted arrival time, the congestion time and the weight coefficient.
In one embodiment, the step of calculating the final arrival time of the final arrival vehicle according to the predicted arrival time, the congestion time and the weighting factor in step S108 includes:
the final arrival time of the final arrival vehicle is calculated by the following formula (1):
T＝b*Tavg+∑an*Yn/Xn (1)
wherein, Σ anA weight coefficient representing the congestion time, b being 1- Σ an，an＞0，b＞0，TavgIndicating the predicted arrival of the finally arriving vehicleUp to time, XnA mileage distance of n kilometers from the destination at the current time or an nth one kilometer from the destination, n is not more than k, k is a positive integer and represents a preset value or an actual distance between the final arriving vehicle and the destination, and Y isnRepresents XnThe total number of vehicles within the guided range distance.
In one embodiment, b and ∑ anThe vehicle track data processing method can be artificially preset, can also be obtained by analyzing and calculating historical vehicle track data, and can be obtained by solving the historical vehicle track data by a least square method and a maximum likelihood method.
Fig. 5 is a schematic diagram of an applicable environment of a congestion time calculation method according to an embodiment of the present invention, wherein D represents a predetermined same destination, if XnIndicating a mileage distance of n km from the destination at the present time, and when n is 3, as shown in fig. 5, Σ an*Yn/XnThe congestion status of the directions represents X in FIG. 51+X2+X3Congestion situation within a range, wherein X1＝1，Xn＝Xn-1+1。
Fig. 6 is a schematic diagram of an application environment of a congestion time calculation method according to another embodiment of the present invention, wherein D represents a predetermined same destination, if XnIndicates the nth kilometer from the destination, and when n is 3, as shown in fig. 6, Σ an*Yn/XnThe congestion status of the directions is represented by X in FIG. 61+X2+X3Congestion situation within a range, wherein Xn＝Xn-1＝1。
In other embodiments, the step of calculating the final arrival time of the final arrival vehicle according to the predicted arrival time, the congestion time and the weighting factor in step S108 includes:
the final arrival time of the final arrival vehicle is calculated by the following formula (2):
T＝b*Tavg+∑an*Yn/Xn+∑cm*Zm (2)
where b represents the weight coefficient of the predicted arrival time, Σ anA weight coefficient, Σ c, representing the congestion timem＝1-b-∑an，an＞0，b＞0，cm＞0，XnA mileage distance of n kilometers from the destination at the current time or an nth one kilometer from the destination, n is not more than k, k is a positive integer and represents a preset value or an actual distance between the final arriving vehicle and the destination, and Y isnRepresents XnTotal number of vehicles within the guided mileage distance, ZmA mileage distance of m kilometers between the final arrival vehicle and the destination is represented, m is a positive integer, and m is n when k represents an actual distance between the final arrival vehicle and the destination.
In one embodiment, b, ∑ anSum Σ cmThe vehicle track data processing method can be artificially preset, can also be obtained by analyzing and calculating historical vehicle track data, and can be obtained by solving the historical vehicle track data by a least square method and a maximum likelihood method.
Fig. 5 is a schematic diagram of an applicable environment of a congestion time calculation method according to an embodiment of the present invention, wherein D represents a predetermined same destination, if XnIndicating a mileage distance of n km from the destination at the present time, and when n is 3, as shown in fig. 5, Σ an*Yn/XnThe congestion status of the directions represents X in FIG. 51+X2+X3Congestion situation within the range, Σ cm*ZmDirecting the vehicle at different distances from the destination is affected by congestion, where X1＝1，Xn＝Xn-1+1。
Fig. 6 is a schematic diagram of an application environment of a congestion time calculation method according to another embodiment of the present invention, wherein D represents a predetermined same destination, if XnIndicates the nth kilometer from the destination, and when n is 3, as shown in fig. 6, Σ an*Yn/XnThe congestion status of the directions is represented by X in FIG. 61+X2+X3Congestion situation within the range, Σ cm*ZmDirecting the vehicle at different distances from the destination is affected by congestion, where Xn＝Xn-1＝1。
Fig. 3 is a flowchart of a vehicle arrival time prediction method according to another embodiment of the present invention, and as shown in fig. 3, the vehicle arrival time prediction method in the present embodiment further includes the following steps S301 on the basis of the steps S101, S102, S104 to S108:
and S301, carrying out Principal Component Analysis (PCA) (principal components analysis) dimensionality reduction processing on the travel track data to obtain dimensionality reduction track data.
In one embodiment, the step S301 further includes the following steps (1) to (7):
(1) the driving track data of a certain vehicle can be characterized by the following vectors:
Fk(t)＝{ak(t1)，ak(t2)，ak(t3)，…，ak(tn)}；
where k denotes a vehicle index in one-to-one correspondence with the vehicle identification, tnDenotes a time index, ak(tn) denotes the kth container truck at tnGPS coordinates of time of day.
(2) The driving track data of all vehicles can be represented by vectors as follows:
D＝(F1(t)，F2(t)，F3(t)，...，Fk(t))。
(3) centralizing all samples: f'k(t)＝Fk(t)-(1/K)∑Fk(t)。
(4) Calculating a covariance matrix DD of the sampleT。
(5) To matrix DDTAnd carrying out eigenvalue decomposition.
(6) And extracting the eigenvectors (w) corresponding to the largest N eigenvalues1，w2，...，wN) After all the eigenvectors are normalized, an eigenvector matrix W is formed.
(7) For each of the sample setsA sample Fk(t), conversion into a new sample Zk(t)＝WTFk(t)，ZkAnd (t) representing the obtained dimension reduction track data.
The step S103 is further a step S302 of:
s302, calculating the probability of the corresponding vehicle reaching the preset same destination through a probability distribution function and the dimension reduction track data, wherein the probability distribution function is obtained by solving the stored historical vehicle track data and whether the vehicle reaches the destination.
In the embodiment, by adding the data dimension reduction step, the calculation amount of data can be reduced, and the prediction speed of whether the vehicle reaches the destination and the time of reaching the destination can be improved.
Fig. 4 is a flowchart of a vehicle arrival time prediction method according to still another embodiment of the present invention, and as shown in fig. 4, the vehicle arrival time prediction method in this embodiment further includes the following step S401 on the basis of the steps S101, S102, S302 to S108 described above:
s401, respectively carrying out data cleaning, data filtering and null value inserting processing on the traveling track data to obtain the traveling track data after preprocessing.
The step S301 is further a step S402:
s402, carrying out principal component analysis and dimensionality reduction on the preprocessed running track data to obtain dimensionality reduction track data.
In one embodiment, the step of performing data cleansing on the travel track data comprises:
storing coordinate information in a GPS data packet of a vehicle which is accessed to the network into a database;
filtering all non-networked vehicles in the data set according to coordinate information in a GPS data packet of the networked vehicles;
extracting the running track data of each vehicle in a preset time period (for example, 8 to 12 points) from the filtered networked vehicles;
a plurality of continuous track points d (such as 120) of each vehicle are extracted from the driving track data, one track point can be taken every 2 minutes from 8 points to 12 points, and if no track data in an interval is filled with null values.
In one embodiment, the step of data filtering the driving trace data comprises:
extracting the characteristics of the plurality of track points d;
filtering and screening out vehicles with the hollow values of the track points exceeding half;
and (3) filtering dead spots: according to the provisions of 'intersection', if the highest speed per hour is 120km/h, the vehicle runs for 2 minutes for 4km at most, if the distance between the GPS coordinates of two points exceeds 4km, the vehicle is judged to be dead pixel, and after the dead pixel is filtered, if the null value exceeds half, the corresponding vehicle is filtered and screened.
In one embodiment, the step of performing the null value insertion process on the travel track data includes:
and if a certain track coordinate point is a null value, taking the average value of the adjacent previous nearest valued point and the adjacent next nearest valued point as the coordinate value of the null value. For the special point processing: if the first point is a null value, taking the value of the next nearest adjacent valued point as the coordinate value of the null value; and if the last point is a null value, taking the value of the adjacent previous nearest valued point as the coordinate value of the null value.
According to the embodiment, the running track data is subjected to data cleaning, data filtering and null value insertion respectively, so that the redundancy of the running track data can be reduced, and the effectiveness of the data is improved.
In one embodiment, the step of calculating the probability that the corresponding vehicle reaches the preset same destination according to the probability distribution function and the traveling track data in step S103 includes:
extracting a first track vector of a vehicle arriving at the destination and a second track vector of a vehicle not arriving at the destination from the historical vehicle track data and the information of whether the vehicle arrives at the destination;
calculating the central distance between each historical vehicle track reaching the destination and the first track vector to obtain histogram distribution formed by a first set, and solving a first probability distribution function according to the first histogram distribution through a maximum expectation algorithm and a mixed Gaussian distribution model;
calculating the central distance between each historical vehicle track reaching the destination and the second track vector to obtain histogram distribution formed by a second set, and solving a second probability distribution function according to the second histogram distribution through a maximum expectation algorithm and a mixed Gaussian distribution model;
calculating the central distance between each historical vehicle track which does not reach the destination and the first track vector to obtain histogram distribution formed by a third set, and solving a third probability distribution function according to the third histogram distribution through a maximum expectation algorithm and a mixed Gaussian distribution model;
calculating the central distance between each historical vehicle track which does not reach the destination and the second track vector to obtain histogram distribution formed by a fourth set, and solving a fourth probability distribution function according to the fourth histogram distribution through a maximum expectation algorithm and a mixed Gaussian distribution model;
substituting the driving track data of the vehicle into the first probability distribution function and the third probability distribution function to obtain a first arrival probability and a second arrival probability of the vehicle, and taking the product of the first arrival probability and the second arrival probability as the probability of the vehicle arriving at the destination;
and substituting the driving track data of the vehicle into the second probability distribution function and the fourth probability distribution function to obtain a first non-arrival probability and a second non-arrival probability of the vehicle, and taking the product of the first non-arrival probability and the second non-arrival probability as the probability that the vehicle does not arrive at the destination.
In one embodiment, the step of determining the vehicle with the calculated probability greater than the preset probability threshold as the candidate arriving vehicle in step S104 further includes:
and if the probability that the vehicle reaches the destination is greater than the probability that the vehicle does not reach the destination and the probability that the vehicle reaches the destination is greater than the preset probability threshold, judging that the vehicle is the candidate arrival vehicle.
When the destination is a port and the vehicle is a container truck, a usage scenario according to the embodiment is, for example: dividing historical vehicle track data into a track vector class 1 after dimensionality reduction of a container truck arriving at a port and a track vector class 2 after dimensionality reduction of the container truck not arriving at the port;
according to the d11 set of the distance between each container truck arriving at port and the class 1 center, histogram distribution can be obtained, and a first probability distribution function p11 is obtained through an EM algorithm and a mixed Gaussian distribution model
According to the distance d12 set between each container truck arriving at port and the class 2 center, histogram distribution can be obtained, and a second probability distribution function p12 is obtained through an EM algorithm and a mixed Gaussian distribution model;
according to the distance d21 set between each container truck not reaching the port and the class 1 center, histogram distribution can be obtained, and a third probability distribution function p21 is obtained through an EM algorithm and a mixed Gaussian distribution model;
according to the distance d22 set between each container truck not reaching the port and the class 2 center, histogram distribution can be obtained, and a fourth probability distribution function p22 is obtained through an EM algorithm and a mixed Gaussian distribution model;
calculating the distance d1 between the driving track data of the container truck to be predicted and the center of class 1, and calculating the distance d2 between the driving track data of the container truck to be predicted and the center of class 2;
substituting d1 into P11 and P21 to obtain probabilities P11 and P21;
substituting d2 into P12 and P22, the probabilities P12 and P22 were determined.
Assuming that the arrival and the departure of the container truck are independent, the probability of arrival of the container truck to be predicted is P11 × P12, and the probability of departure is P21 × P22.
At this time, if P11 × P12> P21 × P22 and P11 × P12>0.6, the container vehicle to be predicted is taken into the candidate arrival vehicle, otherwise, the container vehicle to be predicted is not taken into the candidate arrival vehicle.
According to an example of this embodiment, the reference numerals of the steps S101 to S108 are not used to limit the sequence of each step in this embodiment, and the number of each step is only to make the reference numeral that refers to each step in common when describing each step conveniently, as long as the execution sequence of each step does not affect the logical relationship in this embodiment.
The embodiment can be applied to flow analysis of port gates, judgment of arrival of container vehicles and prediction of arrival time, can further combine the transportation flow direction and distribution condition of the container vehicles, can form related indexes of logistics, transportation and ports, and makes up the defects of management, statistics and prediction of the existing container vehicles. The method increases a new visual angle for observing, predicting and analyzing the operation development trend of the container trucks arriving at the port, and the method analyzes based on historical vehicle GPS data provided by a data platform, designs corresponding container truck arriving prediction logic and mainly comprises three parts, namely data preprocessing, container truck arriving judgment and container truck arriving time prediction. And preprocessing steps such as coordinate data disappearance, mutation, stopping, representation, cleaning, filtering and the like are added to improve the accuracy of the prediction result. By counting the actual arrival time and arrival time, and comparing the arrival time and arrival time predicted by the vehicle arrival time prediction method, the accuracy of whether the vehicle arrives at the port or not predicted by the vehicle arrival time prediction method provided by the invention is 91.69%, and the average error of the predicted final arrival time is 16 minutes.
Fig. 7 is a block diagram illustrating an exemplary structure of a vehicle arrival time prediction apparatus according to an embodiment of the present invention, and the vehicle arrival time prediction apparatus 100 according to an embodiment of the present invention is described in detail below with reference to fig. 7, and as shown in fig. 7, includes a data receiving module 11, a coordinate series generation module 12, a first calculation module 13, a vehicle determination module 14, a second calculation module 15, a time acquisition module 16, a third calculation module 17, and a time calculation module 18.
And the data receiving module 11 is configured to receive a GPS data packet sent by a plurality of vehicles in real time, and analyze vehicle identifiers and coordinate information in the GPS data packet.
And the coordinate sequence generating module 12 is configured to generate a coordinate sequence corresponding to each vehicle identifier according to the time sequence, so as to obtain the travel track data of the corresponding vehicle.
The first calculating module 13 is configured to calculate the probability that the corresponding vehicle reaches the preset same destination through a probability distribution function and the travel track data, where the probability distribution function is obtained by solving the stored historical vehicle track data and whether the vehicle reaches the destination.
And a vehicle determination module 14, configured to determine a vehicle with the calculated probability greater than a preset probability threshold as an alternative arrival vehicle.
And a second calculating module 15, configured to calculate a predicted arrival time of each candidate arrival vehicle according to the historical vehicle trajectory data and the historical arrival time.
In one embodiment, the second calculation module 15 includes:
a historical arrival time obtaining unit, configured to obtain, from the historical vehicle trajectory data, a preset number of historical arrival vehicles having a minimum distance from the current position of the candidate arrival vehicle that is smaller than a preset value, and obtain an arrival time of each of the historical arrival vehicles;
and the average time calculation unit is used for calculating the average arrival time according to the arrival time of each historical arrival vehicle, and taking the average arrival time as the predicted arrival time of the candidate arrival vehicle.
And the time obtaining module 16 is configured to select a previous preset vehicle with the maximum probability in a preset time period away from the current time from the candidate arriving vehicles as a final arriving vehicle, and obtain a predicted arrival time of the final arriving vehicle.
And the third calculating module 17 is configured to calculate the congestion time between the final arrival vehicle and the destination in real time, and obtain a weight coefficient of the congestion time.
And a time calculation module 18, configured to calculate a final arrival time of the final arrival vehicle according to the predicted arrival time, the congestion time, and the weight coefficient.
In one embodiment, the time calculation module 18 calculates the final arrival time of the final arrival vehicle by the following equation (1):
T＝b*Tavg+∑an*Yn/Xn (1)
wherein, Σ anTo representThe weight coefficient of the congestion time, b ═ 1- Σ an，an＞0，b＞0，TavgRepresenting the predicted arrival time, X, of the final arriving vehiclenA mileage distance of n kilometers from the destination at the current time or an nth one kilometer from the destination, n is not more than k, k is a positive integer and represents a preset value or an actual distance between the final arriving vehicle and the destination, and Y isnRepresents XnThe total number of vehicles within the guided range distance.
In another embodiment, the time calculation module 18 calculates the final arrival time of the final arrival vehicle by the following equation (2):
T＝b*Tavg+∑an*Yn/Xn+∑cm*Zm (2)
where b represents the weight coefficient of the predicted arrival time, Σ anA weight coefficient, Σ c, representing the congestion timem＝1-b-∑an，an＞0，b＞0，cm＞0，XnA mileage distance of n kilometers from the destination at the current time or an nth one kilometer from the destination, n is not more than k, k is a positive integer and represents a preset value or an actual distance between the final arriving vehicle and the destination, and Y isnRepresents XnTotal number of vehicles within the guided mileage distance, ZmA mileage distance of m kilometers between the final arrival vehicle and the destination is represented, m is a positive integer, and m is n when k represents an actual distance between the final arrival vehicle and the destination.
In one embodiment, the apparatus 100 for predicting the arrival time of the vehicle further includes:
and the dimension reduction module is used for carrying out principal component analysis and dimension reduction processing on the driving track data to obtain dimension reduction track data.
The first calculating module 13 is specifically configured to calculate, through a probability distribution function and the dimension reduction trajectory data, a probability that the corresponding vehicle reaches a preset same destination.
In one embodiment, the apparatus 100 for predicting the arrival time of the vehicle further includes:
and the data preprocessing module is used for respectively carrying out data cleaning, data filtering and null value insertion processing on the driving track data to obtain the preprocessed driving track data.
The dimension reduction module is specifically configured to perform principal component analysis dimension reduction processing on the preprocessed travel track data to obtain the dimension reduction track data.
In one embodiment, the first calculation module 13 includes:
a vector extraction unit for extracting a first trajectory vector of a vehicle arriving at a destination and a second trajectory vector of a vehicle not arriving at the destination from the historical vehicle trajectory data and information on whether the vehicle arrives at the destination;
the first probability distribution function calculation unit is used for calculating the central distance between each historical vehicle track reaching the destination and the first track vector to obtain histogram distribution formed by a first set, and solving a first probability distribution function according to the first histogram distribution through a maximum expectation algorithm and a mixed Gaussian distribution model;
the second probability distribution function calculation unit is used for calculating the central distance between each historical vehicle track reaching the destination and the second track vector to obtain histogram distribution formed by a second set, and solving a second probability distribution function according to the second histogram distribution through a maximum expectation algorithm and a Gaussian mixture distribution model;
the third probability distribution function calculation unit is used for calculating the central distance between each historical vehicle track which does not reach the destination and the first track vector to obtain histogram distribution formed by a third set, and solving a third probability distribution function according to the third histogram distribution through a maximum expectation algorithm and a Gaussian mixture distribution model;
the fourth probability distribution function calculation unit is used for calculating the central distance between each historical vehicle track which does not reach the destination and the second track vector to obtain histogram distribution formed by a fourth set, and solving a fourth probability distribution function according to the fourth histogram distribution through a maximum expectation algorithm and a Gaussian mixture distribution model;
an arrival probability calculation unit, configured to bring the driving trajectory data of the vehicle into the first probability distribution function and the third probability distribution function to obtain a first arrival probability and a second arrival probability of the vehicle, and take a product of the first arrival probability and the second arrival probability as a probability that the vehicle arrives at the destination;
and the non-arrival probability calculation unit is used for substituting the driving track data of the vehicle into the second probability distribution function and the fourth probability distribution function to obtain a first non-arrival probability and a second non-arrival probability of the vehicle, and taking the product of the first non-arrival probability and the second non-arrival probability as the probability that the vehicle does not arrive at the destination.
In one embodiment, the vehicle determination module 14 includes:
and the judging unit is used for judging that the vehicle is the candidate arrival vehicle when the probability that the vehicle arrives at the destination is greater than the probability that the vehicle does not arrive at the destination and the probability that the vehicle arrives at the destination is greater than the preset probability threshold.
The first, second and third calculation modules in the first to third calculation modules are used only for distinguishing different calculation modules, and are not used for limiting which preselected region determination module has higher priority or other limiting meanings. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or modules is not necessarily limited to those steps or modules explicitly listed, but may include other steps or modules not explicitly listed or inherent to such process, method, article, or apparatus, and such that a division of modules presented in this application is merely a logical division and may be implemented in a practical application in a further manner.
Wherein, the modules included in the vehicle arrival time predicting device can be wholly or partially realized by software, hardware or a combination thereof. Further, each module in the vehicle arrival time prediction apparatus may be a program segment for realizing a corresponding function.
For specific definition of the vehicle arrival time prediction device, reference may be made to the above definition of the vehicle arrival time prediction method, which is not described herein again. The above-mentioned modules in the vehicle arrival time prediction apparatus may be implemented in whole or in part by software, hardware, or a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 8. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used to store data involved in the method of predicting the arrival time of a vehicle. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of predicting vehicle arrival time.
In one embodiment, a computer device is provided, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor when executing the computer program implementing the steps of the method for predicting vehicle arrival time in the above embodiments, such as steps 101 to 108 shown in fig. 2 and other extensions of the method and related steps. Alternatively, the processor, when executing the computer program, realizes the functions of the respective modules/units of the vehicle arrival time prediction apparatus in the above-described embodiment, for example, the functions of the modules 11 to 18 shown in fig. 7. To avoid repetition, further description is omitted here.
Those skilled in the art will appreciate that the architecture shown in fig. 8 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for predicting vehicle arrival time in the above-described embodiments, such as the steps 101 to 108 shown in fig. 2 and extensions of other extensions and related steps of the method. Alternatively, the computer program, when executed by the processor, implements the functions of the respective modules/units of the vehicle arrival time prediction apparatus in the above-described embodiment, for example, the functions of the modules 11 to 18 shown in fig. 7. To avoid repetition, further description is omitted here.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, etc. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like which is the control center for the computer device and which connects the various parts of the overall computer device using various interfaces and lines.
The memory may be used to store the computer programs and/or modules, and the processor may implement various functions of the computer device by running or executing the computer programs and/or modules stored in the memory and invoking data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, video data, etc.) created according to the use of the cellular phone, etc. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
The memory may be integrated in the processor or may be provided separately from the processor.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM), and includes several instructions for enabling a terminal (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present application.
The method, the apparatus, the computer device and the storage medium for predicting vehicle arrival time provided by this embodiment receive a GPS data packet sent by a plurality of vehicles in real time, analyze vehicle identifications and coordinate information in the GPS data packet to obtain travel track data of corresponding vehicles, then calculate a probability that the corresponding vehicle arrives at a preset same destination through a probability distribution function and the travel track data, determine a vehicle having the calculated probability greater than a preset probability threshold as an alternative arrival vehicle, and further consider the number of the maximum vehicles that can be accommodated at the destination because the vehicles that can be accommodated at the same time period of the destination are limited and the alternative arrival vehicles determined according to the probability are not always reachable, so the scheme further sets that a front preset vehicle having the maximum probability in a preset time period separated from the current time is selected from the alternative arrival vehicles as a final arrival vehicle, and acquiring the predicted arrival time of the final arrival vehicle from the pre-calculated predicted arrival time of each candidate arrival vehicle, then calculating the congestion time between the final arrival vehicle and the destination in real time, acquiring the weight coefficient of the congestion time, calculating the final arrival time of the final arrival vehicle according to the predicted arrival time, the congestion time and the weight coefficient, and considering the accommodation situation of the destination, namely the real-time congestion situation between the vehicle and the destination according to the final arrival time of the final arrival vehicle and the final arrival vehicle calculated according to the method of the application, so that the method is applied to the destination and can accurately predict all vehicles which are possible to finally arrive at the destination and the arrival time at the destination.
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (5)
1. A method of predicting vehicle arrival time, the method comprising:
receiving GPS data packets sent by a plurality of vehicles in real time, and analyzing vehicle identifications and coordinate information in the GPS data packets;
generating a coordinate sequence corresponding to each vehicle identifier according to the time sequence to obtain the running track data of the corresponding vehicle;
calculating the probability of the corresponding vehicle reaching the same preset destination through a probability distribution function and the traveling track data, wherein the probability distribution function is obtained by solving the stored historical vehicle track data and whether the vehicle reaches the destination;
determining the vehicles with the calculated probability greater than a preset probability threshold value as alternative arrival vehicles;
calculating the predicted arrival time of each alternative arrival vehicle according to the historical vehicle track data and the historical arrival time;
selecting a front preset vehicle with the maximum probability in a preset time period away from the current time from the candidate arriving vehicles as a final arriving vehicle, and acquiring the predicted arrival time of the final arriving vehicle;
calculating the congestion time between the final arrival vehicle and the destination in real time, and acquiring a weight coefficient of the congestion time;
calculating the final arrival time of the final arrival vehicle according to the predicted arrival time, the congestion time and the weight coefficient;
before the step of calculating the probability that the corresponding vehicle reaches the preset same destination through the probability distribution function and the traveling track data, the method further comprises:
respectively carrying out data cleaning, data filtering and null value insertion processing on the running track data to obtain preprocessed running track data;
carrying out principal component analysis and dimensionality reduction on the preprocessed running track data to obtain dimensionality reduction track data;
wherein, the step of calculating the probability of the corresponding vehicle reaching the same preset destination through the probability distribution function and the traveling track data further comprises:
calculating the probability of the corresponding vehicle reaching the same preset destination through a probability distribution function and the dimension reduction track data;
wherein the step of calculating a final arrival time of the final arrival vehicle based on the predicted arrival time, the congestion time, and the weight coefficient comprises:
calculating a final arrival time of the final arrival vehicle by the following formula
T＝b*Tavg+∑an*Yn/Xn；
Wherein, Σ anA weight coefficient representing the congestion time, b being 1- Σ an，b＞0，an＞0，TavgRepresenting the predicted arrival time, X, of the final arriving vehiclenA mileage distance of n kilometers from the destination at the current time or an nth one kilometer from the destination, n is not more than k, k is a positive integer and represents a preset value or an actual distance between the final arriving vehicle and the destination, and Y isnRepresents XnA total number of vehicles within the guided range distance;
or
Calculating a final arrival time of the final arrival vehicle by the following formula
T＝b*Tavg+∑an*Yn/Xn+∑cm*Zm；
Where b represents the weight coefficient of the predicted arrival time, Σ anA weight coefficient, Σ c, representing the congestion timem＝1-b-∑an，an＞0，b＞0，cm＞0，XnA mileage distance of n kilometers from the destination at the current time or an nth one kilometer from the destination, n is not more than k, k is a positive integer and represents a preset value or an actual distance between the final arriving vehicle and the destination, and Y isnRepresents XnTotal number of vehicles within the guided mileage distance, ZmA mileage distance of m kilometers between the final arrival vehicle and the destination is represented, m is a positive integer, and m is n when k represents an actual distance between the final arrival vehicle and the destination.
2. The method of claim 1, wherein the step of calculating a predicted arrival time for each of the alternative arrival vehicles based on the historical vehicle trajectory data and historical arrival times comprises:
acquiring historical vehicle track data and historical arrival time of all vehicles arriving at the destination;
acquiring the minimum preset arriving vehicles with the distance to the current position of the alternative arriving vehicle smaller than a preset value from the historical vehicle track data, and acquiring the arrival time of each historical arriving vehicle;
and calculating an average arrival time according to the arrival time of each historical arrival vehicle, and taking the average arrival time as the predicted arrival time of the alternative arrival vehicle.
3. An apparatus for predicting vehicle arrival time, the apparatus comprising:
the data receiving module is used for receiving GPS data packets sent by a plurality of vehicles in real time and analyzing vehicle identifications and coordinate information in the GPS data packets;
the coordinate sequence generating module is used for generating a coordinate sequence corresponding to each vehicle identifier according to the time sequence to obtain the running track data of the corresponding vehicle;
the first calculation module is used for calculating the probability of the corresponding vehicle reaching the same preset destination through a probability distribution function and the running track data, wherein the probability distribution function is obtained by solving the stored historical vehicle track data and whether the vehicle reaches the destination;
the vehicle determining module is used for determining the vehicle with the calculated probability larger than a preset probability threshold value as an alternative arrival vehicle;
the second calculation module is used for calculating the predicted arrival time of each alternative arrival vehicle according to the historical vehicle track data and the historical arrival time;
the time obtaining module is used for selecting a front preset vehicle with the maximum probability in a preset time period away from the current time from the candidate arriving vehicles as a final arriving vehicle and obtaining the predicted arrival time of the final arriving vehicle;
the third calculation module is used for calculating the congestion time between the final arrival vehicle and the destination in real time and acquiring the weight coefficient of the congestion time;
the time calculation module is used for calculating the final arrival time of the final arrival vehicle according to the predicted arrival time, the congestion time and the weight coefficient;
wherein, prior to the first computing module, the apparatus further comprises:
the preprocessing module is used for respectively carrying out data cleaning, data filtering and null value insertion processing on the driving track data to obtain preprocessed driving track data;
the dimensionality reduction module is used for carrying out principal component analysis dimensionality reduction processing on the preprocessed running track data to obtain the dimensionality reduction track data;
wherein the first computing module is further to:
the first dimension reduction calculation module is used for calculating the probability of the corresponding vehicle reaching the same preset destination through a probability distribution function and the dimension reduction track data;
wherein the time calculation module comprises:
a first time calculation unit for calculating a final arrival time of the final arrival vehicle by the following formula
T＝b*Tavg+∑an*Yn/Xn；
Wherein, Σ anA weight coefficient representing the congestion time, b being 1- Σ an，b＞0，an＞0，TavgRepresenting the predicted arrival time, X, of the final arriving vehiclenA mileage distance of n kilometers from the destination at the current time or an nth one kilometer from the destination, n is not more than k, k is a positive integer and represents a preset value or an actual distance between the final arriving vehicle and the destination, and Y isnRepresents XnA total number of vehicles within the guided range distance;
or
A second time calculation unit for calculating a final arrival time of the final arrival vehicle by the following formula
T＝b*Tavg+∑an*Yn/Xn+∑cm*Zm；
Where b represents the weight coefficient of the predicted arrival time, Σ anA weight coefficient, Σ c, representing the congestion timem＝1-b-∑an，an＞0，b＞0，cm＞0，XnA mileage distance of n kilometers from the destination at the current time or an nth one kilometer from the destination, n is not more than k, k is a positive integer and represents a preset value or an actual distance between the final arriving vehicle and the destination, and Y isnRepresents XnTotal number of vehicles within the guided mileage distance, ZmA mileage distance of m kilometers between the final arrival vehicle and the destination is represented, m is a positive integer, and m is n when k represents an actual distance between the final arrival vehicle and the destination.
4. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor, when executing the program, implements a method of predicting vehicle arrival time according to any one of claims 1 to 2.
5. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for predicting vehicle arrival time according to any one of claims 1 to 2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911369725.7A CN111192451B (en) | 2019-12-26 | 2019-12-26 | Vehicle arrival time prediction method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911369725.7A CN111192451B (en) | 2019-12-26 | 2019-12-26 | Vehicle arrival time prediction method and device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111192451A CN111192451A (en) | 2020-05-22 |
| CN111192451B true CN111192451B (en) | 2021-07-09 |
Family
ID=70707570
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911369725.7A Active CN111192451B (en) | 2019-12-26 | 2019-12-26 | Vehicle arrival time prediction method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111192451B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112330094A (en) * | 2020-10-09 | 2021-02-05 | 广州市物联万方电子科技有限公司 | Container scheduling method and device and server |
| CN112598907B (en) * | 2020-12-17 | 2021-12-07 | 东风商用车有限公司 | Congestion prediction method, device, equipment and readable storage medium |
| CN113706874B (en) * | 2021-10-28 | 2022-01-28 | 华清科盛(北京)信息技术有限公司 | Method and device for predicting arrival time of logistics vehicles in factory in real time and electronic equipment |
| CN116976781A (en) * | 2023-06-09 | 2023-10-31 | 湖南工商大学 | Method and device for solving path problem of time-position dependent multi-target green vehicle |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102087722A (en) * | 2009-12-04 | 2011-06-08 | 索尼公司 | Learning apparatus and method, prediction apparatus and method, and program |
| CN105900031A (en) * | 2013-10-29 | 2016-08-24 | 沃尔沃建筑设备公司 | System for calculating desired estimated time of arrival |
| CN108257378A (en) * | 2016-12-29 | 2018-07-06 | 杭州海康威视数字技术股份有限公司 | traffic flow forecasting method and device |
| US10210751B1 (en) * | 2017-08-04 | 2019-02-19 | Verizon Patent And Licensing Inc. | Identification of traffic control mechanisms using machine learning |
-
2019
- 2019-12-26 CN CN201911369725.7A patent/CN111192451B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102087722A (en) * | 2009-12-04 | 2011-06-08 | 索尼公司 | Learning apparatus and method, prediction apparatus and method, and program |
| CN105900031A (en) * | 2013-10-29 | 2016-08-24 | 沃尔沃建筑设备公司 | System for calculating desired estimated time of arrival |
| CN108257378A (en) * | 2016-12-29 | 2018-07-06 | 杭州海康威视数字技术股份有限公司 | traffic flow forecasting method and device |
| US10210751B1 (en) * | 2017-08-04 | 2019-02-19 | Verizon Patent And Licensing Inc. | Identification of traffic control mechanisms using machine learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111192451A (en) | 2020-05-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111192451B (en) | Vehicle arrival time prediction method and device, computer equipment and storage medium | |
| US9240124B2 (en) | Traffic-volume prediction device and method | |
| Li et al. | A general framework for unmet demand prediction in on-demand transport services | |
| CN110647929B (en) | Method for predicting travel destination and method for training classifier | |
| CN113155173B (en) | Perception performance evaluation method and device, electronic device and storage medium | |
| CN104933870A (en) | Vehicle fake plate identification method and device based on vehicle behavior analysis | |
| CN104599002B (en) | Method and equipment for predicting order value | |
| CN110111599B (en) | Parking guidance method based on big data, terminal equipment and storage medium | |
| CN110472999B (en) | Passenger flow mode analysis method and device based on subway and shared bicycle data | |
| CN112882073B (en) | Time-threshold-based hidden Markov model human-vehicle integration algorithm | |
| CN112579718B (en) | Urban land function identification method and device and terminal equipment | |
| US11250031B2 (en) | Method of predicting a traffic behaviour in a road system | |
| CN113611104B (en) | Risk identification method and device for freight vehicle, storage medium and terminal | |
| CN111179589A (en) | Method, device, equipment and storage medium for predicting vehicle OD | |
| CN112837556A (en) | Vehicle position information monitoring processing method and device | |
| Rahaman et al. | Predicting Imbalanced Taxi and Passenger Queue Contexts in Airport. | |
| CN110555473A (en) | Driving route planning method, server and system | |
| CN111369790B (en) | Vehicle passing record correction method, device, equipment and storage medium | |
| CN111640300B (en) | Vehicle detection processing method and device | |
| CN109360137B (en) | Vehicle accident assessment method, computer readable storage medium and server | |
| CN111445715A (en) | Intelligent city traffic scheduling method and scheduling equipment based on Internet of things communication | |
| CN113160565B (en) | Fake-licensed vehicle identification method and device, storage medium and terminal | |
| CN113284337B (en) | OD matrix calculation method and device based on vehicle track multidimensional data | |
| CN112686125A (en) | Vehicle type determination method and device, storage medium and electronic device | |
| CN115131958B (en) | Method and device for pushing congestion road conditions, electronic equipment and storage medium |
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 |