CN113095636B - Intelligent scheduling system and method for fuel sharing automobile - Google Patents
Intelligent scheduling system and method for fuel sharing automobile Download PDFInfo
- Publication number
- CN113095636B CN113095636B CN202110318712.8A CN202110318712A CN113095636B CN 113095636 B CN113095636 B CN 113095636B CN 202110318712 A CN202110318712 A CN 202110318712A CN 113095636 B CN113095636 B CN 113095636B
- Authority
- CN
- China
- Prior art keywords
- information
- vehicle
- scheduling
- website
- 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
- 238000000034 method Methods 0.000 title claims abstract description 30
- 239000000446 fuel Substances 0.000 title claims abstract description 14
- 238000012423 maintenance Methods 0.000 claims abstract description 50
- 238000012549 training Methods 0.000 claims abstract description 47
- 230000002776 aggregation Effects 0.000 claims abstract description 15
- 238000004220 aggregation Methods 0.000 claims abstract description 15
- 238000012545 processing Methods 0.000 claims description 32
- 238000004891 communication Methods 0.000 claims description 7
- 238000010801 machine learning Methods 0.000 claims description 7
- 238000001556 precipitation Methods 0.000 claims description 6
- 230000007613 environmental effect Effects 0.000 claims description 5
- 230000006870 function Effects 0.000 claims description 3
- 238000006116 polymerization reaction Methods 0.000 claims description 2
- 238000006243 chemical reaction Methods 0.000 abstract description 3
- 239000003921 oil Substances 0.000 description 16
- 239000010410 layer Substances 0.000 description 13
- 238000010586 diagram Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- PHIQHXFUZVPYII-UHFFFAOYSA-N carnitine Chemical compound C[N+](C)(C)CC(O)CC([O-])=O PHIQHXFUZVPYII-UHFFFAOYSA-N 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 239000000295 fuel oil Substances 0.000 description 2
- 230000000977 initiatory effect Effects 0.000 description 2
- 230000007306 turnover Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013047 polymeric layer Substances 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
Classifications
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
-
- 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
- G06Q10/20—Administration of product repair or maintenance
-
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0645—Rental transactions; Leasing transactions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/51—Discovery or management thereof, e.g. service location protocol [SLP] or web services
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Quality & Reliability (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Finance (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an intelligent scheduling system of a fuel sharing automobile, which comprises an App module, an intelligent scheduling micro-service module, an aggregation layer module and an order prediction module, wherein operation and maintenance personnel do not need to rely on past working experience, do not need to wait for management personnel to send scheduling instructions, only need to execute according to intelligent scheduling tasks pushed by a system received by the App module of a handheld terminal, and are simple and efficient. Meanwhile, the intelligent scheduling method is also disclosed, and the model training algorithm in the intelligent scheduling method can automatically and rapidly predict the order quantity information of the vehicle taking and returning of each website in three hours in the future, so that the scheduling work of a corresponding type is conveniently executed, the average order conversion time length can be reduced, and the management and training cost of enterprises to operation and maintenance personnel is further reduced.
Description
Technical Field
The invention relates to the technical field of shared automobiles, in particular to an intelligent scheduling system and method of a fuel oil shared automobile.
Background
At present, domestic fuel sharing automobiles mainly depend on operation and maintenance personnel familiar with site distribution in daily scheduling operation, scheduling is implemented according to working experience accumulated throughout the year, and peak and trough of demand of the site automobiles are judged to be dependent on experience of people, and additionally, the quantity of fuel automobiles, the number of overstocked sites (the limit of the quantity of the fuel automobiles for taking and parking is more relaxed compared with that of electric automobiles) are required to be comprehensively judged, so that a great number of customers concentrate one site to return the automobiles easily, especially the sites near schools), the idle parking time of the automobiles, whether cross-region scheduling is required or not and other factors are easily caused, and as urban operation vehicles and sites are continuously increased, the time efficiency is poor, the experience replicability is poor, and a great deal of invalid scheduling is caused, so that extra oil consumption and manpower resources are also generated, the operation cost of enterprises is greatly wasted, and social public resources are also wasted to a certain extent.
Disclosure of Invention
The invention aims to provide an intelligent dispatching system and method for a fuel sharing automobile, which are used for solving the problems that the fuel sharing automobile has poor timeliness, dispatching experience can not be quickly copied, the enterprise operation cost is too high caused by manual dispatching and the like in the process of manually initiating dispatching instructions.
In order to achieve the above purpose, the following technical scheme is adopted:
an intelligent scheduling system for a fuel sharing vehicle, comprising:
app module: the intelligent scheduling micro-service module is in communication connection with the intelligent scheduling micro-service module and is used for logging in by an operation and maintenance person to get the scheduling task and sending a request of the operation and maintenance person for getting the scheduling task and current real-time position information to the intelligent scheduling micro-service module;
intelligent scheduling micro-service module: is used for acquiring basic configuration information of the intelligent scheduling system from a database after receiving a request for acquiring the scheduling task sent by an operation and maintenance personnel, and sending a request for acquiring real-time operation information of each website on the periphery of the operation and maintenance personnel and real-time running information of the vehicle to the aggregation layer module;
and (3) a polymerization layer module: the intelligent scheduling micro-service module is in communication connection with each website and each shared automobile, and is used for acquiring real-time operation information of each website and real-time running information of the vehicle and returning the real-time operation information of the vehicle to the intelligent scheduling micro-service module;
order prediction module: the intelligent scheduling micro-service module is used for predicting the order quantity information of the vehicle taking and returning of each website in three hours in the future through an internal model training algorithm, and returning the information to the intelligent scheduling micro-service module so as to integrate the real-time operation information of the website on the periphery of the operation and maintenance personnel and the real-time running information of the vehicle, which are acquired before, and plan out the specific content information of the intelligent scheduling task matched with the current position of the operation and maintenance personnel, and return the specific content information to the App module.
Further, the basic configuration information includes: the method comprises the steps of scheduling a work type, a low-oil processing threshold preset by different vehicle types in each city, a distance range control threshold between people and network points in each city and between network points, a vehicle idle processing threshold preset in each city, a network point charging type, network point parking space quantity information and an over-high threshold and an over-low threshold of the overall vehicle quantity of a sheet zone formed by a plurality of network points.
Further, the real-time operation information includes: the vehicle in-out quantity information of each website, the residence time information of the vehicle at the website and the real-time inventory information of each website.
Further, the aggregation layer module is connected with OBD equipment of the shared automobile, and the aggregation layer module acquires real-time running information of the automobile through the OBD equipment.
Further, the real-time traveling information of the vehicle includes real-time position information of the vehicle and real-time remaining oil amount information of the vehicle.
The intelligent scheduling method of the fuel sharing automobile comprises the following steps:
s1: an operation and maintenance person sends a request for picking up a dispatching task to an intelligent dispatching micro-service module through an App module;
s2: the intelligent dispatching micro-service module acquires basic configuration information of an intelligent dispatching system from the database, and acquires real-time operation information of each website and real-time running information of vehicles from the aggregation layer module;
s3: the intelligent scheduling micro-service module calls an order prediction module to predict order quantity information of vehicle taking and vehicle returning of each website in three hours in the future based on a model training algorithm in the intelligent scheduling micro-service module, and returns the information to the intelligent scheduling micro-service module;
s4: the intelligent scheduling micro-service module synthesizes the various information acquired by the S2 and the S3, plans out the specific content information of the intelligent scheduling task matched with the current position of the operation and maintenance personnel, and returns the specific content information to the App module;
s5: and the operation and maintenance personnel implement specific scheduling work according to the acquired specific content information of the intelligent scheduling task.
Further, the model training algorithm in S3 includes the following steps:
s31: acquiring training data information;
s32: storing and processing the training data information acquired in the step S31;
s33: and (3) performing machine learning training based on the data information processed in the step (S32), acquiring a preliminary training model, and adjusting model parameters through grid searching, so as to predict order quantity information of vehicle taking and vehicle returning of each website in three hours in the future based on the trained model.
Further, the training data information in S31 includes:
site history order information: the method comprises the steps of sharing the vehicle taking and returning order quantity of the vehicle at any time in the history of the website where the vehicle is located;
dot information: the method comprises the steps of including site geographic feature information, site real-time inventory information and site active user quantity information;
environmental information: including historical weather, air temperature and precipitation information;
special event information: including marketing campaign information held prior to the website.
Further, the processing the training data information in S32 includes: null value processing, sample noise point removing processing and characteristic engineering processing.
By adopting the scheme, the invention has the beneficial effects that:
1) The system comprises an App module, an intelligent scheduling micro-service module, an aggregation layer module and an order prediction module, so that operation and maintenance personnel do not need to rely on past working experience, do not need to wait for a manager to send scheduling instructions, and only need to execute according to intelligent scheduling tasks pushed by a system and received by the App module of the handheld terminal, thereby being simple and efficient;
2) Compared with a scheduling instruction sent by a manager, by using the system, the use of human resources can be reduced, invalid scheduling is reduced, and the operation cost is further reduced;
3) The model training algorithm in the intelligent scheduling method can automatically and rapidly predict the order quantity information of the vehicle taking and returning of each website in three hours in the future, so that the scheduling work of the corresponding type is conveniently executed, the average order conversion time length can be reduced, and the management and training cost of enterprises to operation and maintenance personnel is further reduced.
Drawings
FIG. 1 is a schematic block diagram of the present invention;
FIG. 2 is a flow chart diagram of the intelligent scheduling method of the present invention;
FIG. 3 is a logic flow diagram of a model training algorithm of the present invention;
wherein, the attached drawings mark and illustrate:
1-App module; 2-intelligent scheduling micro-service module;
3-a polymeric layer module; 4-order prediction module.
Detailed Description
The invention will be described in detail below with reference to the drawings and the specific embodiments.
Referring to fig. 1, the present invention provides an intelligent scheduling system for a fuel-sharing vehicle, including:
app module 1: the intelligent scheduling micro-service module 2 is in communication connection with the intelligent scheduling micro-service module 2 and is used for logging in by an operation and maintenance person to get the scheduling task and sending a request of the operation and maintenance person to get the scheduling task and current real-time position information to the intelligent scheduling micro-service module 2;
intelligent scheduling microservice module 2: the system is used for acquiring basic configuration information of the intelligent scheduling system from a database after receiving a request for acquiring scheduling tasks sent by operation and maintenance personnel, and sending a request for acquiring real-time operation information of each website on the periphery of the operation and maintenance personnel and real-time running information of vehicles to the aggregation layer module 3;
polymerized layer module 3: the intelligent scheduling micro-service module 2 is in communication connection with each website and each shared automobile, and is used for acquiring real-time operation information of each website and real-time running information of the vehicle and returning the real-time operation information of the vehicle to the intelligent scheduling micro-service module 2;
order prediction module 4: the intelligent scheduling micro-service module 2 is used for predicting the order quantity information of the vehicle taking and returning of each website in three hours in the future through an internal model training algorithm, and returning the information to the intelligent scheduling micro-service module 2 so as to integrate the real-time operation information of the website on the periphery of the operation and maintenance personnel and the real-time running information of the vehicle, which are acquired before, and plan out the specific content information of the intelligent scheduling task matched with the current position of the operation and maintenance personnel, and return the specific content information to the App module 1.
Wherein the basic configuration information includes: the method comprises the steps of scheduling a work type, a low-oil processing threshold preset by different vehicle types in each city, a distance range control threshold between people and network points in each city and between network points, a vehicle idle processing threshold preset in each city, a network point charging type, network point parking space quantity information, and an over-high threshold and an over-low threshold of the overall vehicle quantity of a sheet zone formed by a plurality of network points; the real-time operation information includes: the vehicle in-out quantity information of each website, the residence time information of the vehicle at the website and the real-time inventory information of each website; the aggregation layer module 3 is connected with OBD equipment of the shared automobile, and acquires real-time running information of the automobile through the OBD equipment; the real-time traveling information of the vehicle includes real-time position information of the vehicle and real-time remaining oil amount information of the vehicle.
Referring to fig. 2 to 3, there is also provided an intelligent scheduling method of a fuel sharing vehicle, including the steps of:
s1: the operation and maintenance personnel send a request for picking up the dispatching task to the intelligent dispatching micro-service module 2 through the App module 1;
s2: the intelligent scheduling micro-service module 2 acquires basic configuration information of an intelligent scheduling system from a database, and acquires real-time operation information of each website and real-time running information of a vehicle from the aggregation layer module 3;
s3: the intelligent scheduling micro-service module 2 calls an order prediction module 4 to predict order quantity information of taking and returning vehicles of each website in three hours in the future based on a model training algorithm in the intelligent scheduling micro-service module, and returns the information to the intelligent scheduling micro-service module 2;
s4: the intelligent scheduling micro-service module 2 synthesizes the various information acquired by the S2 and the S3, plans out the specific content information of the intelligent scheduling task matched with the current position of the operation and maintenance personnel, and returns the specific content information to the App module 1;
s5: and the operation and maintenance personnel implement specific scheduling work according to the acquired specific content information of the intelligent scheduling task.
Further, the model training algorithm in S3 includes the following steps:
s31: acquiring training data information;
s32: storing and processing the training data information acquired in the step S31;
s33: and (3) performing machine learning training based on the data information processed in the step (S32), acquiring a preliminary training model, and adjusting model parameters through grid searching, so as to predict order quantity information of vehicle taking and vehicle returning of each website in three hours in the future based on the trained model.
Wherein, the training data information in S31 includes:
site history order information: the method comprises the steps of sharing the vehicle taking and returning order quantity of the vehicle at any time in the history of the website where the vehicle is located;
dot information: the method comprises the steps of including site geographic feature information, site real-time inventory information and site active user quantity information;
environmental information: including historical weather, air temperature and precipitation information;
special event information: including marketing campaign information held prior to the website.
The processing of the training data information in S32 includes: null value processing, sample noise point removing processing and characteristic engineering processing.
The working principle of the invention is as follows:
with continued reference to fig. 1 to 3, in this embodiment, the intelligent scheduling system includes an App module 1, an intelligent scheduling micro-service module 2, an aggregation layer module 3 and an order prediction module 4, where the App module 1 is installed on a handheld terminal (smart phone, etc.) device on an operation and maintenance person, and the operation and maintenance person can log in the system through the App module 1 and claim a scheduling task on a workbench interface in the App module 1; meanwhile, an intelligent scheduling method is provided, and referring to fig. 1 to 3, the method generally comprises the following steps:
1) The operation and maintenance personnel send a request for asking for a dispatching task to the intelligent dispatching micro-service module 2 through the App module 1, and the App module 1 sends the current real-time position information of the operation and maintenance personnel and a request instruction for getting the dispatching task to the intelligent dispatching micro-service module 2 at the background server side;
2) After receiving the request for picking up the scheduling task, the intelligent scheduling micro-service module 2 obtains basic configuration information of the intelligent scheduling system from a database, wherein the basic configuration information comprises: the method comprises the steps of scheduling work types, low-oil processing thresholds preset by different vehicle types in each city, distance range control thresholds between people and nodes in each city and between nodes, vehicle idle processing thresholds preset in each city, node charging types (charging or free), node parking space quantity information, and overall vehicle quantity too high threshold and too low threshold (used for triggering cross-chip area scheduling) of a chip area formed by a plurality of nodes;
3) The intelligent scheduling micro-service module 2 acquires basic configuration information of the system and simultaneously sends a request for acquiring real-time operation information of each website on the periphery of an operation and maintenance person and real-time running information of a vehicle to the aggregation layer module 3;
4) The aggregation layer module 3 is in communication connection with each website and an OBD device (on-board automatic diagnosis system) on the shared automobile, and returns the real-time operation information of each website and the real-time running information of the vehicle on the periphery of the operation and maintenance personnel to the intelligent scheduling micro-service module 2 after the real-time operation information of the vehicle is acquired according to the position information of the operation and maintenance personnel, wherein the real-time running information of the vehicle comprises the real-time position information of the vehicle and the real-time residual oil quantity information of the vehicle, and the real-time operation information of the website comprises: the vehicle in-out quantity information of each website, the residence time information of the vehicle at the website and the real-time inventory information of each website;
5) After the intelligent scheduling micro-service module 2 acquires the information, an order prediction module 4 is called;
6) The order prediction module 4 predicts and returns results through its internal model training algorithm, the results of which include: order quantity information of picking up and returning vehicles in the future 3 hours at each website;
7) The intelligent scheduling micro-service module 2 integrates the obtained information, namely, integrates the supply and demand situation of surrounding network points and the real-time state of vehicles at the nearby network points, plans out the optimal scheduling task at the position of the operation and maintenance personnel initiating the request in the step (1), and returns the task content to the App module 1;
8) After acquiring intelligent scheduling tasks generated by system recommendation from the App module 1, the operation and maintenance personnel implement specific vehicle scheduling work.
The model training algorithm in the order prediction module 4 in the system is the core of the system, and is that the optimal scheduling strategy of people and vehicles is provided by cleaning and characterizing historical vehicle returning data of each website, realizing prediction of the returning vehicle demand of each website in a specific future time range and generating scheduling demands through training of a machine learning model, and integrating correction demands of fuel oil quantity, vehicle idle time, website inventory distribution of each area, employee position and the like; specifically:
referring to fig. 3, the requirement of predicting the order taking and returning of the website is that the order taking and returning of the user within 3 hours in the future of the website is predicted and output by taking hours as dimensions, a regression type machine learning algorithm is adopted, a specifically used algorithm frame is XGBoost (which is a distributed gradient lifting library and provides a set of extreme gradient lifting algorithm frames and is used for training a prediction model), in order to obtain the optimal prediction result, a target loss function is constructed, and then the function takes a minimum value, so that model parameters of the machine learning algorithm are obtained; the sources of training data information mainly include the following 4 aspects:
1) Site history order information, referring to table 1, contains the pick-up and return vehicle order quantity at any moment of site history of the shared vehicle;
2) Dot information, referring to table 2, including dot geographic feature information, historical dot inventory information at any time, and dot active user number information;
3) Environmental information, referring to table 3, including weather, air temperature, and precipitation condition information at any time of history;
4) Special event information, referring to table 4, including historical significant events of each website and held marketing campaign information;
| column name | Language description | Data type | Examples of the invention |
| park_no | Dot number | varchar(8) | 1010 |
| city_id | City numbering | varchar(8) | 400300 |
| trans_date | Transaction date | date | 2020-01-01 |
| trans_hour | Transaction time | tinyint(2) | 10 |
| is_holiday | Whether or not to use holidays | char(1) | Y，N |
| week | Day of the week | tinyint(1) | 1 |
| take_car_num | Order quantity of taking car | tinyint(10) | 5 |
| back_car_num | Order quantity of returning vehicles | tinyint(10) | 3 |
Table 1 dot hourly order structure table
| Column name | Language description | Data type | Examples of the invention |
| park_no | Dot number | varchar(8) | 1010 |
| city_id | City numbering | varchar(8) | 400300 |
| record_date | Recording date | date | 2020-01-01 |
| record_hour | Recording time | tinyint(2) | 10 |
| point_car_nums | Vehicle inventory at point of sale | tinyint(10) | 5 |
| near_user_nums | Net pointActive user at moment | tinyint(10) | 1321 |
| feature | Dot characteristics | varchar(8) | 1: quotient excess, 2: railway station … |
TABLE 2 dot information Structure Table
| Column name | Language description | Data type | Examples of the invention |
| city_id | City numbering | varchar(8) | 400300 |
| record_date | Recording date | date | 2020-01-01 |
| record_hour | Recording time | tinyint(2) | 10 |
| temperature | Temperature at moment | tinyint(4) | 5 |
| precipitation | Precipitation (unit mm) | float(3，1) | 3.8mm |
| weather_type | Weather type | tinyint(2) | 1: light rain, 2: clouds … |
Table 3 environmental information structure table
TABLE 4 Special event Structure List
The management of the training data information adopts the combination of a relational database (MySQL) and a non-relational database (elastic search), and selects different types of databases for data magnitude storage, wherein the data processing of the mentioned training data comprises the following steps: null value processing, sample noise point removing and characteristic engineering (part of characteristic value attribute adopts one-hot coding), then machine learning training is carried out by utilizing processed data, grid searching is carried out to adjust model parameters, and finally predicted future vehicle taking and vehicle returning order quantity of different net points at specific moment is obtained by using a trained model.
When a shared automobile is specifically scheduled, the shared automobile is firstly classified into three types according to the scheduling work actually happening daily by the shared automobile:
1) Low oil treatment (residual oil amount is lower than a preset threshold);
2) Idle processing (the vehicle is parked at a website for too long a period of time without an order being generated during the period);
3) Vehicle lack handling (vehicle inventory at a website cannot meet the demand for vehicles for several hours in the future);
aiming at the three types of dispatching work, the basis of judgment is decomposed, and the vehicle shortage processing is to synthesize real-time inventory in the network after the network prediction order result is obtained, so that whether the network needs to call in for vehicle shortage or not can be directly judged; the low oil treatment is to report the longitude and latitude of the vehicle in real time by means of the shared vehicle-mounted OBD equipment so as to obtain the position information of the vehicle and the residual oil quantity information of the oil cylinder; when the network points are divided, the electronic fence is preset, that is, a virtual fence is formed by drawing a plurality of coordinates around the network point parking lot, and the virtual fence is stored in a solr search engine to judge whether the vehicle is in the network point or not and the parking time of the vehicle in the same network point (the idle time of the vehicle can be calculated), the number of the parked vehicles in the network point (network point inventory) can be calculated, in addition, the network points with the positions belonging to the same area can be combined into a piece area according to the administrative area of the city, the management of the piece area is convenient, and the available vehicle number and the residual vehicle number of the whole piece area are counted.
In this embodiment, on the basis of the principle of highest current efficiency, when an operator demands a task through an App module 1, the system finds out whether a network point needing to process low oil or idle vehicles exists nearby according to the latest position of the operator, and matches the network point nearby to be called out, and the system matches the network point nearby according to a preset priority, wherein the priority refers to just the above, and different priority orders can be configured according to different patches and different time periods according to three task types divided by scheduling work; when operation and maintenance personnel get the task, when the system inquires that the surrounding low-oil vehicles or idle vehicles do not need to be called, but the system can match the recommended call-out net points according to a scoring rule when the net points needing to be called-in of the lack vehicles exist, wherein the scoring rule comprises two parts, namely a first-order scoring and a step scoring.
The dimension of the first-order score is as follows: the real-time vehicle number (i.e. real-time inventory) of the call-out net point, the future vehicle taking amount and the vehicle returning amount of a plurality of hours of the call-out net point can be included in the range of the recommended call-out net point only when the inventory of the call-out net point can meet the requirement of the current net point for a plurality of hours, the step-in grading is carried out according to the single grading of each dimension and a weighting algorithm is used, the net point with the highest grading is the call-out net point finally recommended by the system, and the dimension of the step-in grading is as follows: the method comprises the steps of calling out a distance from a call-in net point (the closer the distance is, the higher the single score is), the distance between an operation and maintenance person and the call-out net point (the closer the distance is, the higher the single score is), the quantity of the inventory of the call-out net point exceeding the requirement of a plurality of hours in the future per se (the higher the number of the call-out net point is, the higher the single score is), net point idle time, net point daily average single quantity, turnover rate (wherein the net point idle time, daily average single quantity and turnover rate are indexes for measuring the whole order quantity of a net point, the worse the single score is, the higher the indexes are), the score and weight proportion can be preset for each dimension of the step score, and the system automatically calculates the scores of the net points in the process of generating a task.
In addition, the above-mentioned dispatching work, such as low-oil processing and idle processing, is dispatching work with operation and maintenance personnel as the center and circulated in the area, and in addition, there are some dispatching works needing global regulation, such as overdrawing dispatching and cross-area dispatching, the system can monitor the available vehicle number of each network point and the available vehicle number of the whole area in real time, for the overdrawing number of a single network point, the system can search whether operation and maintenance personnel in a working state exist within the radius of 3 km range with the overdrawing network point as the center, and then match whether network points suitable for dispatching exist within the radius of 10 km range with the overdrawing network point as the center, wherein the network points suitable for dispatching include the remaining available vehicle number to be greater than 2, or the network points suitable for dispatching network point are not enough in stock, or the network points needing dispatching to replace idle and low-oil vehicles exist; aiming at the situation that the number of vehicles in the whole area exceeds a preset threshold, the system can be matched with other areas with the number of vehicles lower than the preset threshold, and corresponding cross-area dispatching tasks are generated, namely, dispatching out of the net points in the areas with the number of vehicles exceeding the threshold and dispatching in the cross-area to the net points in the areas with the number of vehicles lower than the threshold, so that the goal of balancing the number of vehicles in the areas is achieved.
According to the scheduling system and the scheduling method, operation and maintenance personnel do not need to rely on past working experience, do not need to wait for management personnel to send scheduling instructions, and only need to execute the intelligent scheduling tasks according to the system pushing received by the App module 1 of the handheld terminal, compared with the scheduling instructions sent by the management personnel, the system is used, the order quantity can be predicted to be improved by more than 10% on the basis of the original order specification, invalid scheduling can be reduced by more than 20%, meanwhile, the order quantity predicted based on the method is used for taking and returning the vehicle order quantity, after the scheduling of the vehicle shortage type is executed, the average order conversion time is within 3 hours (after the scheduling of the operation and maintenance personnel is completed, the average time is 3 hours and the order quantity can be converted into an effective customer order), and meanwhile, the management and training cost of enterprises to the operation and maintenance personnel is reduced.
The foregoing description of the preferred embodiment of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (5)
1. An intelligent scheduling system for a fuel sharing vehicle, comprising:
app module: the intelligent scheduling micro-service module is in communication connection with the intelligent scheduling micro-service module and is used for logging in by an operation and maintenance person to get the scheduling task and sending a request of the operation and maintenance person for getting the scheduling task and current real-time position information to the intelligent scheduling micro-service module;
intelligent scheduling micro-service module: is used for acquiring basic configuration information of the intelligent scheduling system from a database after receiving a request for acquiring the scheduling task sent by an operation and maintenance personnel, and sending a request for acquiring real-time operation information of each website on the periphery of the operation and maintenance personnel and real-time running information of the vehicle to the aggregation layer module;
and (3) a polymerization layer module: the intelligent scheduling micro-service module is in communication connection with each website and each shared automobile, and is used for acquiring real-time operation information of each website and real-time running information of the vehicle and returning the real-time operation information of the vehicle to the intelligent scheduling micro-service module;
order prediction module: the method comprises the steps that the intelligent scheduling micro-service module is used for calling, order quantity information of vehicle taking and vehicle returning of each website in three hours in the future is predicted through a model training algorithm in the intelligent scheduling micro-service module, the information is returned to the intelligent scheduling micro-service module, so that real-time operation information of the website on the periphery of an operation and maintenance person and real-time running information of the vehicle, which are acquired before the intelligent scheduling micro-service module is integrated, specific content information of an intelligent scheduling task, which is matched with the current position of the operation and maintenance person, is planned, and the specific content information is returned to an App module; the basic configuration information includes: the method comprises the steps of scheduling a work type, a low-oil processing threshold preset by different vehicle types in each city, a distance range control threshold between people and network points in each city and between network points, a vehicle idle processing threshold preset in each city, a network point charging type, network point parking space quantity information, and an over-high threshold and an over-low threshold of the overall vehicle quantity of a sheet zone formed by a plurality of network points; the algorithm framework used by the model training algorithm is XGBoost, and a target loss function is constructed; sources of training data information of the model training algorithm comprise site history order information, site information, environment information and special event information; the model training algorithm combines a relational database and a non-relational database to manage training data information, and selects different types of databases for data magnitude and stores the data magnitude, wherein the training data information is also subjected to data processing; the data processing comprises null value processing, sample noise point removing and characteristic engineering; the intelligent scheduling task comprises low-oil treatment, idle treatment, vehicle-lack treatment, super-stop scheduling and cross-region scheduling; the super-stop scheduling means that the system monitors the available vehicle number of each website and the available vehicle number of the whole area in real time, and searches whether operation and maintenance personnel in a working state exist within a radius range of 3 km by taking the super-stop website as the center aiming at the excessive available vehicle number of the single website, and matches whether the website suitable for scheduling exists within the radius range of 10 km by taking the super-stop website as the center, wherein the website suitable for scheduling comprises more than 2 residual available vehicle numbers, or the scheduling website per se has insufficient inventory, or the website which needs scheduling in for replacing idle and low-oil vehicles exists; the cross-region scheduling refers to the situation that the number of vehicles in the whole region exceeds a preset threshold value, the system can be matched with other regions with the number of vehicles lower than the preset threshold value, then vehicles are scheduled out from the net points in the region with the number of vehicles exceeding the threshold value, and the cross-region scheduling is performed to the net points in the region with the number of vehicles lower than the threshold value.
2. The intelligent scheduling system of a fuel-sharing vehicle of claim 1, wherein the real-time operating information comprises: the vehicle in-out quantity information of each website, the residence time information of the vehicle at the website and the real-time inventory information of each website.
3. The intelligent scheduling system of a fuel-sharing vehicle of claim 1, wherein the aggregation layer module is connected to an OBD device of the sharing vehicle, and obtains real-time driving information of the vehicle through the OBD device.
4. The intelligent scheduling system of a fuel-sharing vehicle of claim 3, wherein the real-time travel information of the vehicle includes real-time location information of the vehicle and real-time remaining fuel amount information of the vehicle.
5. An intelligent scheduling method for fuel sharing automobiles is characterized by comprising the following steps:
s1: an operation and maintenance person sends a request for picking up a dispatching task to an intelligent dispatching micro-service module through an App module;
s2: the intelligent dispatching micro-service module acquires basic configuration information of an intelligent dispatching system from the database, and acquires real-time operation information of each website and real-time running information of vehicles from the aggregation layer module;
s3: the intelligent scheduling micro-service module calls an order prediction module to predict order quantity information of vehicle taking and vehicle returning of each website in three hours in the future based on a model training algorithm in the intelligent scheduling micro-service module, and returns the information to the intelligent scheduling micro-service module;
s4: the intelligent scheduling micro-service module synthesizes the various information acquired by the S2 and the S3, plans out the specific content information of the intelligent scheduling task matched with the current position of the operation and maintenance personnel, and returns the specific content information to the App module;
s5: the operation and maintenance personnel implement specific scheduling work according to the acquired specific content information of the intelligent scheduling task; the model training algorithm in S3 includes the following steps:
s31: acquiring training data information;
s32: storing and processing the training data information acquired in the step S31;
s33: performing machine learning training based on the data information processed in the step S32, acquiring a preliminary training model, and adjusting model parameters through grid searching, so as to predict order quantity information of vehicle taking and vehicle returning of each website in three hours in the future based on the trained model; the training data information in S31 includes:
site history order information: the method comprises the steps of sharing the vehicle taking and returning order quantity of the vehicle at any time in the history of the website where the vehicle is located; dot information: the method comprises the steps of including site geographic feature information, site real-time inventory information and site active user quantity information;
environmental information: including historical weather, air temperature and precipitation information;
special event information: including marketing campaign information held prior to the website; the processing of the training data information in S32 includes: null value processing, sample noise point removing processing and characteristic engineering processing; the intelligent scheduling task comprises low-oil treatment, idle treatment, vehicle-lack treatment, super-stop scheduling and cross-region scheduling; the super-stop scheduling means that the system monitors the available vehicle number of each website and the available vehicle number of the whole area in real time, and searches whether operation and maintenance personnel in a working state exist within a radius range of 3 km by taking the super-stop website as the center aiming at the excessive available vehicle number of the single website, and matches whether the website suitable for scheduling exists within the radius range of 10 km by taking the super-stop website as the center, wherein the website suitable for scheduling comprises more than 2 residual available vehicle numbers, or the scheduling website per se has insufficient inventory, or the website which needs scheduling in for replacing idle and low-oil vehicles exists; the cross-region scheduling refers to the situation that the number of vehicles in the whole region exceeds a preset threshold value, the system can be matched with other regions with the number of vehicles lower than the preset threshold value, then vehicles are scheduled out from the net points in the region with the number of vehicles exceeding the threshold value, and the cross-region scheduling is performed to the net points in the region with the number of vehicles lower than the threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110318712.8A CN113095636B (en) | 2021-03-25 | 2021-03-25 | Intelligent scheduling system and method for fuel sharing automobile |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110318712.8A CN113095636B (en) | 2021-03-25 | 2021-03-25 | Intelligent scheduling system and method for fuel sharing automobile |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113095636A CN113095636A (en) | 2021-07-09 |
| CN113095636B true CN113095636B (en) | 2024-01-23 |
Family
ID=76669516
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110318712.8A Active CN113095636B (en) | 2021-03-25 | 2021-03-25 | Intelligent scheduling system and method for fuel sharing automobile |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113095636B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115695139A (en) * | 2022-12-29 | 2023-02-03 | 安徽交欣科技股份有限公司 | Method for enhancing micro-service system architecture based on distributed robust |
Citations (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2001069488A1 (en) * | 2000-03-10 | 2001-09-20 | Jones Charles P | Vehicle scheduling system |
| CN105405213A (en) * | 2015-11-01 | 2016-03-16 | 泉州黄章智能科技有限公司 | Electric car intelligent renting system |
| CN105719019A (en) * | 2016-01-21 | 2016-06-29 | 华南理工大学 | Public bicycle peak time demand prediction method considering user reservation data |
| CN106372776A (en) * | 2016-08-19 | 2017-02-01 | 北京恒天易开科技股份有限公司 | Vehicle scheduling system and method for unattended rental points in electric vehicle rental industry |
| CN107424407A (en) * | 2017-08-21 | 2017-12-01 | 江苏萌小明智能科技有限公司 | A kind of vehicle dispatch system and vehicle scheduling scheme generation method |
| CN107563532A (en) * | 2017-08-30 | 2018-01-09 | 顾泰来 | A kind of shared vehicle dispatching method and device |
| CN107944780A (en) * | 2018-01-17 | 2018-04-20 | 上海钛捷信息科技有限公司 | A kind of vehicle scheduling platform and automobile leasing method based on automobile resources dynamic dispatching with distribution |
| CN108510729A (en) * | 2018-04-24 | 2018-09-07 | 徐漫洋 | Shared automobile scheduling system and dispatching method |
| CN108510730A (en) * | 2018-04-24 | 2018-09-07 | 徐漫洋 | Vehicle dispatching method and system between shared automobile site |
| CN108596484A (en) * | 2018-04-24 | 2018-09-28 | 徐漫洋 | A kind of shared Truck dispartching method and system based on site attributive analysis |
| CN108960632A (en) * | 2018-07-06 | 2018-12-07 | 深圳市有钱科技有限公司 | A kind of transregional dispatching method of shared bicycle |
| CN109360413A (en) * | 2018-12-11 | 2019-02-19 | 北京首汽智行科技有限公司 | A kind of vehicle dispatching method and system |
| CN110033161A (en) * | 2019-02-27 | 2019-07-19 | 山东开创云软件有限公司 | A kind of dispatching method and system of shared automobile |
| CN110220527A (en) * | 2019-05-31 | 2019-09-10 | 中国四维测绘技术有限公司 | A kind of paths planning method and device based on public activity prediction |
| CN110276557A (en) * | 2019-06-27 | 2019-09-24 | 四川首汽交投汽车共享科技有限公司 | A kind of inter-network grid dispatching work order creation method |
| CN111126740A (en) * | 2019-07-31 | 2020-05-08 | 北京嘀嘀无限科技发展有限公司 | Shared automobile charging scheduling method, electronic equipment and storage medium |
| CN111612183A (en) * | 2019-02-25 | 2020-09-01 | 北京嘀嘀无限科技发展有限公司 | Information processing method, information processing device, electronic equipment and computer readable storage medium |
| KR20200109427A (en) * | 2019-03-12 | 2020-09-23 | 주식회사 코어시스템즈 | Bus operation management method and system |
| CN111815095A (en) * | 2019-06-20 | 2020-10-23 | 北京嘀嘀无限科技发展有限公司 | Shared automobile scheduling method, electronic equipment and storage medium |
| CN111815937A (en) * | 2019-11-22 | 2020-10-23 | 北京嘀嘀无限科技发展有限公司 | Control method and device for dispatching of super-parking vehicles, storage medium and electronic equipment |
| CN111861080A (en) * | 2019-10-30 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Information processing method and device, electronic equipment and storage medium |
| CN111868763A (en) * | 2018-03-16 | 2020-10-30 | 福特汽车公司 | Optimizing and predicting resource availability in a shared vehicle environment |
| CN111862579A (en) * | 2020-06-10 | 2020-10-30 | 深圳大学 | Taxi scheduling method and system based on deep reinforcement learning |
| CN111882097A (en) * | 2019-10-11 | 2020-11-03 | 北京嘀嘀无限科技发展有限公司 | Vehicle maintenance personnel scheduling method and system |
| CN111915209A (en) * | 2020-08-11 | 2020-11-10 | 上海钧正网络科技有限公司 | Shared vehicle scheduling method and device, computer equipment and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10670411B2 (en) * | 2017-12-29 | 2020-06-02 | Lyft Inc. | Efficient matching of service providers and service requests across a fleet of autonomous vehicles |
-
2021
- 2021-03-25 CN CN202110318712.8A patent/CN113095636B/en active Active
Patent Citations (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2001069488A1 (en) * | 2000-03-10 | 2001-09-20 | Jones Charles P | Vehicle scheduling system |
| CN105405213A (en) * | 2015-11-01 | 2016-03-16 | 泉州黄章智能科技有限公司 | Electric car intelligent renting system |
| CN105719019A (en) * | 2016-01-21 | 2016-06-29 | 华南理工大学 | Public bicycle peak time demand prediction method considering user reservation data |
| CN106372776A (en) * | 2016-08-19 | 2017-02-01 | 北京恒天易开科技股份有限公司 | Vehicle scheduling system and method for unattended rental points in electric vehicle rental industry |
| CN107424407A (en) * | 2017-08-21 | 2017-12-01 | 江苏萌小明智能科技有限公司 | A kind of vehicle dispatch system and vehicle scheduling scheme generation method |
| CN107563532A (en) * | 2017-08-30 | 2018-01-09 | 顾泰来 | A kind of shared vehicle dispatching method and device |
| CN107944780A (en) * | 2018-01-17 | 2018-04-20 | 上海钛捷信息科技有限公司 | A kind of vehicle scheduling platform and automobile leasing method based on automobile resources dynamic dispatching with distribution |
| CN111868763A (en) * | 2018-03-16 | 2020-10-30 | 福特汽车公司 | Optimizing and predicting resource availability in a shared vehicle environment |
| CN108510729A (en) * | 2018-04-24 | 2018-09-07 | 徐漫洋 | Shared automobile scheduling system and dispatching method |
| CN108510730A (en) * | 2018-04-24 | 2018-09-07 | 徐漫洋 | Vehicle dispatching method and system between shared automobile site |
| CN108596484A (en) * | 2018-04-24 | 2018-09-28 | 徐漫洋 | A kind of shared Truck dispartching method and system based on site attributive analysis |
| CN108960632A (en) * | 2018-07-06 | 2018-12-07 | 深圳市有钱科技有限公司 | A kind of transregional dispatching method of shared bicycle |
| CN109360413A (en) * | 2018-12-11 | 2019-02-19 | 北京首汽智行科技有限公司 | A kind of vehicle dispatching method and system |
| CN111612183A (en) * | 2019-02-25 | 2020-09-01 | 北京嘀嘀无限科技发展有限公司 | Information processing method, information processing device, electronic equipment and computer readable storage medium |
| CN110033161A (en) * | 2019-02-27 | 2019-07-19 | 山东开创云软件有限公司 | A kind of dispatching method and system of shared automobile |
| KR20200109427A (en) * | 2019-03-12 | 2020-09-23 | 주식회사 코어시스템즈 | Bus operation management method and system |
| CN110220527A (en) * | 2019-05-31 | 2019-09-10 | 中国四维测绘技术有限公司 | A kind of paths planning method and device based on public activity prediction |
| CN111815095A (en) * | 2019-06-20 | 2020-10-23 | 北京嘀嘀无限科技发展有限公司 | Shared automobile scheduling method, electronic equipment and storage medium |
| CN110276557A (en) * | 2019-06-27 | 2019-09-24 | 四川首汽交投汽车共享科技有限公司 | A kind of inter-network grid dispatching work order creation method |
| CN111126740A (en) * | 2019-07-31 | 2020-05-08 | 北京嘀嘀无限科技发展有限公司 | Shared automobile charging scheduling method, electronic equipment and storage medium |
| CN111882097A (en) * | 2019-10-11 | 2020-11-03 | 北京嘀嘀无限科技发展有限公司 | Vehicle maintenance personnel scheduling method and system |
| CN111861080A (en) * | 2019-10-30 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Information processing method and device, electronic equipment and storage medium |
| CN111815937A (en) * | 2019-11-22 | 2020-10-23 | 北京嘀嘀无限科技发展有限公司 | Control method and device for dispatching of super-parking vehicles, storage medium and electronic equipment |
| CN111862579A (en) * | 2020-06-10 | 2020-10-30 | 深圳大学 | Taxi scheduling method and system based on deep reinforcement learning |
| CN111915209A (en) * | 2020-08-11 | 2020-11-10 | 上海钧正网络科技有限公司 | Shared vehicle scheduling method and device, computer equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 基于车联网环境的共享自动驾驶汽车调度研究;王睿;中国优秀硕士学位论文全文数据库工程科技Ⅱ辑(第2期);C034-703 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113095636A (en) | 2021-07-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109034566B (en) | A kind of intelligent dispatching method and device based on passenger flow above and below bus station | |
| CN110705747A (en) | Intelligent public transport cloud brain system based on big data | |
| US20190347582A1 (en) | Matching Drivers with Shared Vehicles to Optimize Shared Vehicle Services | |
| CN113557539A (en) | Method and system for converting physical movement into carbon units | |
| CN110033161A (en) | A kind of dispatching method and system of shared automobile | |
| CN109784523B (en) | Online taxi appointment intelligent order distribution method based on multi-objective optimization | |
| CN103278833A (en) | Line recommendation system and method based on Beidou satellite/GPS (global positioning system) data | |
| CN103632532A (en) | Taxi taxi-taking inducing method | |
| CN112801552A (en) | Traffic big data mining and intelligent analysis-based network appointment and cruise supervision method | |
| CN113095636B (en) | Intelligent scheduling system and method for fuel sharing automobile | |
| CN107038858A (en) | Method is recommended in the dynamic share-car of the private car that commutes | |
| CN113194138A (en) | Travel management method and system based on AI deep learning | |
| CN108596484A (en) | A kind of shared Truck dispartching method and system based on site attributive analysis | |
| CN107665393A (en) | A kind of automobile management method based on automatic Pilot technology | |
| CN113538067A (en) | Inter-city network taxi appointment demand prediction method and system based on machine learning | |
| CN113935505A (en) | Shared electric vehicle operation optimization method based on column generation and ant colony algorithm fusion | |
| CN114694399B (en) | Parking stall reservation management system based on thing networking | |
| CN106781442A (en) | A kind of vehicle behavior early warning system | |
| CN116884266A (en) | Smart city parking management method and management system based on big data | |
| CN114254856B (en) | Shared single-vehicle operation and maintenance scheduling method and system based on honeycomb diagram | |
| CN116227760B (en) | Method, device, storage medium and equipment for predicting influence of travel activities | |
| CN112949987A (en) | Taxi dispatching and matching method, system, equipment and medium based on prediction | |
| CN116206463B (en) | Public road operation vehicle dispatch system | |
| CN112837201A (en) | Accurate data-driven intelligent resource allocation system | |
| CN110019376B (en) | Driving comparison method for electric vehicle rental system |
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 |