CN116682254B - Single-route-taking planning method for driver based on taxi order and GPS data - Google Patents
Single-route-taking planning method for driver based on taxi order and GPS data Download PDFInfo
- Publication number
- CN116682254B CN116682254B CN202310967105.3A CN202310967105A CN116682254B CN 116682254 B CN116682254 B CN 116682254B CN 202310967105 A CN202310967105 A CN 202310967105A CN 116682254 B CN116682254 B CN 116682254B
- Authority
- CN
- China
- Prior art keywords
- data
- order
- time
- taxi
- real
- 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
- 238000013439 planning Methods 0.000 title claims abstract description 48
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000013473 artificial intelligence Methods 0.000 claims abstract description 20
- 238000005516 engineering process Methods 0.000 claims abstract description 17
- 239000013598 vector Substances 0.000 claims abstract description 17
- 238000012545 processing Methods 0.000 claims abstract description 14
- 230000001413 cellular effect Effects 0.000 claims abstract description 5
- 238000004458 analytical method Methods 0.000 claims description 15
- 238000012384 transportation and delivery Methods 0.000 claims description 11
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 9
- 238000012300 Sequence Analysis Methods 0.000 claims description 6
- 238000000611 regression analysis Methods 0.000 claims description 6
- 230000006399 behavior Effects 0.000 claims description 5
- 238000003058 natural language processing Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 3
- 239000003086 colorant Substances 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 230000004927 fusion Effects 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 230000003287 optical effect Effects 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 230000029305 taxis Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 201000004569 Blindness Diseases 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/20—Monitoring the location of vehicles belonging to a group, e.g. fleet of vehicles, countable or determined number of vehicles
- G08G1/202—Dispatching vehicles on the basis of a location, e.g. taxi dispatching
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The application discloses a single-route-taking planning method for a driver based on a taxi order and GPS data, which comprises the following steps: step one, data acquisition: collecting historical order data and real-time GPS data; step two, data processing: a large amount of historical order data and real-time GPS data are processed and analyzed by using an artificial intelligence technology so as to provide accurate data support for a route planning algorithm, the historical order quantity is counted according to a cellular range of 1 km by utilizing the patrol history order data and the real-time GPS data, net-call and shake-call orders in a certain area, an area with possibly tense capacity in the future is predicted according to the state of empty and loaded vehicles, the GPS position and the driving direction of the real-time vehicles, the vehicles in the area with the tense capacity are guided in real time according to a certain heat vector, the driving route of the vehicles is corrected according to the capacity condition of the vehicles continuously, and the optimal driver order receiving route is designed, so that the order receiving efficiency of the driver is improved, and the empty driving rate of the taxi is reduced.
Description
Technical Field
The application belongs to the field of taxi scheduling, and particularly relates to a taxi order taking single-route planning method for a driver based on a taxi order and GPS data, and meanwhile, relates to artificial intelligence technology in the fields of machine learning, deep learning and the like.
Background
The traditional taxi dispatching method has certain blindness, and the problems of route crossing, idle running and the like easily occur in the process of taking a bill, so that the operation efficiency of the taxi is low. The existing taxi dispatching system can conduct certain route planning through order data and GPS data, but does not fully consider actual situations of drivers, such as traffic jams, road conditions and other factors, so that certain limitations exist in practical application. In cities, taxis are a common transportation means, while regional taxis are a special taxi service form, and the method is characterized in that the taxis are carried out according to a fixed area, so that convenience trip service is provided for passengers. However, because the regional cruising taxi operation is affected by a plurality of factors such as quantity, road condition, passenger flow volume, order taking behavior and the like, how to effectively manage and optimize the order taking behavior of a driver is always a difficult problem faced by the taxi industry.
Currently, some companies have begun to employ GPS positioning technology and data analysis methods to optimize driver order taking routing. However, these methods often provide simple route recommendations and cannot take into account further factors such as traffic conditions, passenger demands, etc. In addition, these methods have certain limitations such as the need for extensive data support, the need for specialized technicians to perform data analysis, and the like.
Therefore, the application provides a driver single-route-receiving planning system based on order data and GPS data, which aims to solve the problems of the existing system and improve the efficiency and accuracy of the system.
Disclosure of Invention
In view of the above, the application aims at overcoming the defects of the prior art, and the main content of the application is a single-route planning method for driver access based on taxi orders and GPS data, and meanwhile, the application utilizes artificial intelligence technology in the fields of machine learning, deep learning, natural language processing and the like.
In order to achieve the above purpose, the present application provides the following technical solutions: a driver single-route-receiving planning method based on taxi orders and GPS data comprises the following steps:
step one, data acquisition: collecting historical order data and real-time GPS data;
step two, data processing: processing and resolving a large amount of historical order data and real-time GPS data using artificial intelligence techniques to provide accurate data support for route planning algorithms;
step three, designing a route planning algorithm:
a. counting historical order quantity of urban orders according to a cellular range of 1 km;
b. predicting the future range with the tension of the transportation capacity according to the real-time state of the empty and loaded vehicle, the GPS position and the driving direction of the vehicle;
c. guiding the vehicles in the capacity rich area in real time according to different heat vectors, and correcting the vehicle driving route continuously according to the capacity condition of the vehicles;
step four, algorithm optimization: the route planning algorithm is continuously optimized by utilizing an artificial intelligence technology, the ratio relation between the order forecast amount and the truly occurring order amount and shunting number is continuously adjusted according to the historical data, and the algorithm is optimized;
step five, real-time scheduling: and the algorithm is applied to a taxi dispatching system to realize real-time route planning.
Further preferred is: in the first step, historical order data and real-time GPS data are collected through a taxi terminal device, and taxi related driver and vehicle information comprises any one or more of license plate numbers, vehicle types, colors, gender of drivers, age and academic; collecting position information, speed, head direction and running track of the vehicle through GPS equipment installed on the vehicle; meanwhile, collecting information of the time and place of getting on and off the passenger through a sensor connected with the price meter; finally, the data are collected through network equipment connected with a dispatching center.
Further preferred is: in the second step, preprocessing the collected data, including de-duplication, cleaning and normalization;
grouping orders according to OD requirements by using a clustering algorithm;
calculating the total order area demand and distribution according to the grouping result; processing and resolving a large amount of historical order data and real-time GPS data using artificial intelligence techniques to provide accurate data support for route planning algorithms; meanwhile, the behavior of the driver is identified and analyzed by using a computer vision technology and a natural language processing technology so as to know the driving habit and the order taking tendency of the driver;
and provides personalized services and route planning schemes according to driving habits and order taking trends.
Further preferred is: in step two, the artificial intelligence technique includes:
acquiring each order;
randomly selecting an order from all orders to serve as an initial clustering center;
selecting a plurality of orders from other orders to serve as other clustering centers according to order information of each order, the initial clustering center and the number of order groups, wherein the order similarity among the orders serving as the clustering centers is the smallest, the order similarity among the orders is determined according to the order information, and the order information at least comprises: end position, initial position, pick-up distance and predicted delivery time;
clustering the ungrouped orders according to the order information of the ungrouped orders and the determined clustering centers, and determining the order groups in a parallel order determining mode;
for each order group, determining at least one pick-up and delivery capacity corresponding to the order group;
and carrying out order distribution according to the matching degree of the orders in the order group and the pick-up and delivery capacity corresponding to the order group.
Further preferred is: the clustering algorithm comprises the following steps:
acquiring travel demand data of a user;
clustering is carried out according to the travel demand data, and a travel demand cluster is determined;
determining a demand cluster distance matrix according to the travel demand clusters, including:
determining a representative OD of each travel demand cluster according to the travel demand clusters;
determining the position distance dissimilarity and the direction distance dissimilarity among the plurality of representative ODs, wherein the position distance dissimilarity is determined according to the head-tail distances among the plurality of representative ODs, and the direction distance dissimilarity is determined according to the included angles among the plurality of representative ODs and the length proportion;
performing weighted calculation according to the position distance dissimilarity degree and the direction distance dissimilarity degree, determining the distances among a plurality of representative ODs, and generating the demand cluster distance matrix;
and carrying out secondary clustering according to the demand cluster distance matrix, and determining demand subareas, wherein each demand subarea comprises a plurality of OD (optical density) with similar positions and directions.
Further preferred is: in the third step, the different heat vectors are respectively a low-level heat vector, a medium-level heat vector and a high-level heat vector.
Further preferred is: in the fourth step, an artificial intelligence technology is used for optimizing a route planning algorithm, and the ratio relation between the predicted order quantity and the truly generated order quantity and shunting quantity is continuously adjusted according to historical data, so that the algorithm is optimized;
and modeling historical order quantity and passenger flow data by using a time sequence analysis and regression analysis method so as to predict future demand conditions and adjust the scheduling plan of the vehicle according to the future demand conditions.
Further preferred is: the time sequence analysis and regression analysis method comprises the following steps:
preprocessing time series data of historical order quantity and passenger flow data, wherein the preprocessing comprises one or more of data deduplication, time series set division, data type conversion, missing value filling, time series feature extraction, time series feature construction, independent heat coding and data fusion;
inputting the time series data of the historical order quantity and the passenger flow volume data into a preset analysis prediction model, wherein the method comprises the following steps of:
inputting the preprocessed time series data into the preset analysis prediction model;
acquiring time sequence data of historical order quantity and passenger flow volume data, wherein the time sequence data comprises one or more of a central processing unit utilization rate time sequence, a memory utilization rate time sequence, an average input/output request time sequence, a network card receiving byte number per second time sequence and a network card transmitting byte number per second time sequence;
inputting the time series data of the historical order quantity and the passenger flow volume data into a preset analysis prediction model, wherein the preset analysis prediction model is obtained through training of the time series data of a reference server and a critical value corresponding to the time series data of the reference server at preset time, and the critical value comprises a maximum value and/or a minimum value;
and obtaining the prediction critical value of the time series data of the historical order quantity and the passenger flow data according to the output of the preset analysis prediction model.
Further preferred is: in step five, a route planning algorithm is applied to the taxi dispatching system to realize real-time route planning, and the operation plan of the vehicle is adjusted according to the prediction result, so that personalized service and route planning schemes are provided to adapt to the needs of users and the changes of traffic conditions.
Compared with the prior art, the application has the beneficial effects that:
the application can better predict the range of possible capacity shortage in the future and guide vehicles in the capacity rich area in real time by processing a large amount of historical order data and real-time GPS data by using artificial intelligence technology. The method has wide application prospect, and can be applied to the fields of taxi dispatching, network taxi management and the like;
according to the application, by utilizing the patrol and lease historical order data and the real-time GPS data, the historical order quantity is counted according to the cellular range of 1 km by using the net-call and shake-call orders in a certain area, the area with possibly-stressed transport capacity in the future is predicted according to the real-time vehicle empty-load state, the GPS position and the driving direction, the vehicles in the transport capacity rich area are guided in real time according to a certain heat vector, the vehicle driving route is corrected according to the transport capacity condition of the vehicles continuously, and the optimal driver order receiving route is designed, so that the order receiving efficiency of a driver is improved, and the empty driving rate of a taxi is reduced.
Drawings
FIG. 1 is a flow chart of the method of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Referring to fig. 1, the present application provides a technical solution: a driver single-route-receiving planning method based on taxi orders and GPS data comprises the following steps:
step one, data acquisition: collecting historical order data and real-time GPS data;
step two, data processing: processing and resolving a large amount of historical order data and real-time GPS data using artificial intelligence techniques to provide accurate data support for route planning algorithms;
step three, designing a route planning algorithm:
a. counting historical order quantity of urban orders according to a cellular range of 1 km;
b. predicting the future range with the tension of the transportation capacity according to the real-time state of the empty and loaded vehicle, the GPS position and the driving direction of the vehicle;
c. guiding the vehicles in the capacity rich area in real time according to different heat vectors, and correcting the vehicle driving route continuously according to the capacity condition of the vehicles;
step four, algorithm optimization: the route planning algorithm is continuously optimized by utilizing an artificial intelligence technology, the ratio relation between the order pre-measurement and the truly occurring order quantity and shunting quantity is continuously adjusted according to historical data, the algorithm is optimized, and the planning precision and efficiency are further improved;
step five, real-time scheduling: and the algorithm is applied to a taxi dispatching system to realize real-time route planning.
In this embodiment, specific: in the first step, historical order data and real-time GPS data are collected through a taxi terminal device, and taxi related driver and vehicle information comprises any one or more of license plate numbers, vehicle types, colors, gender of drivers, age and academic; collecting position information, speed, head direction and running track of the vehicle through GPS equipment installed on the vehicle; meanwhile, collecting information of the time and place of getting on and off the passenger through a sensor connected with the price meter; finally, the data are collected through network equipment connected with a dispatching center. Based on the above description, in the application, the taxi terminal device requires the user identity information provided by the user (driver and passenger) to pass the authentication of the trusted third party, and the user (driver and passenger) provides the user identity information to the taxi terminal device under the condition that the user identity information provided by the taxi terminal device is determined to pass the authentication of the trusted third party. The method can ensure the rationality of the user identity information required by the taxi terminal equipment to a certain extent, thereby being beneficial to ensuring the privacy and safety of the user. In addition, the reasonability of the user identity information requirement of the taxi terminal equipment is also realized by the trusted third party to help the user (driver and passenger) to confirm, and the trust of the user (driver and passenger) to the taxi terminal equipment can be enhanced, so that the normal driving experience is ensured.
In this embodiment, specific: in the second step, preprocessing the collected data, including de-duplication, cleaning and normalization;
grouping orders according to OD requirements by using a clustering algorithm;
calculating the total order area demand and distribution according to the grouping result; processing and resolving a large amount of historical order data and real-time GPS data using artificial intelligence techniques to provide accurate data support for route planning algorithms; meanwhile, the behavior of the driver is identified and analyzed by using a computer vision technology and a natural language processing technology so as to know the driving habit and the order taking tendency of the driver;
and provides personalized services and route planning schemes according to driving habits and order taking trends.
In this embodiment, specific: in step two, the artificial intelligence technique includes:
acquiring each order;
the server may receive an order sent by the user's terminal and determine order information for the order to distribute the received order through subsequent steps. In one or more embodiments of the present description, the order information includes at least: end position, initial position, pickup distance, and predicted arrival time. The final position and the initial position may be determined according to an order sent by the terminal of the user, for example, assuming that the order uploaded by the terminal includes a position selected by the user and a merchant name, the server takes the position selected by the user as the final position, and determines the initial position according to the merchant name. The server can then determine the pick-up distance and the predicted delivery time for the order based on the end location and the initial location. For example, a path is planned according to the determined end position and initial position, the distance of the pick-up path is determined as the pick-up distance, and the estimated time of arrival of the order is determined according to the average speed of the pick-up capacity.
Randomly selecting an order from all orders to serve as an initial clustering center;
the server can determine each order group according to a preset scheduling period when determining that order allocation is required, so as to reduce the calculated amount when determining the matching degree of the order and the pick-up and delivery capacity; the server may group orders according to order similarity between each order. Moreover, since clustering methods can be generally adopted to determine each order group according to the similarity, the server can determine each clustering center first; the server can determine the similarity between the orders according to the order information of the orders, and determine other clustering centers according to the similarity between the orders and the initial clustering center.
Selecting a plurality of orders from other orders to serve as other clustering centers according to order information of each order, the initial clustering center and the number of order groups, wherein the order similarity among the orders serving as the clustering centers is the smallest, the order similarity among the orders is determined according to the order information, and the order information at least comprises: end position, initial position, pick-up distance and predicted delivery time;
clustering the ungrouped orders according to the order information of the ungrouped orders and the determined clustering centers, and determining the order groups in a parallel order determining mode;
for each order group, determining at least one pick-up and delivery capacity corresponding to the order group;
and carrying out order distribution according to the matching degree of the orders in the order group and the pick-up and delivery capacity corresponding to the order group.
In this embodiment, specific: the clustering algorithm comprises the following steps:
acquiring travel demand data of a user;
clustering is carried out according to the travel demand data, and a travel demand cluster is determined;
determining a demand cluster distance matrix according to the travel demand clusters, including:
determining a representative OD of each travel demand cluster according to the travel demand clusters;
determining the position distance dissimilarity and the direction distance dissimilarity among the plurality of representative ODs, wherein the position distance dissimilarity is determined according to the head-tail distances among the plurality of representative ODs, and the direction distance dissimilarity is determined according to the included angles among the plurality of representative ODs and the length proportion;
performing weighted calculation according to the position distance dissimilarity degree and the direction distance dissimilarity degree, determining the distances among a plurality of representative ODs, and generating the demand cluster distance matrix;
and carrying out secondary clustering according to the demand cluster distance matrix, and determining demand subareas, wherein each demand subarea comprises a plurality of OD (optical density) with similar positions and directions.
By analyzing the spatial distribution characteristics of the travel demands of the users, the demand coverage area is divided into a plurality of different demand subareas, so that on one hand, a decision maker is helped to know the travel characteristics of the city, and a developer is helped to reduce the solving scale of a single problem; on the other hand, by considering the flow direction relation among the ODs, the rationality of the division of the demand subareas can be improved, and the generation of public transportation lines under the driving of data is facilitated;
and de-duplicating the travel data, and determining a plurality of OD pairs and the demand of each OD pair according to the travel starting point and the travel ending point to serve as the travel demand data. In the embodiment of the application, the division of the demand subareas is only performed from the perspective of the geographic position of the space, and the division of the high demand areas and the low demand areas is not performed, so that the demand quantity is irrelevant. Therefore, the trip data is de-duplicated, only every two non-repeated trip records are left as an OD pair, and the same demand number of starting and ending points is used as the demand of the OD pair. The following table 1 shows the data format of the travel demand data according to the embodiment of the present application, and it can be understood that the data format can be adjusted according to the actual application demand, and the present application is not limited thereto.
TABLE 1
In this embodiment, specific: in the third step, the different heat vectors are respectively a low-level heat vector, a medium-level heat vector and a high-level heat vector.
In this embodiment, specific: in the fourth step, an artificial intelligence technology is used for optimizing a route planning algorithm, and the ratio relation between the predicted order quantity and the truly generated order quantity and shunting quantity is continuously adjusted according to historical data, so that the algorithm is optimized;
and modeling historical order quantity and passenger flow data by using a time sequence analysis and regression analysis method so as to predict future demand conditions and adjust the scheduling plan of the vehicle according to the future demand conditions.
In this embodiment, specific: the time sequence analysis and regression analysis method comprises the following steps:
preprocessing time series data of historical order quantity and passenger flow data, wherein the preprocessing comprises one or more of data deduplication, time series set division, data type conversion, missing value filling, time series feature extraction, time series feature construction, independent heat coding and data fusion;
inputting the time series data of the historical order quantity and the passenger flow volume data into a preset analysis prediction model, wherein the method comprises the following steps of:
inputting the preprocessed time series data into the preset analysis prediction model;
acquiring time sequence data of historical order quantity and passenger flow volume data, wherein the time sequence data comprises one or more of a central processing unit utilization rate time sequence, a memory utilization rate time sequence, an average input/output request time sequence, a network card receiving byte number per second time sequence and a network card transmitting byte number per second time sequence;
inputting the time series data of the historical order quantity and the passenger flow volume data into a preset analysis prediction model, wherein the preset analysis prediction model is obtained through training of the time series data of a reference server and a critical value corresponding to the time series data of the reference server at preset time, and the critical value comprises a maximum value and/or a minimum value;
and obtaining the prediction critical value of the time series data of the historical order quantity and the passenger flow data according to the output of the preset analysis prediction model.
Time-series data of the target server, for example, time-series data of 5 indexes (CPU usage, memory usage, average IO request number, number of bytes received by the network card per second and number of bytes transmitted by the network card per second) for 2 months, is obtained from the Hive database of the operator, and may include the following fields: acquisition date (data_date), acquisition hour (data_hour), server IP (IP), maximum value (max_value), minimum value (min_value), average value (avg_value), and the like. For example, as shown in table 2, a time series of indicators (e.g., CPU usage, memory usage, average IO requests, number of bytes received per second by the network card, or number of bytes sent per second by the network card) includes 5 features: acquisition date, acquisition hour, maximum value, minimum value and average value;
TABLE 2
In this embodiment, specific: in step five, a route planning algorithm is applied to the taxi dispatching system to realize real-time route planning, and the operation plan of the vehicle is adjusted according to the prediction result, so that personalized service and route planning schemes are provided to adapt to the needs of users and the changes of traffic conditions.
The application has the advantages that the optimal driver order receiving route can be automatically found according to the historical order data and the real-time GPS data, thereby improving the order receiving efficiency of the driver and reducing the idle rate of the taxi. Furthermore, by using artificial intelligence techniques to process large amounts of historical order data and real-time GPS data, we can better predict the extent to which there may be a capacity shortage in the future and guide vehicles in the capacity rich area in real-time. The method has wide application prospect and can be applied to the fields of taxi dispatching, network taxi management and the like.
In the description of the present specification, the descriptions of the terms "one embodiment," "example," "specific example," and the like, mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples.
Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Although embodiments of the present application have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the application, the scope of which is defined in the appended claims and their equivalents.
Claims (7)
1. The method for planning the single-route access of the driver based on the taxi order and GPS data is characterized by comprising the following steps:
step one, data acquisition: collecting historical order data and real-time GPS data;
step two, data processing: processing and resolving a large amount of historical order data and real-time GPS data using artificial intelligence techniques to provide accurate data support for route planning algorithms;
step three, designing a route planning algorithm:
a. counting historical order quantity of urban orders according to a cellular range of 1 km;
b. predicting the future range with the tension of the transportation capacity according to the real-time state of the empty and loaded vehicle, the GPS position and the driving direction of the vehicle;
c. guiding the vehicles in the capacity rich area in real time according to different heat vectors, and correcting the vehicle driving route continuously according to the capacity condition of the vehicles;
step four, algorithm optimization: the route planning algorithm is continuously optimized by utilizing an artificial intelligence technology, the ratio relation between the order forecast amount and the truly occurring order amount and shunting number is continuously adjusted according to the historical data, and the algorithm is optimized;
optimizing a route planning algorithm by using an artificial intelligence technology, continuously adjusting the ratio relation between the predicted order quantity and the truly generated order quantity and shunting quantity according to historical data, and optimizing the algorithm;
modeling historical order quantity and passenger flow data by using a time sequence analysis and regression analysis method so as to predict future demand conditions and adjust a scheduling plan of the vehicle according to the future demand conditions;
the time sequence analysis and regression analysis method comprises the following steps:
preprocessing time series data of historical order quantity and passenger flow data, wherein the preprocessing comprises one or more of data deduplication, time series set division, data type conversion, missing value filling, time series feature extraction, time series feature construction, independent heat coding and data fusion;
inputting the time series data of the historical order quantity and the passenger flow volume data into a preset analysis prediction model, wherein the method comprises the following steps of:
inputting the preprocessed time series data into the preset analysis prediction model;
acquiring time sequence data of historical order quantity and passenger flow volume data, wherein the time sequence data comprises one or more of a central processing unit utilization rate time sequence, a memory utilization rate time sequence, an average input/output request time sequence, a network card receiving byte number per second time sequence and a network card transmitting byte number per second time sequence;
inputting the time series data of the historical order quantity and the passenger flow volume data into a preset analysis prediction model, wherein the preset analysis prediction model is obtained through training of the time series data of a reference server and a critical value corresponding to the time series data of the reference server at preset time, and the critical value comprises a maximum value and/or a minimum value;
obtaining a prediction critical value of the time series data of the historical order quantity and the passenger flow volume data according to the output of the preset analysis prediction model;
step five, real-time scheduling: and the algorithm is applied to a taxi dispatching system to realize real-time route planning.
2. The driver interface single-route planning method based on the taxi order and the GPS data according to claim 1, wherein: in the first step, historical order data and real-time GPS data are collected through a taxi terminal device, and taxi related driver and vehicle information comprises any one or more of license plate numbers, vehicle types, colors, gender of drivers, age and academic; collecting position information, speed, head direction and running track of the vehicle through GPS equipment installed on the vehicle; meanwhile, collecting information of the time and place of getting on and off the passenger through a sensor connected with the price meter; finally, the data are collected through network equipment connected with a dispatching center.
3. The driver interface single-route planning method based on the taxi order and the GPS data according to claim 1, wherein: in the second step, preprocessing the collected data, including de-duplication, cleaning and normalization;
grouping orders according to OD requirements by using a clustering algorithm;
calculating the total order area demand and distribution according to the grouping result; processing and resolving a large amount of historical order data and real-time GPS data using artificial intelligence techniques to provide accurate data support for route planning algorithms; meanwhile, the behavior of the driver is identified and analyzed by using a computer vision technology and a natural language processing technology so as to know the driving habit and the order taking tendency of the driver;
and provides personalized services and route planning schemes according to driving habits and order taking trends.
4. A driver interface single-pass planning method based on a taxi order and GPS data according to claim 3, wherein: in step two, the artificial intelligence technique includes:
acquiring each order;
randomly selecting an order from all orders to serve as an initial clustering center;
selecting a plurality of orders from other orders to serve as other clustering centers according to order information of each order, the initial clustering center and the number of order groups, wherein the order similarity among the orders serving as the clustering centers is the smallest, the order similarity among the orders is determined according to the order information, and the order information at least comprises: end position, initial position, pick-up distance and predicted delivery time;
clustering the ungrouped orders according to the order information of the ungrouped orders and the determined clustering centers, and determining the order groups in a parallel order determining mode;
for each order group, determining at least one pick-up and delivery capacity corresponding to the order group;
and carrying out order distribution according to the matching degree of the orders in the order group and the pick-up and delivery capacity corresponding to the order group.
5. A driver interface single-pass planning method based on a taxi order and GPS data according to claim 3, wherein: the clustering algorithm comprises the following steps:
acquiring travel demand data of a user;
clustering is carried out according to the travel demand data, and a travel demand cluster is determined;
determining a demand cluster distance matrix according to the travel demand clusters, including:
determining a representative OD of each travel demand cluster according to the travel demand clusters;
determining the position distance dissimilarity and the direction distance dissimilarity among the plurality of representative ODs, wherein the position distance dissimilarity is determined according to the head-tail distances among the plurality of representative ODs, and the direction distance dissimilarity is determined according to the included angles among the plurality of representative ODs and the length proportion;
performing weighted calculation according to the position distance dissimilarity degree and the direction distance dissimilarity degree, determining the distances among a plurality of representative ODs, and generating the demand cluster distance matrix;
and carrying out secondary clustering according to the demand cluster distance matrix, and determining demand subareas, wherein each demand subarea comprises a plurality of OD (optical density) with similar positions and directions.
6. The driver interface single-route planning method based on the taxi order and the GPS data according to claim 1, wherein: in the third step, the different heat vectors are respectively a low-level heat vector, a medium-level heat vector and a high-level heat vector.
7. The driver interface single-route planning method based on the taxi order and the GPS data according to claim 1, wherein: in step five, a route planning algorithm is applied to the taxi dispatching system to realize real-time route planning, and the operation plan of the vehicle is adjusted according to the prediction result, so that personalized service and route planning schemes are provided to adapt to the needs of users and the changes of traffic conditions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310967105.3A CN116682254B (en) | 2023-08-03 | 2023-08-03 | Single-route-taking planning method for driver based on taxi order and GPS data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310967105.3A CN116682254B (en) | 2023-08-03 | 2023-08-03 | Single-route-taking planning method for driver based on taxi order and GPS data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116682254A CN116682254A (en) | 2023-09-01 |
| CN116682254B true CN116682254B (en) | 2023-10-20 |
Family
ID=87785878
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310967105.3A Active CN116682254B (en) | 2023-08-03 | 2023-08-03 | Single-route-taking planning method for driver based on taxi order and GPS data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116682254B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016023435A1 (en) * | 2014-08-12 | 2016-02-18 | 北京东方车云信息技术有限公司 | Taxi operating area familiarity-based dispatching system and method in online taxi hiring |
| CN109978193A (en) * | 2017-12-28 | 2019-07-05 | 北京嘀嘀无限科技发展有限公司 | Network about vehicle order allocation method and device |
| CN110807921A (en) * | 2019-10-24 | 2020-02-18 | 上海钧正网络科技有限公司 | Vehicle scheduling method, device, equipment and storage medium |
| CN111862579A (en) * | 2020-06-10 | 2020-10-30 | 深圳大学 | Taxi scheduling method and system based on deep reinforcement learning |
| CN114862209A (en) * | 2022-05-12 | 2022-08-05 | 阿波罗智联(北京)科技有限公司 | Transport capacity scheduling method and device, electronic equipment and storage medium |
| CN115759660A (en) * | 2022-11-24 | 2023-03-07 | 广州文远知行科技有限公司 | Scheduling method, device, equipment and medium for unmanned vehicle |
| CN116151598A (en) * | 2023-04-20 | 2023-05-23 | 武汉嘉联瑞通应用科技有限公司 | Intelligent bus balanced scheduling method and system based on passenger flow synchronous optimization |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2535718A (en) * | 2015-02-24 | 2016-08-31 | Addison Lee Ltd | Resource management |
| CN112041858A (en) * | 2018-05-22 | 2020-12-04 | 北京嘀嘀无限科技发展有限公司 | System and method for providing travel advice |
| JP7310764B2 (en) * | 2020-09-11 | 2023-07-19 | トヨタ自動車株式会社 | Vehicle allocation system, vehicle allocation server, and vehicle allocation method |
-
2023
- 2023-08-03 CN CN202310967105.3A patent/CN116682254B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016023435A1 (en) * | 2014-08-12 | 2016-02-18 | 北京东方车云信息技术有限公司 | Taxi operating area familiarity-based dispatching system and method in online taxi hiring |
| CN109978193A (en) * | 2017-12-28 | 2019-07-05 | 北京嘀嘀无限科技发展有限公司 | Network about vehicle order allocation method and device |
| CN110807921A (en) * | 2019-10-24 | 2020-02-18 | 上海钧正网络科技有限公司 | Vehicle scheduling method, device, equipment and storage medium |
| CN111862579A (en) * | 2020-06-10 | 2020-10-30 | 深圳大学 | Taxi scheduling method and system based on deep reinforcement learning |
| CN114862209A (en) * | 2022-05-12 | 2022-08-05 | 阿波罗智联(北京)科技有限公司 | Transport capacity scheduling method and device, electronic equipment and storage medium |
| CN115759660A (en) * | 2022-11-24 | 2023-03-07 | 广州文远知行科技有限公司 | Scheduling method, device, equipment and medium for unmanned vehicle |
| CN116151598A (en) * | 2023-04-20 | 2023-05-23 | 武汉嘉联瑞通应用科技有限公司 | Intelligent bus balanced scheduling method and system based on passenger flow synchronous optimization |
Non-Patent Citations (1)
| Title |
|---|
| 考虑实时单与预约单协同优化的出租汽车调度算法研究;王爽;《中国优秀硕士学位论文全文数据库 (工程科技Ⅱ辑)》(第03期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116682254A (en) | 2023-09-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Golbabaei et al. | The role of shared autonomous vehicle systems in delivering smart urban mobility: A systematic review of the literature | |
| CN108242149B (en) | Big data analysis method based on traffic data | |
| Ma et al. | Development of a data-driven platform for transit performance measures using smart card and GPS data | |
| Yuan et al. | Where to find my next passenger | |
| CN103177575B (en) | System and method for dynamically optimizing online dispatching of urban taxies | |
| CN110491158B (en) | Bus arrival time prediction method and system based on multi-metadata fusion | |
| CN106777703A (en) | A kind of bus passenger real-time analyzer and its construction method | |
| Pernestål et al. | Effects of driverless vehicles: Comparing simulations to get a broader picture | |
| Ionita et al. | Where to park? predicting free parking spots in unmonitored city areas | |
| CN113538067B (en) | Inter-city network vehicle-closing demand prediction method and system based on machine learning | |
| CN110598917B (en) | Destination prediction method, system and storage medium based on path track | |
| CN111914940B (en) | Shared vehicle station clustering method, system, device and storage medium | |
| CN115790636A (en) | Unmanned retail vehicle cruise path planning method and device based on big data | |
| Xu et al. | Dynamic bicycle scheduling problem based on short-term demand prediction | |
| Wu et al. | Predicting peak load of bus routes with supply optimization and scaled Shepard interpolation: A newsvendor model | |
| Ma et al. | Public transportation big data mining and analysis | |
| Aemmer et al. | Measurement and classification of transit delays using GTFS-RT data | |
| CN111723871B (en) | Estimation method for real-time carriage full load rate of bus | |
| CN116682254B (en) | Single-route-taking planning method for driver based on taxi order and GPS data | |
| CN106682759B (en) | Battery supply system for electric taxi and network optimization method | |
| CN112767685A (en) | Public transport passenger flow analysis system based on positioning and card swiping information | |
| CN114078322A (en) | Bus running state evaluation method, device, equipment and storage medium | |
| Ruch et al. | The impact of fleet coordination on taxi operations | |
| CN103236180B (en) | A kind of Vehicular information interactive interface method | |
| Link et al. | Combining GPS tracking and surveys for a mode choice model: Processing data from a quasi-natural experiment in Germany |
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 |