WO2016119704A1 - 一种为按需服务提供信息的方法及系统 - Google Patents

一种为按需服务提供信息的方法及系统 Download PDF

Info

Publication number
WO2016119704A1
WO2016119704A1 PCT/CN2016/072357 CN2016072357W WO2016119704A1 WO 2016119704 A1 WO2016119704 A1 WO 2016119704A1 CN 2016072357 W CN2016072357 W CN 2016072357W WO 2016119704 A1 WO2016119704 A1 WO 2016119704A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
passenger
historical
driver
destination
Prior art date
Application number
PCT/CN2016/072357
Other languages
English (en)
French (fr)
Inventor
陈烨
卓呈祥
吴召学
许明
秦凯杰
张亚杰
卢海阳
郭栋
余鹏
芦彦君
包文毅
Original Assignee
北京嘀嘀无限科技发展有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Priority claimed from CN201510039939.3A external-priority patent/CN104599217B/zh
Priority claimed from CN201510048217.4A external-priority patent/CN104574255A/zh
Priority claimed from CN201510070073.2A external-priority patent/CN104599161A/zh
Priority claimed from CN201510105381.4A external-priority patent/CN104658255B/zh
Priority claimed from CN201510151590.2A external-priority patent/CN104837114B/zh
Priority claimed from CN201510239402.1A external-priority patent/CN104899252B/zh
Priority claimed from CN201510284601.4A external-priority patent/CN104869638B/zh
Priority claimed from CN201510464596.5A external-priority patent/CN105138590A/zh
Priority claimed from CN201510591079.4A external-priority patent/CN105303817B/zh
Priority claimed from CN201511000093.9A external-priority patent/CN106919996A/zh
Priority claimed from CN201510991394.6A external-priority patent/CN106919993A/zh
Priority to JP2017539550A priority Critical patent/JP6637054B2/ja
Priority to MYPI2017001096A priority patent/MY193639A/en
Priority to AU2016212530A priority patent/AU2016212530A1/en
Priority to EP16742766.5A priority patent/EP3252704B1/en
Priority to CA2975002A priority patent/CA2975002C/en
Priority to BR112017016064-1A priority patent/BR112017016064B1/pt
Priority to KR1020177023933A priority patent/KR20180006875A/ko
Application filed by 北京嘀嘀无限科技发展有限公司 filed Critical 北京嘀嘀无限科技发展有限公司
Priority to US15/546,657 priority patent/US10458806B2/en
Priority to GB1712010.6A priority patent/GB2550309A/en
Priority to SG11201706149XA priority patent/SG11201706149XA/en
Publication of WO2016119704A1 publication Critical patent/WO2016119704A1/zh
Priority to PH12017501345A priority patent/PH12017501345A1/en
Priority to HK18104998.4A priority patent/HK1245955A1/zh
Priority to US16/569,632 priority patent/US11156470B2/en
Priority to AU2019101806A priority patent/AU2019101806A4/en
Priority to AU2019236639A priority patent/AU2019236639A1/en
Priority to US17/448,717 priority patent/US11892312B2/en

Links

Images

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
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0283—Price estimation or determination
    • G06Q30/0284—Time or distance, e.g. usage of parking meters or taximeters
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/36—Input/output arrangements for on-board computers
    • G01C21/3605—Destination input or retrieval
    • G01C21/3617—Destination input or retrieval using user history, behaviour, conditions or preferences, e.g. predicted or inferred from previous use or current movement
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3453—Special cost functions, i.e. other than distance or default speed limit of road segments
    • G01C21/3484—Personalized, e.g. from learned user behaviour or user-defined profiles
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29—Geographical information databases
    • 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
    • G06Q10/02—Reservations, e.g. for tickets, services or events
    • 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/14—Travel agencies
    • G06Q50/40—
    • 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
    • H04L67/52—Network services specially adapted for the location of the user terminal
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02—Services making use of location information
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02—Services making use of location information
    • H04W4/029—Location-based management or tracking services
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/30—Services specially adapted for particular environments, situations or purposes
    • H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
    • 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
    • G06Q30/04—Billing or invoicing

Definitions

  • the present application relates to systems and methods for providing information for on-demand services, and more particularly to methods and systems for predicting travel destinations using mobile internet technologies and data processing techniques.
  • the passenger/driver's destination or travel route can be predicted according to the passenger/driver's travel rules, the user experience of both parties to the transportation service can be improved.
  • a method of providing information for an on-demand service comprising receiving service request information from a passenger of a passenger terminal device, the service request information including an origin of the passenger a location; obtaining historical service request information related to the passenger; determining travel route related information based at least in part on the origin location of the passenger and the historical service request information.
  • a system for providing information for an on-demand service comprising: a computer readable storage medium configured to store an executable module, comprising: a service requester interface module configured To receive service request information from a passenger of a passenger terminal device, the service request information includes an origin location of the passenger; and a processing module configured to: 1) acquire historical service request information related to the passenger 2) determining travel path related information based at least in part on the origin location of the passenger and the historical service request information; a processor capable of executing the executable of the computer readable storage medium storage Module.
  • the service request information includes a time information.
  • the travel path related information includes at least one of the following: a destination; a path to the destination by the current location of the passenger; a distance of the path.
  • the destination is determined based on a classification model.
  • the classification model is based on at least one location type.
  • a method of providing information for an on-demand service further includes transmitting the travel path related information to the passenger terminal device.
  • a method of providing information for an on-demand service further includes receiving processing of the travel path related information by a passenger from the passenger end device.
  • the historical service request information includes at least one of the following information: a historical origin; a historical destination; a history of arrival from the history of the passenger to the historical destination Path; the distance of the above historical path.
  • a method of providing information for an on-demand service further includes determining a service fee.
  • determining the service fee comprises: obtaining a plurality of location information from a driver at a plurality of time points; calculating the service fee based at least in part on the plurality of location information.
  • FIG. 1-A is a schematic diagram of a network environment including an on-demand service system, according to some embodiments of the present application.
  • 1-B is another schematic diagram of a network environment including an on-demand service system, according to some embodiments of the present application.
  • FIG. 2 is an exemplary system diagram of an on-demand service system, in accordance with some embodiments of the present application.
  • FIG. 3 is an exemplary block diagram of a processing module in a POI engine, shown in accordance with some embodiments of the present application;
  • 4-A is an exemplary block diagram of a passenger interface in a POI engine, shown in accordance with some embodiments of the present application;
  • 4-B is an exemplary block diagram of a driver interface in a POI engine, shown in accordance with some embodiments of the present application;
  • FIG. 5 is an exemplary block diagram of a client device shown in accordance with some embodiments of the present application.
  • FIG. 6 is an exemplary block diagram of a database shown in accordance with some embodiments of the present application.
  • FIG. 7 is a flow diagram of determining destination related information, in accordance with some embodiments of the present application.
  • FIG. 8 is an exemplary embodiment of receiving destination related information on a passenger end device, in accordance with some embodiments of the present application.
  • 9-A is an exemplary embodiment of predicting current destination related information, shown in some embodiments of the present application.
  • 9-B is an exemplary embodiment of receiving and processing destination related information on a passenger end device, in accordance with some embodiments of the present application.
  • 10-A is an exemplary flowchart of generating destination related information, shown in some embodiments of the present application.
  • 10-B is an exemplary flow diagram for establishing a POI classification model, shown in accordance with some embodiments of the present application.
  • FIG. 11 is an exemplary flow diagram of a POI engine providing a travel path to a user, in accordance with some embodiments of the present application.
  • 12-A is an exemplary flowchart showing a POI engine providing travel mode planning to a user in accordance with some embodiments of the present application;
  • 12-B is an exemplary flowchart of a POI engine processing travel information, in accordance with some embodiments of the present application.
  • FIG. 13 is an exemplary flow diagram of a POI engine detecting vehicle status, in accordance with some embodiments of the present application.
  • FIG. 14 is an exemplary flowchart showing that a POI engine determines that a user's location information is abnormal according to some embodiments of the present application;
  • 15-A is an exemplary flowchart showing that the POI engine determines that the location information of the user is abnormal according to some embodiments of the present application;
  • FIG. 15-B is an exemplary flowchart of determining, by the POI engine, that the positioning information is abnormal according to some embodiments of the present application;
  • Figure 16 shows the structure of a mobile device that can implement the particular system disclosed in this application
  • Figure 17 shows the structure of a computer that can implement the particular system disclosed in this application.
  • Embodiments of the present application may be applied to different transportation systems including, but not limited to, one or a combination of terrestrial, marine, aerospace, aerospace, and the like. For example, taxis, buses, trains, buses, trains, motor trains, high-speed rail, subways, ships, airplanes, spaceships, hot air balloons, unmanned vehicles, receiving/delivery, etc., apply management and/or distribution of transportation. system.
  • Application scenarios of different embodiments of the present application include, but are not limited to, a combination of one or more of a web page, a browser plug-in, a client, a customization system, an in-house analysis system, an artificial intelligence robot, and the like.
  • the "passenger”, “customer”, “demander”, “service requester”, “service requester”, “consumer”, “consumer”, “user demander”, etc. described in this application are interchangeable. , refers to the party that needs or subscribes to the service, can be an individual, or a tool. Similarly, the “driver”, “provider”, “supplier”, “service provider”, “service provider”, “service provider”, “service party”, etc. described herein are also interchangeable, Refers to the provision of services or assistance in providing services People, tools or other entities.
  • the "user” described in the present application may be a party that needs or subscribes to a service, or a party that provides a service or assists in providing a service.
  • the network environment 100 can include an on-demand service system 105, one or more passenger devices 120, one or more databases 130, one or more driver devices 140, one or more networks 150, one or more information Source 160.
  • the on-demand service system 105 can include a POI (Point of Interest) engine 110.
  • the POI engine 110 may be a system that analyzes the collected information to generate an analysis result.
  • the POI engine 110 can be a server or a server group, and each server in the group is connected through a wired or wireless network.
  • a server group can be centralized, such as a data center; a server group can also be distributed, such as a distributed system.
  • the POI engine 110 can be centralized or distributed.
  • Passenger terminal 120 and driver terminal 140 may be collectively referred to as a user, which may be a person, tool, or other entity directly associated with a service order, such as a requestor and service provider of a service order. Passengers can be service demanders. In this document, "passenger”, “passenger” and “passenger equipment” are used interchangeably.
  • the passenger may also include a user of the passenger end device 120. In some embodiments, the user may not be the passenger himself.
  • user A of passenger terminal device 120 may use passenger terminal device 120 to request on-demand service for passenger B, or to accept other information or instructions sent by on-demand service or on-demand service system 105.
  • the user of the passenger end device 120 may also be referred to herein simply as a passenger.
  • the driver can be a service provider. In this article, “driver”, “driver” and “driver device” are used interchangeably.
  • the driver may also include a user of the driver's end device 140. In some embodiments, the user may not be the driver himself.
  • user C of driver device 140 may use driver device 140 to accept other information or instructions sent by driver D to on-demand service or on-demand service system 105.
  • the user of the driver device 120 may also be referred to simply as a driver.
  • the passenger terminal 120 can include one or a combination of the desktop computer 120-1, the notebook computer 120-2, the built-in device 120-3 of the motor vehicle, the mobile device 120-4, and the like.
  • the built-in device 120-3 of the motor vehicle may be a carputer or the like;
  • the mobile device 120-4 may be a smart phone, a personal digital assistance (PDA), a tablet, or a handheld game.
  • PDA personal digital assistance
  • Driver terminal 140 may also include one or more of similar devices.
  • the POI engine 110 can directly access and/or access data information stored in the database 130, and can also access and/or access information of the client 120/140 directly through the network 150.
  • database 130 can be broadly referred to as a device having a storage function.
  • the database 130 is primarily used to store data collected from the passengers 120 and/or the driver 140 and various data utilized, generated, and output by the POI engine 110 during operation.
  • Database 130 can be local or remote.
  • the connection or communication of database 130 with on-demand service system 105 or a portion thereof (e.g., POI engine 110) may be wired or wireless.
  • Network 150 can be a single network or a combination of multiple different networks.
  • the network 150 may be a local area network (LAN), a wide area network (WAN), a public network, a private network, a private network, or a public switched telephone network (PSTN).
  • PSTN public switched telephone network
  • the Internet a wireless network, a virtual network, or any combination of the above.
  • Network 150 may also include multiple network access points, such as wired or wireless access points, such as base station 150-1, base station 150-2, Internet switching points, etc., through which any data source may be connected
  • the network 150 is entered and sent over the network 150.
  • the driver terminal 140 in the transportation service is taken as an example, but the application is not limited to the scope of this embodiment.
  • the driver device 140 can be a mobile phone or a tablet.
  • the network environment 100 of the driver device 140 can be divided into a wireless network (Bluetooth, wireless local area network (WLAN), Wi-Fi, etc.), and a mobile network (2G, 3G, 4G). Signal, etc., or other private connection (virtual private network (VPN)), shared network, near field communication (NFC), ZigBee, etc.).
  • a wireless network Bluetooth, wireless local area network (WLAN), Wi-Fi, etc.
  • Signal, etc., or other private connection virtual private network (VPN)
  • shared network e.gBee, etc.
  • NFC near field communication
  • ZigBee ZigBee
  • Information source 160 is a source of additional information for the system.
  • the information source 160 can be used to provide service related information to the system, such as weather conditions, traffic information, legal and regulatory information, news events, lifestyle information, lifestyle guide information, and the like.
  • the information source 160 may exist in the form of a single central server, or in the form of a plurality of servers connected through a network, or in the form of a large number of personal devices. When the information source exists in the form of a large number of personal devices These devices can use a user-generated content, such as uploading text, sound, images, video, etc. to the cloud server, so that the cloud server together with the numerous personal devices connected to it form an information source.
  • the information source 160 may be a municipal service system including map information and city service information, a traffic real-time broadcast system, a weather broadcast system, a news network, and the like.
  • the information source 160 may be a physical information source such as a common speed measuring device, a sensing device, an Internet of Things device, such as a driver's vehicle speedometer, a radar speedometer on a road, and a temperature and humidity sensor.
  • the information source 160 can also be a source for obtaining news, information, road real-time information, etc., such as a network information source.
  • the network information source may include one or more of an Internet news group based on Usenet, a server on the Internet, a weather information server, a road status information server, and the like.
  • the information source 160 may be a system that stores a plurality of catering service providers in a certain area, a municipal service system, a traffic road condition system, a weather broadcast system, a news network, and a rule system that stores legal and regulatory information about the local area.
  • a municipal service system a traffic road condition system
  • a weather broadcast system a weather broadcast system
  • a news network a news network
  • a rule system that stores legal and regulatory information about the local area.
  • the above examples are not intended to limit the scope of the information sources herein, nor are they limited to the scope of services of the examples.
  • the present application can be applied to any service, any device or network capable of providing information related to the corresponding services. Can be classified as a source of information.
  • information exchange between the on-demand service system 105 and different portions of the network environment 100 in which it is located can be performed by way of an order.
  • the object of the order can be any product.
  • the product can be a tangible product or an intangible product.
  • a tangible product can be any kind or combination of physical objects, such as food, medicine, daily necessities, chemical products, electrical appliances, clothing, automobiles, real estate, luxury goods, and the like.
  • An intangible product may include one or a combination of a service product, a financial product, an intellectual product, an internet product, and the like.
  • An Internet product can be any product that meets people's needs for information, entertainment, communication or business. There are many classification methods.
  • the Internet product may include one or a combination of a personal host product, a Web product, a mobile Internet product, a commercial host platform product, an embedded product, and the like.
  • the mobile internet product can be a software, program or system for use in a mobile terminal.
  • the mobile terminal includes, but is not limited to, a combination of one or more of a notebook, a tablet, a mobile phone, a personal digital assistant (PDA), an electronic watch, a POS machine, a car computer, a television, and the like.
  • PDA personal digital assistant
  • the travel software or application can be software or applications such as travel software, vehicle reservations, maps, and the like.
  • the traffic reservation software or application refers to a reservation for a horse, a carriage, a rickshaw (for example, a two-wheeled bicycle, a tricycle, etc.), a car (for example, a taxi, a bus, etc.), a train, a subway, a ship, an aircraft (for example) , a combination of one or more of aircraft, helicopters, space shuttles, rockets, hot air balloons, etc.).
  • FIG. 1-B Another schematic diagram of a network environment 100 is shown in FIG. 1-B.
  • Figure 1-B is similar to Figure 1-A.
  • database 130 is self-contained and can be directly coupled to network 150.
  • the on-demand service system 105, or a portion thereof (e.g., the POI engine 110), and/or the client 120/140 can directly access the database 130 over the network 150.
  • the manner in which the database 130 in FIG. 1-A or FIG. 1-B is connected to the on-demand service system 105, or a portion thereof (eg, the POI engine 110), and/or the client 120/140 may be different.
  • the access rights of the parties to the database 130 can be limited.
  • the on-demand service system 105, or a portion thereof e.g., the POI engine 110
  • the end device 140 can read part of the public information or personal information related to the user when certain conditions are met.
  • the on-demand service system 105 can update/modify the information of the public or related to the user in the database 130 based on the experience of one or more users of a user (passenger or driver) using the on-demand service system 105.
  • a driver 140 may view partial information about the passenger 120 in the database 130 upon receiving a service order from a passenger 120; however, the driver 140 may not autonomously modify the information about the passenger 120 in the database 130. Instead, it can only report to the on-demand service system 105, and the on-demand service system 105 decides whether to modify the information about the passenger 120 in the database 130.
  • a passenger 120 upon receiving a request from a driver 140 to provide a service, may view some information about the driver 140 in the database 130 (such as user rating information, driving experience, etc.); but the passenger 120 does not.
  • the information about the driver 140 in the database 130 can be modified autonomously, and can only be reported to the on-demand service system 105, and the on-demand service system 105 decides whether to modify the information about the driver 140 in the database 130.
  • database 130 may be a cloud computing platform with data storage capabilities, including but not limited to public clouds, private clouds, community clouds, hybrid clouds, and the like. Variations such as these are within the scope of the present application.
  • FIG. 2 is an exemplary system diagram.
  • the POI engine 110 may include one or more processing modules 210, one or more storage modules 220, one or more passenger interfaces 230, and one or more driver interfaces 240.
  • the modules in the POI engine 110 can be centralized or distributed.
  • One or more of the modules of the POI engine 110 may be local or remote.
  • the POI engine 110 can be one or a combination of a web server, a file server, a database server, an FTP server, an application server, a proxy server, a mail server, and the like.
  • the POI engine 110 can be used to receive information from the passenger end device 120 via the passenger interface 230 or to transmit the processed information to the passenger end device 120 via the passenger interface 230. In some embodiments, the POI engine 110 can be used to receive information from the driver device 140 via the driver interface 240 or to transmit the processed information to the driver device 140 via the driver interface 240.
  • the manner in which the information is received and transmitted may be direct (e.g., directly from the one or more passenger end devices 120 and/or one or more of the driver devices 140 via the network 150 directly through the passenger interface 230 or the driver interface 240, or may be Receiving information from information source 160) may also be indirect.
  • Processing module 210 may obtain the required information by sending a request to one or more information sources 160.
  • Information in information source 160 may include, but is not limited to, weather conditions, road conditions, traffic conditions, etc., or any combination of the above.
  • the POI engine 110 can communicate with the database 130.
  • the POI engine 110 can extract information in a database, such as map data, historical order information, and the like.
  • the historical order information may include a combination of one or more of a departure place of a historical order, a destination of a historical order, a time when a historical order occurs, a price of each order in a historical order, and the like.
  • the POI engine 110 can also send information received from the passenger interface 230 and/or the driver interface 240 to the database 130.
  • the processing results of the information by the processing module 210 in the POI engine 110 can also be sent to the database 130.
  • the processing module 210 can be used for processing related information. Processing module 210 may send the processed information to passenger interface 230 and/or driver interface 240.
  • the manner of information processing may include, but is not limited to, a combination of one or several of storing, classifying, filtering, converting, calculating, retrieving, predicting, training, and the like.
  • the processing module 210 may include, but is not limited to, a central processing unit (CPU), an application specific integrated circuit (ASIC), and an application specific instruction set processor.
  • ASIP Application Specific Interconnect Protocol
  • PPU Physical Processing Unit
  • DSP Digital Processing Processor
  • FPGA Field-Programmable Gate Array
  • PLD Programmable Logic A combination of one or more of a device (Programmable Logic Device (PLD)), a processor, a microprocessor, a controller, a microcontroller, and the like.
  • PLD Programmable Logic Device
  • the passenger interface 230 and the driver interface 240 can receive respective transmitted information from the passenger end device 120 and the driver device 140, respectively.
  • the information received above may be request information of the service, current location information of the passenger and/or driver, text sent by the passenger device 120/driver device 140, other information sent by the passenger device 120/driver device 140 ( For example, uploaded images, videos, audio information, etc.).
  • the received information may be stored in the storage module 220, may be calculated and processed by the processing module 210, and may also be sent to the database 130.
  • the information received by the passenger interface 230 and the driver interface 240 can be sent to the processing module 210 for processing, the generated processed information.
  • the information generated by the processing module 210 described above may be an optimization of the current location information of the passenger and/or the driver, and may be the starting location and/or destination information about the order.
  • the information generated by the processing module 210 described above may be confirmation information of the location of the passenger and/or driver, such as confirming the presence of an abnormal condition in the location of the passenger and/or driver.
  • the information generated by the processing module 210 may include a combination of one or more of a travel mode, a trade rate of an order when using each travel mode or a combination of travel modes, and the like.
  • the above modes of travel include a combination of a plurality of cars, trains, taxis, buses, trains, motor trains, high-speed rails, subways, ships, airplanes, and the like.
  • the information generated by the processing module 210 may be path related information.
  • the information related to the above path may include the number of paths, the start and end points of each path, and different travel modes. The time, price, etc. required for each path.
  • the information generated by processing module 210 may be transmitted to passenger device 120 and/or driver device 140 via passenger interface 230 and/or driver interface 240.
  • the information generated by the processing module 210 can be stored in the database 130, the storage module 220, or other modules or units having storage functions within the on-demand service system 105.
  • database 130 can be placed in the background of on-demand service system 105 (as shown in Figure 1-A). In some embodiments, database 130 can be self-contained, directly connected to network 150 (as shown in Figure 1-B). In some embodiments, database 130 can be part of on-demand service system 105. In some embodiments, database 130 can be part of POI engine 110. Database 130 can be broadly referred to as a device having a storage function. The database 130 is primarily used to store data collected from the client device 120/140 and/or the information source 160 and various data generated in the operation of the POI engine 110. Database 130 or other storage devices within the system generally refer to all media that can have read/write capabilities.
  • the database 130 or other storage devices in the system may be internal to the system or external devices of the system.
  • the connection between the database 130 and other storage devices in the system may be wired or wireless.
  • Database 130 or other storage devices within the system may include, but are not limited to, a combination of one or more of a hierarchical database, a networked database, and a relational database.
  • the database 130 or other storage device within the system can digitize the information and store it in a storage device that utilizes electrical, magnetic or optical means.
  • Database 130 or other storage devices within the system can be used to store various information such as programs and data.
  • the database 130 or other storage devices in the system may be devices that store information by means of electrical energy, such as various memories, random access memory (RAM), read only memory (ROM), and the like.
  • the random access memory includes but is not limited to a decimal counter tube, a selection tube, a delay line memory, a Williams tube, a dynamic random access memory (DRAM), a static random access memory (SRAM), a thyristor.
  • Read only memory includes, but is not limited to, bubble memory, magnetic button line memory, thin film memory, magnetic plate line memory, magnetic core memory, drum memory, optical disk drive, hard disk, magnetic tape, Non-volatile random access memory (NVRAM), phase change memory, magnetoresistive random storage memory, ferroelectric random access memory, nonvolatile SRAM, flash memory, electronic erasable rewritable read only memory , erasable programmable read only memory, programmable read only memory, shielded heap read memory, floating connection gate random access memory, nano random access memory, track memory, variable resistance memory, programmable metallization unit, etc.
  • NVRAM Non-volatile random access memory
  • the database 130 or other storage devices within the system may be devices that store information using magnetic energy, such as hard disks, floppy disks, magnetic tapes, magnetic core memories, magnetic bubble memories, USB flash drives, flash memories, and the like.
  • the database 130 or other storage device within the system may be a device that optically stores information, such as a CD or DVD.
  • the database 130 or other storage device within the system may be a device that uses magneto-optical means to store information, such as a magneto-optical disk or the like.
  • the access mode of the database 130 or other storage devices in the system may be one or a combination of random storage, serial access storage, read-only storage, and the like.
  • Database 130 or other storage devices within the system may be non-persistent memory or permanent memory. The storage devices mentioned above are just a few examples, and the storage devices that the system can use are not limited thereto. Database 130 or other storage devices within the system may be local or remote.
  • the foregoing processing module 210 and/or the database 130 may actually exist in the user end 120/140, and may also perform corresponding functions through the cloud computing platform.
  • the cloud computing platform includes, but is not limited to, a storage-based cloud platform based on storage data, a computing cloud platform based on processing data, and an integrated cloud computing platform that takes into account data storage and processing.
  • the cloud platform used by the client 120/140 may be a public cloud, a private cloud, a community cloud, or a hybrid cloud.
  • some order information and/or non-order information received by the client 120/140 may be calculated and/or stored by the user cloud platform according to actual needs.
  • Other order information and/or non-order information may be calculated and/or stored by a local processing module and/or a system database.
  • the POI engine 110 shown in FIG. 2 can be implemented in a variety of ways.
  • the POI engine 110 can be implemented in hardware, software, or a combination of software and hardware.
  • the hardware portion can be implemented using dedicated logic; the software portion can be stored in memory and executed by a suitable instruction execution system, such as a microprocessor or dedicated design hardware.
  • a suitable instruction execution system such as a microprocessor or dedicated design hardware.
  • processor control code such as on a disk, CD, or Such code is provided on a carrier medium of a DVD-ROM, a programmable memory such as a read only memory (firmware), or a data carrier such as an optical or electronic signal carrier.
  • the POI engine 110 and its modules can be implemented not only with hardware such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, and the like. It can also be implemented by, for example, software executed by various types of processors, or by a combination of the above-described hardware circuits and software (for example, firmware).
  • the processing module 210, the storage module 220, the passenger interface 230, the driver interface 240, and the database 130 may be different modules embodied in one system, or may be a module to implement the functions of the above two or more modules.
  • passenger interface 230 and driver interface 240 may be the same interface while interacting with passenger device 120 and driver device 140.
  • database 130 can be located within POI engine 110, with all of the functions of database 130 and storage module 220 being implemented by the same storage device. Variations such as these are within the scope of the present application.
  • processing module 210 may include the following units: an address resolution unit 310, an image processing unit 320, a voice processing unit 330, a grouping unit 340, a calculation unit 350, a path processing unit 360, a sorting unit 370, a determining unit 380, a text processing unit 390, and Model training unit 395.
  • Decision unit 380 can further include a calculation sub-unit 385.
  • processing module 210 may also include other units. In some embodiments, some of the above units may not be present. In some embodiments, some of the above units may be combined into one unit to function together. In some embodiments, the above units may be independent. In some embodiments, the above units may be in communication with one another.
  • the address resolution unit 310 can process the received address information. Above address information It may be from the passenger interface 230, the driver interface 240, the database 130, the information source 160, or other units or sub-units in the processing module 210.
  • the manner of processing the above information may include resolving address information or inversely resolving address information.
  • Inverse parsing refers to textual description information that converts an address coordinate to the location of the coordinate. Parsing refers to converting text description information of a place into an address coordinate information.
  • the address coordinates can be, for example, latitude and longitude coordinates.
  • the text description information may be, for example, one or more of a common name of a place, a street house number of a place, a landmark building name of a place, and the like, and a representative and representative name.
  • the address resolution unit 310 can also send the processed address information to other units, including but not limited to the image processing unit 320, the audio processing unit 330, the path processing unit 360, the sorting unit 370, the determining unit 370, the passenger interface 230, the driver interface. A combination of one or more of 240 and the like.
  • the image processing unit 320 may process the received image (still picture or video) information to obtain processed information.
  • the processing manner may include, for example, one or more image processing means such as image enhancement, image recognition, image segmentation, image measurement (angle, distance, calculation of perspective relationship), and the like.
  • the source of images received by image processing unit 320 includes a combination of one or more of passenger interface 230, driver interface 240, database 130, information source 160, or other units or sub-units in processing module 210.
  • the image information recognized by the image processing unit 320 can be input to the address resolution unit 310 for finding the corresponding address information.
  • the processed results generated by image processing unit 320 may be sent to path planning unit 360.
  • the voice processing unit 330 can process audio information from the passenger end device 120 and/or the driver device 140. Processing methods include noise reduction, speech recognition, semantic recognition, and character recognition. The voice processing unit 330 may output the recognized audio information to other units for processing, such as outputting the identified address information to the address resolution unit 310, the path planning unit 360, and the like.
  • the grouping unit 340 can group the received information.
  • the number of groups can be one, two, three, four, five, and the like.
  • the above information may be location information of the passenger and/or driver, including location coordinates and location names.
  • the grouping unit 340 may group the received GPS coordinates of the vehicle from the driver interface 240 and then determine the state of the vehicle based on the result of the grouping.
  • the method used by the grouping may be one or more clustering algorithms. It includes one or more of clustering algorithms such as K-MEANS algorithm, K-MEDOIDS algorithm or CLARANS algorithm.
  • grouping unit 340 can classify and output information.
  • the grouping unit 340 may group historical orders based on the distance between the starting position in the historical order and the current location of the passenger and the frequency of order usage within a certain time.
  • the results generated by the grouping unit 340 may be further sent to other units or sub-units in the processing module for processing, for example, the path processing unit 360, or may be sent to the passenger interface 230 and/or the driver interface 240 for output.
  • the foregoing clustering algorithm includes, but is not limited to, a segmentation clustering algorithm, a hierarchical clustering algorithm, a constraint-based clustering algorithm, a clustering algorithm in machine learning, and clustering for high-dimensional data.
  • a segmentation clustering algorithm e.g., a segmentation clustering algorithm, a hierarchical clustering algorithm, a constraint-based clustering algorithm, a clustering algorithm in machine learning, and clustering for high-dimensional data.
  • Segmentation clustering algorithms include, but are not limited to, density-based methods, grid-based methods, graph theory-based methods, based on Iterative redistribution clustering algorithm for squared errors.
  • Density-based clustering algorithms include, but are not limited to, Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm, Ordering Points to Identify the Clustering Structure (OPTICS) algorithm, DENsity-based CLUstEring (DENCLUE) algorithm, Clustering Using References and Density (CURD) algorithm, etc.
  • Grid-based clustering algorithms include, but are not limited to, the STatistical INformation Grid (STING) algorithm, the Clustering In QUEst (CLIQUE) algorithm, the WAVE-CLUSTER algorithm, and the like. Iterative redistribution clustering algorithms based on square error include, but are not limited to, probability-based clustering, nearest neighbor clustering, K-Medoids, K-Means and CLARANS.
  • Hierarchical clustering algorithms include but are not limited to aggregate clustering and decomposition clustering. Among them, CURE, ROCK and CHAMELEON algorithms are the three most representative methods in aggregate clustering, including but not limited to based on the nearest distance.
  • Clustering algorithms in machine learning include, but are not limited to, artificial neural network methods and methods based on evolutionary theory. Among them, methods based on evolutionary theory include Simulated Annealing (SA) and Genetic Algorithms (GA). .
  • SA Simulated Annealing
  • GA Genetic Algorithms
  • Clustering algorithms for high-dimensional data include, but are not limited to, subspace clustering algorithms (subspace) Clustering) and joint clustering.
  • the calculation unit 350 can calculate the received information.
  • the above information may be from the passenger interface 230, the driver interface 240, the database 130, the information source 160, or other units or sub-units in the processing module 210, such as the address resolution unit 310 and the like.
  • the content of the above calculation includes a combination of one or more of distance, time, order transaction rate or required fee.
  • computing unit 350 can calculate the probability of a historical travel path.
  • computing unit 350 may calculate the probability of occurrence of the originating location and/or the terminating location in the historical order.
  • computing unit 350 may calculate the distance between the current location of the passenger and the starting location in the historical order.
  • computing unit 350 may calculate the transaction rate of the order and the required fee when a certain travel mode is employed at a particular location and at a particular point in time. In some embodiments, computing unit 350 may calculate one or more of the distance between the origin of the order and the end position of the order, the time required, the cost required, and the distance to walk, and the like. combination. The calculation unit 350 can transmit the calculated result to other units, for example, the path processing unit 360, the sorting unit 370, and the like.
  • the path processing unit 360 can be used to calculate and plan the travel path of the passenger and the travel path of the driver to the passenger based on the positioning information from the passenger terminal device 120 and the driver device 140.
  • Path processing unit 360 can perform path planning based on information from other units.
  • the other units described above may include a combination of one or more of the self address resolution unit 310, the image processing unit 320, the voice processing unit 330, the grouping unit 340, the calculation unit 350, the sorting unit 370, and the like.
  • path processing unit 360 can perform path planning based on information from database 130 and/or information source 160.
  • the path processing unit 360 may further perform comprehensive analysis processing on the historical order, the map data, the classification model, and the service-related information in the information source 160 in the received database 130, thereby generating different paths. For passengers and / or drivers to choose.
  • the above historical order includes a combination of one or more of a starting position of a historical order, a termination position of a historical order, a time of a historical order transaction, a transaction rate, a fee, and the like.
  • the above map data may include geographic coordinates of artificial objects such as streets, bridges, buildings, geographical coordinates of various natural features such as water bodies, mountains, forests, wetlands, and descriptive names or signs of the above objects (street number, building name, River name, store name, etc.), image information of the above objects, and the like.
  • the above service related information may include weather conditions, traffic A combination of one or more of information, legal and regulatory information, news events, living information, living guide information, and the like.
  • the results generated by path processing unit 360 may be transmitted to passenger terminal device 120 and/or driver device 140 via passenger interface 230 and/or driver interface 240. In some embodiments, the results generated by path processing unit 360 may also be sent to ranking unit 370 for processing to generate results having a certain order or priority.
  • Sorting unit 370 can sort the received information based on certain rules.
  • the above rule may be a combination of one or more of the probability size, the length of the distance, the order of time, the length of time spent, the amount of cost required, and the way of travel.
  • the source of the information processed by the sorting unit 370 can be the computing unit 350.
  • the ranking unit 370 can sort the alternate origin or destination based on the number or probability of occurrences of the originating and/or destination in the historical order, and in accordance with the order of the number of times described above.
  • the passenger device 120 and/or the driver device 140 are sent to the passenger and/or driver for selection.
  • the sorting unit 370 can sort the travel mode and/or the path according to the amount of the required fee.
  • sorting unit 370 may order the travel mode and/or path according to the length of time spent. The results of the sorting can be in order from largest to smallest or from small to large. In some embodiments, sorting unit 370 can output the information that participates in the ranking. In some embodiments, the sorting unit 370 can output one piece of information participating in the sorting under a preset condition.
  • the above preset condition may be a combination of one or more of the highest frequency of use of an address, the least cost of the route, the shortest time required, the shortest walking distance of the passenger, and the minimum required travel mode.
  • the determination unit 380 can determine the status of the passenger and/or the driver. In some embodiments, decision unit 380 can determine whether the location information transmitted by passenger device 120 and/or driver device 140 is accurate. In some embodiments, the determination unit 380 can determine the state of the vehicle, such as whether it is stationary, whether it is moving, the direction of motion, the speed of motion, the acceleration of motion, and the like. The above determination of the state of the vehicle can be used to calculate the required fee for an order. The calculation of the above required fee may be completed by the calculation subunit 385 in the decision unit 380. In some embodiments, the determining unit 380 can determine the deviation between the positioning result transmitted by the driver device 140 using the first positioning technology and the positioning result using the second positioning technology or multiple positioning technologies. The above deviation can be calculated by the calculation subunit 385. According to the above The deviation can determine whether the positioning information of the first positioning technology is abnormal. Based on the determination result, the POI engine 110 can decide whether to send the order information to the driver device 140.
  • the text processing unit 390 can process the text information received by the processing module 210.
  • the processing of the text information may include combining the text information, extracting the feature text in the text information, classifying the feature text, and the like.
  • the text processing module 390 may perform processing such as deleting the content satisfying the specific condition in the text information.
  • the textual information may be from the passenger interface 230, the driver interface 240, the database 130, the information source 160, the storage module 220, or other units or sub-units in the processing module 210.
  • the results generated by text processing unit 390 can be sent to other units for further processing.
  • the model training unit 395 can be used to train the location classifier and/or the POI classification model.
  • the model training unit 395 can receive information from the database 130, the information source 160, or other modules or units in the on-demand service system, and utilizes the received information to train the location classifier and/or the POI classification model.
  • the model training unit 395 can distinguish between an address classification type to which an address included in a location information or text address data belongs.
  • the model training unit 395 can determine the travel destination or travel trajectory of the passenger history based on historical order information of a user (eg, a passenger). Depending on the purpose of the trip or the trajectory of the trip, the passenger's service request can be responded to by recommending a suitable destination and/or departure point for the passenger.
  • processing module 210 in the POI engine 110 is merely exemplary and is not intended to limit the application to the scope of the embodiments. It will be understood that, for those skilled in the art, after understanding the functions performed by the processing module, it is possible to perform any combination of the various modules, units or sub-units in the case of implementing the above functions, and to implement the above methods and systems. Various revisions and changes in the form and details of the application domain.
  • computing unit 350 and computing sub-unit 385 can be integrated into the same unit or module to perform computing functions.
  • the processing module 210 can also include a separate pricing unit to implement the calculation of the cost of the order. In some embodiments, some units are not required, such as text processing unit 390.
  • processing module 210 can include other units or sub-units. Variations such as these are within the scope of the present application.
  • FIG. 4-A shows a block diagram of the passenger interface 230 in the POI engine 110, in accordance with some embodiments.
  • the passenger interface 230 may include a passenger information receiving unit 410, a passenger information analyzing unit 420, and a passenger information transmitting unit 430.
  • the passenger information receiving unit 410 can be used to receive information sent by the passenger terminal device 120, and to identify, organize, and classify the information.
  • the information sent by the passenger terminal device 120 may be the current location of the passenger terminal device 120 determined by the positioning technology, the current location/departure location input by the passenger, other information related to the current location of the passenger, the current system time, Passenger's expected departure time/arrival time/journey time, etc., passenger selection/request/description of service, content/format/time/number of passengers' information desired to be received, passengers open or open on passenger terminal device 120 One or more of the service application and other information. From the information type or format, the information transmitted by the passenger terminal device 120 may be natural language text information input by the passenger on the passenger terminal device 120, binary information transmitted by the passenger terminal device 120, and input and output modules of the passenger terminal device 120.
  • the passenger terminal device 120 can provide the above information to the passenger information receiving unit 410 in the passenger interface 230 via the network 150.
  • the passenger information analysis unit 420 can be configured to perform the parsing operation on the passenger information received by the passenger information receiving unit 410.
  • the parsing operations herein may include collating or classifying passenger information, and performing format conversion or extraction, analysis, or transformation of the information content to convert to a format that processing module 210 or storage module 220 can calculate, process, or store.
  • the passenger information parsing unit 420 can also be used to convert the information processed by the processing module 210 or the information in the storage module 220 into information that can be read or selected by the passenger device 120 according to the instruction or preference of the passenger device 120.
  • the format is provided to the passenger information transmitting unit 430.
  • the passenger information transmitting unit 430 can be used to transmit information that the POI engine 110 needs to transmit to the passenger device 120 to the passenger terminal device 120 via the network 150.
  • the passenger information receiving unit 410 may be composed of a wired or wireless receiving device that establishes contact with the passenger terminal device 120 via the network 150.
  • the passenger information transmitting unit 430 may be composed of a wired or wireless transmitting device that establishes contact with the passenger device 120 via the network 150.
  • FIG. 4-B shows a box of the driver interface 240 in the POI engine 110, in accordance with some embodiments.
  • the driver interface 240 may include a driver information receiving unit 415, a driver information analyzing unit 425, and a driver information transmitting unit 435.
  • the driver information receiving unit 415 can be used on the driver's device to receive information sent by the driver, and to identify, organize, and classify the information.
  • the information sent by the driver may be the current location of the driver determined by the positioning technology, the speed of the driver, the current service status fed by the driver (passenger, waiting for passengers, empty driving), the driver's request for service One or more of the selection/confirmation/rejection information, the driver opening/opening the service application on the driver device 140, and the like.
  • the information sent by the driver device 140 may be natural language text information input by the driver on the device, binary information sent by the driver device 140, and audio information recorded by the driver device 140 (including the driver). One or more of the voice input), the image (still picture or video) information captured by the driver device 140, and other types of multimedia information.
  • the driver device 140 can provide the above information to the driver information receiving unit 415 in the driver interface 240 via the network 150.
  • the driver information analysis unit 425 can be configured to perform the parsing operation on the driver information received by the driver information receiving unit 415.
  • the parsing operations herein may include collating or categorizing the driver information, and performing a format conversion or extraction, analysis, or transformation of the information content to convert to a format that the processing module 210 or the storage module 220 can calculate, process, or store.
  • the driver information parsing unit 425 can also be used to convert the information processed by the processing module 210 or the information in the storage module 220 to the information that the driver device 140 can read or select according to the instruction or preference of the driver device 140.
  • the format is provided to the driver information transmitting unit 435.
  • the driver information transmitting unit 435 can be used to transmit information that the POI engine 110 needs to send to the driver device 140 to the driver device 140 via the network 150.
  • the driver information receiving unit 415 may be composed of a wired or wireless receiving device that establishes contact with the driver device 140 via the network 150.
  • the driver information transmitting unit 435 may be composed of a wired or wireless transmitting device that establishes contact with the driver device 140 via the network 150.
  • the passenger terminal device 120 may include an input and output module 510, a display module 520, a positioning module 530, a communication module 540, a processing module 550, and a storage module 560.
  • the passenger terminal device 120 can also contain more modules or components.
  • the input output module 510 can be configured to receive one or more forms of input of the passenger on the on-demand service application graphical interface, the map interface, and the input and output operation interface, and pass the information to be provided to the passenger in one or more forms. Output.
  • the input/output module 510 can also be used to perform one or more of optical, acoustic, electromagnetic, mechanical and other information of a passenger or the outside world (such as a surrounding environment) by means of signal conversion or the like as still picture, video, audio, mechanical. Vibration and other forms are collected and recorded.
  • the form of the input or output may include one or more of a sound signal, an optical signal, a mechanical vibration signal, and the like.
  • the display module 520 can be used to display a graphical interface of an on-demand service application, a map interface, an input and output operation interface, an operating system interface, and the like.
  • the positioning module 530 can determine the position of the passenger and/or its state of motion based on one or more positioning/ranging techniques. Specifically, determining the position of the passenger and its motion state may include calculating one or more of the passenger's position, speed, acceleration, angular velocity, path, and the like.
  • the communication module 540 can be configured to transmit or receive information to be transmitted or to be received by the passenger device 120 by way of wired or wireless communication. For example, communication module 540 can communicate with passenger interface 230 in POI engine 110 to enable passenger device 120 to transmit or receive information from POI engine 110.
  • the passenger device 120 can also communicate with the driver device 140 via the communication module 540, for example, Bluetooth communication, infrared communication. After the driver device 140 and the passenger device 120 turn on the Bluetooth, the distance between the driver and the passenger can be directly measured.
  • the processing module 550 can be used to calculate and process information obtained by the passenger terminal device 120.
  • the storage module 560 can be used to store information acquired, generated, calculated, or processed by the input/output module 510, the positioning module 530, the communication module 540, and the processing module 550.
  • the above positioning technologies include, but are not limited to, the positioning technology may be selected from the group consisting of Global Positioning System (GPS) technology, Global Navigation Satellite System (GLONASS) technology, Beidou navigation system technology, Galileo positioning system (Galileo) technology, and quasi-zenith satellite system (QAZZ).
  • GPS Global Positioning System
  • GLONASS Global Navigation Satellite System
  • Beidou navigation system technology Beidou navigation system technology
  • Galileo positioning system Galileo positioning system
  • QAZZ quasi-zenith satellite system
  • ranging techniques including, but not limited to, ranging techniques may be one or more based on electromagnetic waves, acoustic waves, or other fluctuations.
  • electromagnetic wave distance measurement technology can utilize one or more of radio waves, infrared rays, visible light, and the like.
  • the range technology using radio waves can utilize the Bluetooth band, or other microwave bands.
  • the sound wave ranging technique may be one or more of ultrasonic based infrasound waves, or acoustic waves in other frequency bands, and the like.
  • Use electricity Magnetic wave or acoustic wave ranging techniques can measure distance based on one or more of a variety of principles. For example, ranging techniques using electromagnetic waves or acoustic waves may be based on one or more of the time the waveform propagates, the Doppler effect, the signal strength, the signal attenuation characteristics, and the like.
  • the above description of the client device 120/140 is merely for convenience of description, and the present application is not limited to the scope of the embodiments. It can be understood that, for those skilled in the art, after understanding the functions performed by the user equipment, it is possible to perform any combination of the modules in the case of implementing the above functions, or to form a subsystem to be connected with other modules. Various modifications and changes in the form and details of the application of the above methods and systems.
  • the input and output module 510 and the display module 520 may be different modules embodied in one system, or may be a module to implement the functions of the above two or more modules.
  • the positioning module 530 and the communication module 540 may be different modules, or may be the same module integrated in the same hardware. Variations such as these are within the scope of the present application.
  • FIG. 6 is a schematic structural diagram of the database 130.
  • the database 130 can store information for a variety of different content, such as a historical order database 610, a map database 620, a user database 630, a classification model database 640, and the like.
  • a historical order database 610 a map database 620
  • a user database 630 a user database 630
  • a classification model database 640 a classification model database 640
  • the historical order database 610 may include the origin of the historical order, the destination, the type of origin, the type of destination, the start/end time of the historical order, the location of the passenger and the driver, the mileage of the trip, the travel, the amount of the order service , order service tip, order service rate, order service time rate, order travel time, passenger position and travel speed at different times during the service, average travel speed, passenger and/or driver's evaluation of historical orders And so on.
  • the map database 620 may include geographical coordinates of artificial objects such as streets, bridges, buildings, and the geographical coordinates of natural features such as various water bodies, mountains, forests, wetlands, and descriptive names or signs of the above objects (street number, building name, River name, store name, etc.), image information of the above objects, and the like.
  • artificial objects such as streets, bridges, buildings
  • natural features such as various water bodies, mountains, forests, wetlands, and descriptive names or signs of the above objects (street number, building name, River name, store name, etc.), image information of the above objects, and the like.
  • the information stored by the user database 630 may include service related information of the user 120/140, such as account name, display name (nickname), ID (driver's license, ID card, etc.) number, registration time, user level/level, traffic violation record, The drunk driving record, the driver information of the driver 140.
  • service related information of the user 120/140 such as account name, display name (nickname), ID (driver's license, ID card, etc.) number, registration time, user level/level, traffic violation record, The drunk driving record, the driver information of the driver 140.
  • the user database 630 can also store other social information of the user 120/140, such as credit history, criminal records, honor and reward records, and the like.
  • the user database 630 can also store basic information about the user 120/140, such as age, gender, nationality, address, work location, ethnic group, religious belief, education level, work experience, marital status, emotional status, language ability, professional skills. , political inclinations, hobbies, favorite music/TV programs/movies/books, etc.
  • the classification model database 640 can be used to store location type information associated with the location, mapping relationship information of various location descriptive names and location types, and association information between the location types. For example, the correlation coefficient between a descriptive name of a certain type of location and a type of location, the correlation coefficient of one type of location with another type of location, the collective relationship of one type of location with another, and the like.
  • a location type can be thought of as a collection of locations, including at least one location belonging to that location type.
  • a location type can also contain other location types as its subtypes. There may be cross-over portions between the two location types, that is, the same location may belong to one or more location types at the same time. From a collection perspective, the location type can be a Cantor set or a fuzzy set.
  • Each type of location can have a clear definition or “boundary” or a clear “boundary”.
  • a location type of a fuzzy set its elements can have a membership degree that is used to characterize the likelihood or probability of belonging to that location type. The degree of membership may be less than one or equal to one.
  • the storage of the above information may be implemented by different modules or components in a database 130.
  • the storage of the above information may also be implemented by a plurality of databases 130, which may exchange information with each other via wired or wireless communication connections.
  • the destination related information may include the location of the destination, the type of location of the destination, the time the passenger arrived at the destination, the route from the origin to the destination, and arrived from the origin. At least one of an average speed of the destination, a mode of transportation from the origin to the destination, a fee to arrive at the destination from the origin, and the like.
  • the destination related information may be related to one destination or may be related to a plurality of alternative destinations.
  • the POI engine 110 of the system 105 can receive location related information from a passenger terminal device 120 via the network 150 via its passenger interface 230.
  • the location related information may include, but is not limited to, the current location of the passenger, the passenger location at a certain moment in the future, the passenger location in a certain time period in the future, the origin of the passenger, the current time, and the passenger. The departure time specified by the guest.
  • the current location of the passenger may be acquired by the positioning module 530 of the passenger end device 120 or may be obtained by the input and output module 510.
  • the current location of the passenger may be a passenger location coordinate determined by one or more positioning techniques, or a descriptive name of the current location of the passenger input, and the like.
  • the current location related information further includes other information about the current location of the passenger and/or the driver, such as a business district, a residential area, an attraction, a hospital, a school, a large building, a bus station, a railway station, and a subway station. One or more of airports, bridges, intersections, etc.
  • the location-related information described above also includes pictures, video, audio, etc., uploaded from the passenger terminal device 120 and/or the driver device 140 about its current location.
  • the above picture, video, and audio information can be obtained through the input and output module 510 (see FIG. 5).
  • a passenger can take a landmark building around his or her cell phone camera and upload it to the POI engine 110.
  • the passenger terminal device 120 can obtain a voice or a video about the situation around its current location and send it to the POI engine 110.
  • the origin of the passenger designation generally refers to the origin of the passenger (or other passenger equipment 120 user) specified on the passenger equipment 120.
  • the passenger (or other passenger device 120 user) may enter or select an origin on an input box or list, array of icons provided by the input and output module 510 of their device 120.
  • the passenger may also specify the origin by operating an icon, a pin, or the like on the map interface displayed on the display module 520 of the device 120.
  • the passenger may also provide the originating device information to the passenger device 120 by voice input.
  • the current time can be obtained by the processing module 550 on the passenger premises device 120.
  • the departure time specified by the passenger can be input through the input and output module 510 on the device 120.
  • the specified departure time can be a specific time or a time range. The length of the time range and the starting time and ending time may vary with the application scenario, the current needs of the passenger, and the traffic service conditions.
  • the POI engine 110 retrieves historical information from a database 130 at step 720.
  • the structure and function of the database 130 are shown in Figure 6 and its corresponding textual description.
  • the historical information may include information related to historical orders stored by the historical order database 610.
  • the history information may also include map information stored by the map database 620.
  • Historical information may also include storage by user database 630 User service related information, other social information, basic information, etc. For the content of the above various information, refer to FIG. 6 and its corresponding text description, and details are not described herein again.
  • step 720 is after step 710, the above numbers do not represent or imply any chronological order, but merely serve as an identification for convenience of description.
  • the above step 720 can be performed in synchronization with step 710 or earlier than step 710.
  • the processing module 210 of the POI engine 110 determines the destination related information.
  • the POI engine 110 processing module 210 can predict the destination location/descriptive name/place type that the passenger wants to reach.
  • the processing module 210 can also plan at least one path from the origin to the destination based on the origin location and the destination location.
  • the processing module 210 can also estimate the path-related information according to the path planning algorithm.
  • the path related information includes, but is not limited to, travel distance, travel time, time to arrive at the destination, traffic jam time, fuel consumption, travel speed, number of traffic lights, travel expenses, and toll costs.
  • the path processing unit 360 of the processing module 210 may utilize one or more path optimization algorithms to calculate a path that determines the above-mentioned destination from the origin.
  • the criteria for determining the above path can be an optimal total cost.
  • the above total cost can be expressed in different forms. These forms may include, for example, path distance, travel time of the path, estimated traffic jam time of the path, estimated fuel consumption of the path, estimated travel speed of the path, number of traffic lights of the path, estimated cost of the path, path One or more of the transit costs, etc.
  • the total cost can depend on one or more of the above forms.
  • path optimization algorithms include, but are not limited to, traditional path planning algorithms, graphics algorithms, intelligent bionic algorithms, and other algorithms.
  • Traditional path planning algorithms include, but are not limited to, simulated annealing (SA), artificial potential method, fuzzy logic arithmetic, and tabu search (TS).
  • the methods of graphics include, but are not limited to, the C space method (also known as the view space method), the free space method, and the grid method.
  • Intelligent bionic algorithms include, but are not limited to, ant colony algorithms, neural network algorithms, genetic algorithms (GA), and particle swarm optimization (POS).
  • Other algorithms include, but are not limited to, Dijkstra algorithm, Shortest path fast algorithm (Shortest path) Faster algorithm (SPFA)), Bellman-Ford algorithm, Johnson algorithm, Fallback algorithm and Floyd-Warshall algorithm.
  • the calculation module 350 can calculate and process the path to obtain information related to the path. For details of the path-related information, refer to the above description, and details are not described herein again.
  • the computing module 350 can utilize information from the database 130 and/or the information source 160 when calculating the information related to the above path.
  • the information utilized includes, but is not limited to, historical order information from the historical order database 610, map data from the map database 620, weather, calendar, holidays, social activities, laws and regulations, etc. from other sources of information 160 Type of information.
  • FIG. 1-A and FIG. 6 For the content of the above information, refer to FIG. 1-A and FIG. 6 and their corresponding descriptions, and details are not described herein again.
  • the POI engine 110 After determining the destination related information, the POI engine 110 transmits the determined destination related information via the passenger interface 230 to the passenger end device 120 via the passenger interface 230 for the display and subsequent processing by the passenger end device 120.
  • the destination-related information sent may be the destination itself, or may be a path from the current location of the passenger device 120 or the origin of the passenger to the destination, or may be the one mentioned above. Path related information.
  • the transmitted destination related information may be associated with one destination or may be associated with multiple destinations.
  • related information associated with a plurality of destinations is represented in the form of a list.
  • the sorting unit 370 in the processing module 210 may sort the plurality of destinations, and the sorting criteria may be based on the above-mentioned path-related information, for example, the estimated path distance, the estimated travel time, and the estimated One or more of fuel consumption, estimated total cost, and the like.
  • the sorting unit 370 can perform ascending or descending order according to the above criteria.
  • the POI engine 110 may receive processing of destination related information from passengers of the passenger end device 120 via its passenger interface 230 via the network 150.
  • the processing of the passenger-related information by the passenger may be one or more of confirmation, denial, selection, addition, modification, etc. of the passenger's destination information.
  • the processing module 210 of the POI engine 110 may further analyze and calculate the processing to obtain a processing result.
  • the processing result can correspond to one
  • the destination determined by the passengers may also correspond to a path and/or path related information to the destination.
  • the driver interface 240 of the POI engine 110 transmits the processing results to the at least one driver device 140 via the network 150.
  • the driver interface 240 of the POI engine 110 receives a response from the driver of the driver device 140 to the processing results.
  • the content of the response may be one or more of willing/unwilling to provide transportation services for passengers, additional conditions for providing transportation services to passengers, current location information of drivers, and the like.
  • the POI engine 110 can process the response to confirm the driver's response.
  • the passenger interface 230 of the POI engine 110 may transmit the driver's willingness to provide the transportation service, additional conditions, and current location information to the passenger terminal device 120.
  • the passenger interface 230 can also send other information about the driver to the passenger end device 120.
  • Such information may include one or more of user service related information, other social information, basic material information, and the like.
  • the above description of the process of determining the destination-related information for the POI engine 110 is merely exemplary and is not intended to limit the application to the scope of the embodiments. It will be understood that, after understanding the principles of the foregoing processes, those skilled in the art may perform any combination of the steps in the implementation of the above functions, and perform the form and details on the processes and steps for implementing the above methods. Various corrections and changes. One or several steps from step 710 to step 780 may be skipped or omitted, while new steps may be inserted in addition to the above steps. For example, after step 780, the POI engine may receive transaction reports from the passenger end device 120 and/or the driver device 140 via its passenger interface 230 and/or driver interface 240.
  • this information can be directly sent to the driver device 140, that is, steps 740 and 750 are skipped, and the driver is notified in advance of the predicted passenger. Land and destination. Variations and variations such as these do not depart from the scope of the present application.
  • FIG. 8 shows an exemplary embodiment of receiving destination related information on a passenger end device.
  • the passenger terminal device 120 acquires a location related information by means of its positioning module 530 and/or input and output module 510.
  • the passenger device 120 passes the acquired location related information via the network 150.
  • the communication module 540 transmits out.
  • the target of the transmission may be the system 105, or other passenger equipment 120, or one or more driver equipment 140.
  • the passenger terminal device 120 transmits location related information to the system 105 for processing by the POI engine 110 and generating destination related information.
  • step 820 the passenger terminal device 120 proceeds to step 830 to receive destination related information from the system 105 via the communication module 540.
  • destination related information refer to FIG. 7 and its corresponding description, and details are not described herein again.
  • the destination related information received by the passenger device 120 is associated with a plurality of destinations. Further, information related to a plurality of destinations may be represented or presented in a list form.
  • the passenger terminal device 120 can display the received information via its display module 520.
  • the information can also be displayed in plain text or in hypertext.
  • the destination related information is represented or displayed in the form of a hypertext marking language (HTML).
  • the destination related information can be displayed in a map interface.
  • the input and output module 510 of the passenger end device 120 receives processing from the passenger regarding the destination related information.
  • the communication module 540 of the passenger end device 120 may send this processing out in step 850.
  • the target of the transmission may be system 105, other passenger device 120, or one or more driver devices 140.
  • the passenger terminal device 120 can also receive information from the outside. This information may be from system 105, other passenger premises equipment 120, one or more driver equipment 140. Information from system 105 may include, but is not limited to, receipt of receipts processed by passengers, destination processing results generated based on passenger-based processing, notifications by system 105 to transmit passenger information to one or more driver devices 140, The response of one or more driver devices 140 to the processing results, and the like.
  • steps 840 and 850 can be skipped and the guest device 120 can not perform related operations after accepting the destination related information. Variations such as these are within the scope of the present application.
  • FIG. 9-A illustrated in FIG. 9-A is an exemplary embodiment in which system 105 predicts current destination related information.
  • step 910 the POI engine 110 acquires current origination information and departure time information from a passenger terminal device 120 via the passenger interface 230.
  • step 920 the POI engine 110 retrieves historical order information associated with the passenger terminal device 120 from a database 130.
  • the POI engine 110 may acquire all historical order information associated with the above-described passenger terminal device 120, or may only acquire historical order information within a time period.
  • the above time period may be changed according to the user account information associated with the passenger terminal device 120, the frequency of the user history order, the location of the location, the current traffic situation, and the like.
  • the above time period may also be preset, and the length of time may take any possible length, such as, but not limited to, 1 month, 3 months, 6 months, 1 year or other length of time.
  • the POI engine 110 may obtain all the geographical history order information associated with the above-mentioned passenger terminal device 120, and may also obtain its associated historical order information near the current location.
  • the vicinity of the current position referred to herein may refer to an area within a threshold value, or may refer to a certain geographical area.
  • the above threshold may be an artificially preset distance value, for example, 1 km, 2 km, 5 km, 10 km, or other distance values.
  • the threshold may also be a variable distance value, which varies according to factors such as user account information associated with the passenger terminal device 120, the location of the passenger terminal device 120, current traffic service conditions, and the like.
  • the geographical area may be any size administrative division, commercial area, public area, residential area or any other artificially defined area.
  • the geographical scope may also be a natural geographical division without a clear boundary (for example, a geographical division divided by factors such as landform, climate, animal and plant distribution, etc.) or an area delimited by rivers, mountains, and the like.
  • the content of the above historical order information can be various, and can include the originating letter of the historical order.
  • One or more of factors such as interest rate, departure time, destination information, arrival time, travel time, and average travel speed.
  • Step 930 based on the current origin information, the departure time information, and the historical order information associated with the passenger device 120 described above, the POI engine 110 may generate one or more alternate destination information.
  • the computing unit 350 in the processing module 210 can predict the destination information based on the existing origin information. This prediction can be evaluated based on the degree of association between the current origin and the origin of the historical order.
  • the historical order has a higher degree of association with the current order when the origin of the historical order is close to the origin of the current passenger.
  • the historical order when the departure time of the historical order is close to the departure time of the current passenger, the historical order has a higher degree of relevance to the current order.
  • the historical order here is close to the current order, which means that the two are close in the year, month, day, top/afternoon, hour, and minute.
  • the historical order when the departure time of the historical order has a certain periodicity with the departure time of the current passenger, the historical order has a higher degree of relevance to the current order.
  • the periodicity rule here can mean that two orders have a certain degree of repeatability or similarity, and are separated by a time period.
  • the period may be an integer multiple of the unit time length of one year, one month, one day, etc., of course, may be an integral multiple of other time lengths.
  • the evaluation of the degree of association between the current order and the historical order by the calculation unit 350 in the processing module 210 may be performed by calculating a score indicator.
  • the scores of historical destinations corresponding to respective historical origins may be obtained using big data operations.
  • the score of the historical destination corresponding to each historical origin may be calculated using Equation 1:
  • the time is the current departure time; the source is the current origin; the POI i is a historical data, including the historical origin, the historical destination, and the historical departure time; and d represents the interval between the current departure time and the historical data POI i ;
  • the historical data reference with less days from the current departure time point has a greater meaning; s represents the current departure time and the interval between the historical data POI i , for short-term destination weight within 1 day, distance The closer the current departure time is, the higher the score; h indicates the interval between the current departure time and the historical data POI i departure time at the hourly granularity, and the smaller the number of hours from the current departure departure time interval, the greater the meaning of the historical data reference; POI i .
  • Source represents the historical origin in the POI i historical data
  • f(x, y) may be a decimal such as 0.1, 0.2, or 0.3, or may be other decimals.
  • the above distance threshold may be an artificially set value, such as 50 meters, 100 meters, 200 meters, 500 meters, or other distance values.
  • the historical destination with the largest score may be further processed to determine whether the historical destination may be set as the default destination.
  • This processing can be implemented by computing unit 350.
  • the score of the historical destination with the highest score can be further compared with the score of other historical destinations.
  • the ratio of the score of the historical destination with the highest score and the total score of the plurality of historical destinations may be calculated; if the ratio is greater than the second threshold, it is determined that the historical destination with the largest score is the default destination.
  • a passenger has three historical travel information, the score for the first trip to A is 2, the score for the second trip to A is 1.5, and the score for the third trip to B is 1.
  • For historical destination A its score is 3.5 and historical destination B has a score of 1.
  • the first threshold is set to 2 and the second threshold is set to 0.75.
  • the determining unit 380 in the processing module 210 may compare the score of the historical destination A with the first threshold, and if the score of the historical destination A is greater than the first threshold, determine the score (3.5) of the historical destination A and Whether the ratio of the sum (4.5) of the scores of the historical destinations A and B is greater than the second threshold, and if the ratio (3.5/4.5) is greater than the second threshold, it is determined that the historical destination A is the predicted destination.
  • the first threshold and the second threshold may be set as needed.
  • processing module 210 can also determine a plurality of default destinations according to the level of the score, instead of determining only the historical destination of the highest score as the default. Processing module 210 may sort the default destinations after determining a plurality of default destinations. According to the above scores, the sorting rules can be arranged in ascending order or in descending order. It should be noted that the purpose of setting the first threshold and the second threshold in determining the predicted destination is to ensure the accuracy of the prediction method of the passenger travel destination, and only to the target passenger when the accuracy is high. End device 120 transmits the predicted destination.
  • the address resolution unit 310 in the processing module 210 may further parse or inversely parse the candidate destination information, that is, convert the candidate destination represented by the geographic coordinate to the alternative destination of the description name representation. Alternatively, or convert an alternate destination represented by a descriptive name to an alternate destination represented by geographic coordinates.
  • the alternate destination information sent may be represented by a description name, may be represented by geographic coordinates, or may be represented by both.
  • the POI engine 110 may transmit the alternate destination information to the passenger end device 120 via the network 150 via the passenger interface 230 in step 940.
  • the POI engine 110 may also send alternate destination information to one or more of the driver devices 140 via the driver interface 240.
  • the POI engine 110 may receive processing from the passenger end device 120 for alternate destination information via the passenger interface 230.
  • the POI engine 110 can also analyze and calculate the above processing to generate a processing result. After this, the POI engine 110 can also have several subsequent operations. For details of the processing result and subsequent operations, refer to FIG. 7 and its related description, and details are not described herein again.
  • the above description of the flow or steps of the POI engine 110 based on the historical order information and the passenger's current origin location and departure time prediction destination information is merely exemplary and does not constitute a limitation of the present application. It can be understood that, for those skilled in the art, after understanding the operations performed by the POI engine 110 in the above process and the information acquired and provided, it is possible to perform any combination of the steps in the case of achieving the same effect. Various modifications and changes in form and detail are made to the process of implementing the above method. For example, in some embodiments, steps 940 and 950 can be skipped. The POI engine 110 may not perform related operations after transmitting destination related information. As another example, the POI engine 110 can also utilize the passenger terminal at step 910.
  • Other related information of the device 120 or the information source 160 including but not limited to, at least one location information of the passenger equipment 120 in a previous period of time, other passenger information acquired by the passenger equipment 120 (physical health information, such as heartbeat, pulse , blood pressure; social information, such as activities on social networks, dating of friends, etc.), weather information, current social activities, holiday information, laws and regulations, etc., collectively determine alternative destination information. Variations such as these are within the scope of the present application.
  • FIG. 9-B shows an exemplary embodiment of receiving and processing destination related information on a passenger end device.
  • the passenger terminal device 120 acquires the current origination information and the current departure time.
  • the current origin may be the current location, or may be the origin of the location set or designated by the passenger.
  • the current origin When the current origin is the current location, the current origin may be determined by the communication module 540 of the passenger device 120 according to one or more positioning technologies, or may be received by the input and output module of the passenger device 120. Determined by the instruction.
  • the communication module 530 can determine a more accurate current location based on two or more positioning techniques.
  • the communication module 540 can obtain GPS positioning information and base station positioning information by communicating with the GPS positioning satellite and the communication base station, and processed by the processing module 550 to determine a more accurate current location.
  • the processing module 550 can use the current location as the current origin location.
  • the current origin may be the one entered or selected by the passenger when the passenger originates in a position set or designated by the passenger on the passenger end device 120.
  • the passenger terminal device 120 can monitor whether there is an input command in the destination input box.
  • the passenger terminal device 120 inputs and outputs module 510 acquires current departure location information of the passenger terminal device 120.
  • the processing module 550 can simultaneously acquire the corresponding time of the passenger input instruction.
  • the passenger terminal device 120 can also store and record several common destinations preset by the passenger.
  • the passenger can call up the above-mentioned common destination on the passenger terminal device 120, display the common destination through the display module 520, and select through the input and output module 510.
  • the passenger terminal device 120 transmits the current origination information and the current departure time to the system 105 via the communication module 540.
  • the passenger terminal device 120 may also transmit information of other content including, but not limited to, passenger's physiological health information, passengers' requirements/preferrions/expectations to the transportation service, passengers' other information, etc. .
  • the passenger terminal device 120 communication module 540 receives the alternate destination information transmitted from the system 105 passenger interface 230.
  • the passenger terminal device 120 can display the received information via its display module 520.
  • the information can also be displayed in plain text or in hypertext.
  • the destination related information is represented or displayed in the form of a hyper text marking language (HTML).
  • the destination related information can be displayed in a map interface.
  • the passenger equipment 120 may receive the passenger's processing of the alternate destination information via the input and output module 510.
  • the above processing includes, but is not limited to, deleting/selecting/designating one or more alternative destinations and adding a new destination information.
  • the passenger terminal device 120 may transmit the above processing in step 955.
  • the target of the transmission may be system 105, one or more other passenger equipment 120, and one or more driver equipment 140.
  • the passenger equipment 120 may also obtain other related information in step 915, including but not limited to, at least one location information of the passenger equipment 120 in a previous period of time, other passenger information (health information, such as heartbeat, pulse, blood pressure ) and other information.
  • the passenger other information may be acquired by the sensing component (not shown in FIG. 5) of the input/output module 510 of the passenger terminal device 120, or may be acquired by other devices, such as a wearable device or a health device.
  • Passenger terminal device 120 The above information can also be sent out in step 925. Variations such as these are within the scope of the present application.
  • the POI engine 110 receives the geographic information of the passenger. Reception of geographic information may be accomplished by passenger interface 230.
  • the above geographic information may include location information and time information.
  • the location information may include the location where the passenger is currently located, and the starting location of the order.
  • the above time information may include the current time, the time when the passenger made the service request, the time set by the passenger, and the like.
  • the current location of the passenger may be the same as or different from the starting position of the order.
  • the current position of the passenger and/or the starting position of the order may be obtained by a specific positioning technique or may be obtained by manually inputting a specific address name by the passenger.
  • a specific positioning technique For a description of the positioning technology, refer to other parts in this specification, as shown in FIG. 5 and related descriptions, and details are not described herein again.
  • the POI engine 110 may generate an alternate destination based on a particular POI classification model. This step can be done by the processing module 210.
  • the particular POI classification model described above is related to passengers. Each passenger has a corresponding POI classification model.
  • the POI classification model described above may be stored in a user database 630, a storage module 220, or other modules or units having storage functions in the on-demand service system 105. The determination process regarding the above specific POI classification model is described with reference to FIG. 10-B.
  • the POI engine 110 can determine the POI classification type to which the passenger is currently located or the starting position of the order according to the POI classification model described above.
  • the POI engine 110 may determine the POI classification type of the order termination location according to the location of the passenger or the POI classification type of the starting position of the order. In some embodiments, the POI engine 110 may determine the order termination based on the location of the passenger or the POI classification type of the origin of the order and the current time, the time the passenger requested the service, or the departure time set by the passenger. The POI classification type of the location. The POI engine 110 may generate at least one alternative destination information based on the POI classification type of the order termination location.
  • the number of alternative destinations described above may be arbitrary, for example, one, two, three, four, five, and the like.
  • the above alternative destinations may belong to the same POI classification type, or may belong to different POI classification types, for example, two POI classification types, three POI classification types, and the like.
  • the number of alternative destinations generated above and/or the type of POI classification to which the destination belongs The quantity can be fixed or adjustable.
  • the POI engine 110 can receive a setting from the passenger end device 120 for the number of destinations to N1 and a number of POI classification types to which the destination belongs to N2.
  • the number of destinations in each POI classification type can be fixed or adjustable.
  • the POI engine 110 may also sort the generated alternate destinations according to a particular ordering rule, such as step 1030.
  • the above ordering can be done by the sorting unit 370 in the processing module 210.
  • the specific sorting rule described above may be based on a combination of one or more of including the probability size, the length of the distance, the order of time, the length of time spent, the amount of cost required, the number of travel modes employed, and the like.
  • the POI engine 110 may calculate, by the computing unit 350, the time, the distance from the starting position of the order to the alternate destination, the required fee, the type of travel mode required, and the different travel modes. One or more of the order turnover rate, etc.
  • the sorting unit 370 can sort the alternate destinations according to the results of the computing unit 350. In some embodiments, the ranking unit 370 can sort the alternate destinations according to the number of uses or frequency of the alternate destinations described above.
  • the POI engine 110 may send the sorted alternate destinations to the passenger end device 120 via the passenger interface 230.
  • the number of alternate destinations sent to the passenger end device 120 may be one or more of the alternate destinations participating in the ranking described above.
  • the destination information generated by step 1020 may include a recommended travel mode or a combination of multiple travel modes, and may also include a fee for selecting a different travel mode or a combination of different travel modes.
  • the POI engine 110 can sort the alternate destination information according to the number of travel modes or the amount of cost required.
  • the POI engine 110 may send an alternate destination to the passenger device 120 and/or the driver device 140.
  • the alternate destinations sent above may be ordered or unsorted.
  • the POI engine 110 can transmit all of the alternate destinations generated in step 1020 to the passenger end device 120.
  • the POI engine 110 may send the pre-ranked N destinations sorted according to certain rules among the alternate destinations in step 1020 to the passenger end device 120.
  • the value of N may include 2, 3, 4, 5, 6, 7, 8, 9, 10, or greater than 10.
  • the POI engine 110 can sort the N destinations described above. It is then sent to the passenger terminal device 120. Sorting can be based on one or more rules, such as the number of uses from large to small, frequency from high to low, travel mode from small to large, time spent from short to long, cost from small to large, different travel modes Order turnover rate, etc.
  • the ordering rules may be automatically set by the POI engine 110.
  • the ordering rules may be preset by the passenger.
  • the ranking rule may be specified by the passenger based on an order (such as a current order or an order that meets one condition).
  • the POI engine 110 can provide one or more sorting methods for passenger selection. Passengers may specify one or more of these sorting methods and/or applicable conditions.
  • the POI engine 110 allows a passenger to define one or more rankings and/or applicable conditions by himself.
  • the ranking can be based on a number of factors, and the POI engine 110 allows the passengers themselves to define the weight of each factor in calculating the ranking.
  • the POI engine 110 can transmit the N destinations described above in a random order.
  • the POI engine 110 may further receive processing from the passenger end device 120 for alternate destinations.
  • the above processing may include directly selecting one of the destinations to send to the POI engine 110.
  • the above processing includes selecting a plurality of ones to send to the POI engine 110.
  • the above processing includes deleting one or more alternate destinations. It is to be noted that the above description of the processing of at least one alternative destination for the POI engine 110 is merely exemplary and does not constitute a limitation of the present application. In some embodiments, other processing methods may also be included.
  • the POI engine 110 may transmit the processing result to the driver device 140 after receiving the processing result from the passenger terminal device 120.
  • the POI engine 110 will receive the selection from the passenger end device 120 for the alternate destination described above and use this selection as the termination location for the order.
  • the POI engine 110 may send an order including the start position of the order and the termination position of the above order to the driver device 140.
  • step 1010 is also not required.
  • the POI engine 110 receives the service request signal of the passenger, it can directly determine the possible travel trajectory of the passenger according to the current time without having to collect the current location of the passenger and/or the starting position of the order.
  • the service request signal described above may include the service provided by the POI engine 110 that the service is opened.
  • the travel trajectory described above may refer to a starting position and an ending position of the order.
  • the POI classification model is related to the passenger individual, for example, associated with the passenger's account name. Each passenger has its own specific POI classification model. For convenience of explanation, the following description will be made only for the case of one passenger.
  • the POI engine 110 may obtain historical order information associated with the passenger (or other passenger device 120 user). The historical order information may be all historical order information related to the passenger, or may be historical order information related to the passenger within a preset time period.
  • the above predetermined time period may include one day or several days, one week or several weeks, one month or several months, one quarter or several quarters, one year or several years, and the like. In some embodiments, the predetermined time period may be two months. In some embodiments, the preset time period may be randomly given or may be a fixed value. In some embodiments, the predetermined time period described above may be determined based on historical experience or experimental data.
  • the historical order information may include a combination of one or more of a starting position of a historical order, a termination position of a historical order, a time when a passenger issues a historical service request, or a historical departure time set by a passenger. The historical order information may be from the historical order database 610 in the database 130, the storage module 220, or other modules or units having storage functions in the on-demand service system 105.
  • the POI engine 110 may process the historical order information of the passengers according to a location classifier pre-established by the on-demand service system.
  • the method for establishing the above location classifier can be Reference is made to the relevant description below in this specification.
  • the historical order information described above may include a combination of one or more of location information, time information, required fee information, and the like.
  • the above location information may include the starting location and/or the ending location of the order.
  • the above time information may include the time when the passenger made the service request or the departure time set by the passenger.
  • the above processing includes performing address classification on the start position and/or the end position in the historical order, and generating an address classification type corresponding to the start position and/or the end position of the historical order.
  • the above address classification types may include transportation facilities, real estate communities, office areas, food and beverages, hotels, leisure and entertainment, address place names, shopping consumption, and the like.
  • the POI engine 110 may determine the POI type of the passenger based on the result of the address classification of the starting location and/or the ending location in the historical order.
  • the above POI types may be a plurality of types.
  • the POI engine 110 can predict the historical travel destination of the passenger by all the historical orders for the passenger or the address classification type of the starting position and/or the ending position in the historical order within a certain period of time in history. / or travel trajectory.
  • a period of time in the above history may be one week or weeks, one month or several months, one quarter or several quarters, one year or several years, and the like.
  • the passenger may be determined to be in a historical or historical time.
  • the section mainly moves between the place of residence and the restaurant. It can thus be known that the passenger is more inclined to eat and drink during a certain period of time in history or history.
  • the POI engine 110 can determine the POI type of the passenger based on the time information in the historical order and the address information in the historical order.
  • the above POI types may be a plurality of types.
  • the time information in the above historical order may include any time point or time period of the day.
  • the POI engine 110 can predict the travel destination and/or travel trajectory of the passenger for a certain period of time in history or history.
  • the starting position of the passenger's historical order is historically or historically the type of address classification is "real estate".
  • the end position of the passenger's historical order is historically or historically.
  • the address classification type is "office area”
  • the passenger's POI type is "real estate area” and "office area”. Then you can be sure that the passenger is Historically or historically, there has been a major movement between the place of residence and the workplace. It can thus be inferred that the passenger is more inclined to work during the historical or historical period.
  • the POI classification model can be obtained based on the POI type of the passenger determined above. According to the above POI classification model, the behavior habits of the passengers can be inferred. Further, by obtaining the current position information and/or time information of a certain passenger, it is possible to estimate the type of the address classification to which the destination of the passenger belongs, and to estimate the destination of the passenger.
  • the process of establishing a location classifier may include the following steps: (a) the processing module 210 may acquire text address data of a plurality of known address classification types; (b) the text processing unit 390 may adopt a preset word segmentation method for the plurality of The text address data of the known address classification type is subjected to word segmentation processing to generate a plurality of feature texts; (c) the model training unit 395 may train the plurality of feature texts as the training data to generate a location classifier.
  • the methods for training the above-mentioned location classifiers may include naive Bayesian algorithm, weighted Bayesian algorithm, decision tree, Rocchio, neural network, linear least squares fitting, K-nearest neighbor, genetic algorithm, maximum entropy, linear regression model training. a combination of one or more of the methods and the like.
  • the linear regression model described above may include a logistic regression model and a support vector machine model.
  • the method of training a location classifier described herein may also include other algorithms or models. In some embodiments, the location classifier can also be obtained directly from empirical values without data training.
  • processing module 210 may also include a sample equalization unit (not shown in FIG. 3). After obtaining the text address data of the plurality of known address classification types, the sample equalization unit may perform sample equalization on the text address data of the plurality of known address classification types.
  • the above-described sample equalization includes: based on the number of text address data of the above-described known address classification type and the number of address classification types, the calculation unit 350 can calculate the average number of text address data of each address classification type.
  • the sample equalization described above may employ a "replacement sampling" approach.
  • the text address data of the address classification type is increased such that the number of text address data possessed by the address classification type is equal to the average value. Conversely, if the number of text address data actually owned by an address classification type is greater than the above average number, then The text address data of the address classification type is removed such that the number of text address data possessed by the address classification type is equal to the average value.
  • the text processing unit 390 may segment the text address data of each known address classification type to generate a plurality of feature texts.
  • the results of the wording "Beijing Shangdi Metro Station” are three characteristic texts of "Beijing", " ⁇ ", and "Metro Station".
  • the processing module 210 can also include a redundancy removal unit.
  • the redundancy removal unit described above can be included in the text processing unit 390.
  • the text removal unit may remove the feature text whose length is less than a threshold in the feature text.
  • the threshold may be 2, 3, 4, or the like.
  • the results of the words “I am at Beijing Xi'erqi Metro Station” are “I”, “Yes”, “Beijing”, “Xi Erqi”, and “Metro Station”. Since the lengths of "I” and “Yes” are short, feature texts of length less than 2 can be deleted, and the remaining feature texts are "Beijing", "West Second Flag", and "Metro Station”.
  • the model training unit 395 may train the plurality of feature texts as the training data to generate a location classifier.
  • the model training unit 395 can train the location classifier using a naive Bayesian algorithm.
  • the calculation unit 350 can calculate the posterior probability P(Y
  • X) P(X
  • the computing unit 350 in the processing module 210 can calculate the probability that the text address data belongs to each type of address classification.
  • the probability that the above text address data belongs to each address classification type can be obtained by Equation 2:
  • P(X) is the probability of occurrence of the start or end position of the above order.
  • Y y j ) based on the data statistics.
  • the computing unit 350 in the processing module 210 can calculate the probability that the text address data described above belongs to each type of address classification. For the description, the probability of the address classification type is sequentially recorded as P1, P2, P3, ..., Pq in descending order, where q is the total number of address classification types. Based on the probability of the different address classification types described above, the processing module 210 can determine the address classification type to which the text address data belongs. In some embodiments, the processing unit 210 in the POI engine 110 may use the address classification type corresponding to the largest one of the above probabilities as the address classification type of the text address data. In some embodiments, the POI engine 110 may select the two largest probability values (ie, P1 and P2) of the above probabilities for comparison.
  • the address classification type corresponding to P1 may be used as the address classification type of the text address data described above.
  • the value of Z may be 1 to 2, 2 to 3, 3 to 4, 4 to 5, 5 to 6, or greater than 6.
  • Z has a value of 3 to 5.
  • the probability that the address classification type of "Shangdi Subway Station” is "traffic facility” is 0.6
  • the probability of the address classification type being "address place name” is 0.1
  • the value of setting Z is 3. 0.6>3*0.1 Therefore, the processing unit 210 can determine that the address classification type described in "Upper Subway Station" is "traffic facility".
  • Described above is the process of generating a location classifier. Based on the above-mentioned location classifier, it is possible to perform an address classification on the start position and/or the end position of an order, and determine the type of the address classification to which the start position and/or the end position of the order belong. It is to be noted that the above description is only exemplary and is not intended to limit the scope of the embodiments. It will be appreciated that those skilled in the art will be able to make various modifications and changes in the form and detail of the method described above after understanding the basic principles of the location classifier. Variations such as these are within the scope of the present application.
  • FIG. 11 is an exemplary flow diagram of a POI engine 110 providing a travel path to a user, in accordance with some embodiments of the present application.
  • the POI engine 110 can acquire at least one travel path of the user.
  • the user can be either a passenger or a driver. This step can be accomplished by passenger interface 230 and/or driver interface 240.
  • the travel path described above may be from passenger end device 120 and/or driver device 140, database 130, or information source 160. It should be noted that there are many ways to obtain at least one travel path of the user.
  • the user A plurality of commonly used travel paths may be preset; or, according to the user's daily travel data, consumption habits, etc., the big data may be used to calculate at least one travel path that the user may have.
  • the travel path includes an originating address and a destination address.
  • the POI engine 110 can calculate the probability of the at least one travel path described above.
  • the probability calculation for at least one of the above travel paths can be done by the processing module 210 in the POI engine.
  • the POI engine 110 can calculate the at least one travel path by the computing unit 350 in the processing module 210 in the POI engine 110 based on the historical probability and/or information related to the travel path.
  • the historical probability of each travel path can be obtained by calculation of the user's historical travel data.
  • computing unit 350 is operative to calculate a historical probability for each travel path.
  • the computing unit 350 is configured to calculate a probability of each of the travel paths based on the historical probability and/or information related to the travel path.
  • the information related to the travel path includes, but is not limited to, a combination of one or more of a current location, a current weather condition, a current date, and/or a current time.
  • the acquired travel paths of the users are R 1 , R 2 , . . . , R n ; respectively; the number of travels corresponding to each travel route is C 1 , C 2 , . . . , C n .
  • the information related to the travel path specifically refers to a factor that may affect the user's selection of the travel path, and may include one or a combination of the current location of the user, the current weather condition, the current date, the current time, and the like.
  • the user's consumption behavior can refer to the behavior of the user who makes the consumption decision and completes the consumption process under the influence of the demand motive.
  • the process of consumer behavior is not only the user's thinking, psychological process, but also the process of constantly taking action, generating solutions and solving problems.
  • the user selecting a travel path can be a process of consumer behavior. Users can determine their travel needs based on their own and various external conditions. For example, during working hours on weekdays, the current location of the passengers can be at home, then the passengers are most likely to choose to take a taxi to the company; during the off-hours of the working day, the current location of the passengers is at the company, then the passengers are most likely to choose to take a taxi home. And if it is the off-duty time on weekends, passengers are more likely to choose to take a taxi to entertainment venues such as bars or cinemas. For example, for rainy and snowy weather, passengers' desire to travel may not be strong. Once they choose to travel, the most likely destination is the main places related to daily life that are not too far away, such as restaurants, banks, hospitals or supermarkets.
  • the probability of calculating each travel path may be obtained based on the calculated historical probability.
  • the acquired passenger/driver travel paths are R 1 , R 2 , ..., R n respectively; the corresponding calculated historical probabilities are H 1 , H 2 , ..., H n respectively ; The current probabilities of the travel paths are H 1 , H 2 , ..., H n , respectively .
  • the probability of calculating each travel path may also be obtained based on the calculated historical probability and information related to the travel path.
  • the acquired passenger/driver travel paths are R 1 , R 2 , ..., R n respectively; the corresponding calculated historical probabilities are H 1 , H 2 , ..., H n , respectively .
  • the passenger/driver's travel route can be divided into two groups: the path set G whose origination address is the current position, assuming that the number of paths included therein is k, respectively R 1 , R 2 , ..., R k , correspondingly calculated
  • the historical probabilities are H 1 , H 2 , ..., H k ; and the path set G 2 whose originating address is not the current position, and the number of paths included therein is nk, respectively R k+1 , R k+2 ,... ..., R n , the corresponding calculated historical probabilities are H k+1 , H k+2 , ..., H n .
  • the probability of each path in the set G 2 is 0; and for each path in the set G 1 , since the originating address is The current position, so the "current position" has the same influence coefficient for each of the paths. Therefore, the probability of each path in the set G 1 is ..., The probability of each path in the set G 2 is zero.
  • the current probability of the passenger/driver's travel paths R 1 , R 2 , ..., R n is ..., 0, ..., 0.
  • the probability of calculating each travel path may also be obtained based on information related to the travel path. For example, assume that the passenger/driver's travel path is as shown in Table 1:
  • factors that may affect the passenger/driver's choice of travel path are time and weather.
  • Each factor is assigned an impact factor to indicate the magnitude of the factor's impact on the passenger/driver's final choice of travel path, as shown in Tables 2 and 3:
  • Table 3 The influence factor of weather factors on the passenger/driver's choice of travel route
  • the POI engine 110 may rank the passenger/driver's travel path based on the calculated probability.
  • the passenger/driver's travel route is arranged in descending order of the calculated probability. sequence.
  • the POI engine 110 transmits the sorted travel path list to the guest device 120 and/or the driver device 140. This step can be accomplished by passenger interface 230 and/or driver interface 240.
  • the travel path list may be displayed in the display unit 520 in the passenger equipment 120 and/or the driver equipment 140 and selected by the passenger and/or driver.
  • the most probable travel path in the travel path list may be directly filled into the corresponding service request information as a default travel path.
  • the POI engine 110 can directly transmit the travel path of the acquired passenger or driver without performing step 1120 and/or step 1130.
  • the travel route can be directly sent to the passenger/driver without having to calculate the probability of the travel route.
  • the probability of calculating the travel route is 100%, and the travel route is directly transmitted to the passenger/driver without performing step 1130.
  • modules or steps of the present application can be implemented by a general computing device, which can be concentrated on a single computing device or distributed in a network composed of multiple computing devices. Alternatively, they may be implemented by program code executable by the computing device so that they may be stored in the storage device by the computing device, or they may be fabricated into individual integrated circuit modules, or Multiple modules or steps are made into a single integrated circuit module. Thus, the application is not limited to any particular combination of hardware and software.
  • the POI engine 110 can receive traffic service request related information. This step can be accomplished by passenger interface 230 and/or driver interface 240.
  • the transportation service request sent by the passenger device is received through the passenger interface 230 and/or the driver interface 240, and the transportation service request is obtained.
  • Relevant feature information and basic information includes, but is not limited to, a combination of one or more of a departure time, an origination location, and destination information.
  • the related feature information includes, but is not limited to, originating and destination POI information, real-time weather information, real-time road condition information, driver preference information corresponding to each travel mode, number of idle drivers corresponding to each travel mode within a preset range, and road surface distance.
  • originating and destination POI information real-time weather information
  • real-time road condition information real-time road condition information
  • driver preference information corresponding to each travel mode
  • number of idle drivers corresponding to each travel mode within a preset range a preset range
  • road surface distance One or a combination of several.
  • the POI engine 110 determines, according to the related feature information and the basic information, travel information corresponding to the traffic service request for each single travel mode.
  • This step can be accomplished by decision unit 380 in processing module 210 in POI engine 110.
  • the determining unit 380 is configured to determine travel information of each single travel mode based on the related feature information and basic information.
  • the travel information may include an order transaction rate, a time consumption, a fee, and a walking distance.
  • the travel information corresponding to the taxi request in the single travel mode refers to the order transaction rate, time consumption, cost, and walking distance of each travel mode based on the taxi request.
  • the determining unit 380 is configured to respectively determine POI information corresponding to the origin and destination according to the origin and destination information; and for each travel mode, according to the originating The POI information, the destination POI information, the departure time, the real-time road condition information, the driver preference information corresponding to the travel mode, the number of idle drivers, and the order transaction rate of the travel mode are estimated; according to the origin, destination, and Travel mode The travel route is planned to obtain the road distance, travel time and congestion level, so as to estimate the total cost, walking distance and time consumption.
  • the determining unit 380 is further configured to determine, for the plurality of preset additional amount values, an order turnover rate corresponding to each preset additional amount value and a passenger's value for the preset additional amount Acceptance rate; according to the order transaction rate corresponding to each preset additional amount value and the acceptance rate of the passenger, the optimal additional amount value is obtained, and the order turnover rate corresponding to the optimal additional amount value is used as the final order transaction rate.
  • the server receives the taxi request, and analyzes the point of interest (POI) information corresponding to the origin and destination, such as whether it is a hospital, a cell, a business circle, or the like.
  • POI point of interest
  • the order transaction rate is estimated based on real-time traffic, time, start and end, and surrounding driver information.
  • an estimated value of the order turnover rate and a suggested tip value can be output, and the suggested tip value is used to increase the order turnover rate.
  • the cost is given according to the road distance, the travel time, and the congestion level corresponding to the route formed by the route planning result, Estimate time and distance, and add the cost and consumption to get the total cost. Thereby, travel information of a plurality of single travel modes is obtained.
  • step 1220 specifically includes the following sub-steps 1221, 1222, and 1223.
  • Figure 12-B is an exemplary flow diagram of the POI engine 110 processing travel information.
  • POI information corresponding to the origin and destination is determined according to the origin and destination information.
  • the travel mode is based on the origination POI information, the destination POI information, the departure time, the real-time traffic condition information, the driver preference information corresponding to the travel mode, and the number of idle drivers.
  • the turnover rate is estimated.
  • the step may be implemented by using a pre-established prediction model to predict an order turnover rate of each taxi mode request for the taxi.
  • the prediction model is a prediction model established according to relevant feature information of historical orders in a preset time period according to each travel mode, and the related feature information of the taxi request is a predictor of the prediction model, and each travel mode
  • the order transaction rate for the taxi request is the target variable of the predictive model.
  • the method further includes: determining, in step A01, the order transaction corresponding to each preset additional amount value according to the plurality of preset additional amount values. Rate and acceptance rate of passengers for this preset additional value.
  • the additional amount value is a tip. The best tip value is selected by predicting the order turnover rate and the acceptance rate of the passenger corresponding to the plurality of preset consumption values. It can be understood that this step can also obtain the acceptance rate of the order and the acceptance rate of the passenger to the preset additional amount value by establishing the prediction model in step 1222.
  • the additional amount value is a characteristic data in the prediction model.
  • step A02 according to the order transaction rate corresponding to each preset additional amount value and the acceptance rate of the passenger, the optimal additional amount value is obtained, and the order transaction rate corresponding to the optimal additional amount value is used as the final order transaction. rate.
  • travel route planning is performed according to the origin, destination, and travel mode to obtain road surface distance, travel time, and congestion level to estimate total cost, walking distance, and time consumption.
  • travel information such as tipping, order transaction rate, total cost, walking distance and time consumption of a plurality of single travel modes can be obtained.
  • the POI engine 110 is based on each single travel mode.
  • the row information is determined by a global optimization algorithm, and the travel information corresponding to the travel service request is obtained.
  • This step can be done by the calculation sub-unit 385 in the decision unit 380 in the processing module 210 in the POI engine 110.
  • the calculation sub-unit 385 determines the combined travel mode by using the global optimization algorithm according to the travel information of each single travel mode, and obtains the travel information of the combined travel mode by the determining unit 380.
  • the global optimization algorithm can be a greedy algorithm or the like.
  • the determining unit 380 and its calculating sub-unit 385 adopt a greedy algorithm according to the order transaction rate, time consumption, cost and walking distance of each single travel mode, and save time to determine the time-consuming from less to more.
  • a plurality of combined travel modes with a fee ranging from a small to a large amount are determined for the purpose of saving the cost, and the travel information corresponding to the taxi request is obtained for the plurality of combined travel modes.
  • step 1230 specifically includes the following steps:
  • step 1231 according to the order transaction rate, time consumption, cost and walking distance of each single travel mode, a greedy algorithm is adopted, and a plurality of combined travel modes that consume less time are determined to save time, and the plurality of travel modes are acquired.
  • the combined travel mode corresponds to the travel information of the taxi request;
  • step 1232 according to the order transaction rate, time consumption, cost and walking distance of each single travel mode, a greedy algorithm is adopted, and the cost is determined from the cost reduction to the target A plurality of combined travel modes, and acquiring travel information of the plurality of combined travel modes corresponding to the taxi request.
  • the global optimization algorithm can be separately output in two directions of saving time and saving cost, so that the passenger can select the travel mode according to his own needs. Steps 1231 and 1232 may both be performed, or only one of the steps may be performed.
  • step 1240 all the single travel modes and the combined travel modes are sorted according to the preset travel conditions and sent to the user equipment according to the travel information of the single travel mode and the travel information of the combined travel mode.
  • This step can be accomplished by the ordering unit 370 in the processing module 210 in the POI engine 110 and the passenger interface 230 and/or the driver interface 240. Root According to the travel information of each single travel mode and the travel information of the combined travel mode, the sorting unit 370 sorts the single travel mode and the combined travel mode according to the preset travel conditions and passes through the passenger interface 230 and/or the driver interface 240. Send a list of travel methods.
  • the sorting unit 370 is configured to record the transaction rate, time, cost, and walking distance of each combination travel mode according to the order transaction rate, time consumption, cost, and walking distance of each single travel mode, according to a preset Travel conditions sort all single travel modes and all combined travel modes.
  • the preset travel condition may include one or more of a preset travel distance range, a preset fee, and a preset time consumption. Specifically, this step is mainly to comprehensively sort a plurality of single travel modes and combined travel modes, and sort according to passenger input or system default travel conditions or sorting manner.
  • the method may further include the steps of: the passenger equipment 120 and/or the driver equipment 140 receiving each of the single travel modes and the combined travel modes arranged in order for the passenger to select the travel mode.
  • the passenger terminal device 120 and/or the driver device 140 includes a display unit 520 for displaying the received single travel mode and the combined travel mode list for the passenger to select the travel mode.
  • step 1240 may include order transaction rate, time consumption, cost, and walking distance according to each single travel mode, and the order transaction rate, time consumption, cost, and walking distance of each combination travel mode, according to preset travel.
  • the condition sorts all single travel modes and all combined travel modes.
  • the preset travel condition includes one or more of a preset travel distance range, a preset fee, and a preset time consumption. That is, the travel conditions can be set to multiple, such as the most economical and the walking distance is less than 1km.
  • the present embodiment utilizes the global data of the on-demand service system 105 and the knowledge of the geographic information system to actively help the passenger to find the most suitable travel mode.
  • the taxi transaction rate of the passenger's current peripheral orders is very low, and the passenger's order quality is not very high, which means that the probability of the passenger's taxi order failure will be very high; at this time, the system finds the car in the background.
  • the transaction rate is relatively high, and it is recommended to use the car preferentially.
  • the passengers are currently in the vicinity of a bus stop. After 5 minutes, a suitable bus will pass and the passengers can be pulled very close to the destination. In this way, the background can recommend the bus for passengers and tell the bus arrival time.
  • the backstage can use the bus or taxi in a comprehensive way.
  • the passengers are pulled by the bus to a position with a very high turnover rate.
  • the driver is also Relatively prefer this order for current passengers. Therefore, in the end, the background will give a variety of recommended travel modes, and give the passenger's estimated price, estimated time, and then the passengers choose their own travel mode.
  • the embodiment provides a travel mode planning method, and the plurality of recommended travel modes are obtained by the comprehensive information of the taxi software platform, and the plurality of recommended travel modes include a single travel mode and a combined travel mode; and the plurality of recommended travel modes are followed.
  • the preset sorting method is sorted, such as sorting according to cost, time-consuming or walking distance, for the passengers to select, thereby effectively increasing the order turnover rate, saving the time or cost of the taxi, and optimizing the passenger taxi experience.
  • the taxi software server After placing the order, the taxi software server detects that the order is a real-time request for the order, and analyzes that the destination belongs to the hospital, in the front door business circle. The information is sent to the order receiving program of each product line (ie, multiple travel modes), and the product lines are combined with the traffic data, the corresponding product line driver preference, the number of idle drivers, etc. to predict the transaction rate, and according to the corresponding tip value. Corresponding transaction probability and passenger acceptance, give the best tip value and transaction probability for each product line.
  • the results are as follows: ⁇ Taxis: tipping 5 yuan; transaction probability 0.8; total cost: 90 yuan; walking distance: 700 meters; time: 1.15 hours ⁇ ⁇ special car: tipping 0 yuan; transaction probability 0.9; total cost: 120 Yuan; walking distance: 200 meters: time-consuming: 1.05 hours ⁇ winding: tipping 5 yuan; transaction probability 0.8; total cost 60 yuan; walking distance: 800 meters; time: 1.2 hours ⁇ ⁇ bus: tip 0 yuan ; transaction probability: 1.0; total cost: 10 yuan; walking distance: 3km; time-consuming: 2 hours ⁇ .
  • the data request is sent to the route comprehensive program, and the route comprehensive program is gradually adjusted according to the greedy optimization algorithm according to the system default optimization mode or the passenger-specified optimization mode.
  • the currently selected optimization direction is the most cost-saving direction and requires a walking distance of less than 1 km.
  • the greedy algorithm adopted by the global optimization takes priority from the product line with the best optimization direction.
  • the second alternative optimal solution (such as a ride) is selected.
  • the components therein are logically divided according to the functions to be implemented, but the application is not limited thereto, and the components may be re-divided as needed. Alternatively, for example, some components may be combined into a single component, or some components may be further broken down into more subcomponents.
  • the various component embodiments of the present application can be implemented in hardware, or in a software module running on one or more processors, or in a combination thereof.
  • a microprocessor or digital signal processor may be used in practice to implement some or all of the functionality of some or all of the components in accordance with embodiments of the present application.
  • the application can also be implemented as a device or device program (e.g., a computer program and a computer program product) for performing some or all of the methods described herein.
  • Such a program implementing the present application may be stored on a computer readable medium or may be in the form of one or more signals. Such signals may be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.
  • FIG. 13 is an exemplary flow diagram of the POI engine 110 detecting vehicle status, in accordance with some embodiments of the present application.
  • the POI engine 110 can receive a geographic data stream from the vehicle and acquire a plurality of geographic coordinates of the vehicle over a given time period. This step can be accomplished by passenger interface 230 and/or driver interface 240.
  • the geographic data stream may be acquired using a positioning technology including, but not limited to, Global Positioning System (GPS) technology; Global Navigation Satellite System (GLONASS) technology; Beidou navigation system technology; Galileo positioning system (Galileo) technology; quasi-zenith satellite system (QAZZ) technology; base station positioning technology; and WiFi positioning technology.
  • GPS Global Positioning System
  • GLONASS Global Navigation Satellite System
  • Beidou navigation system technology Beidou navigation system technology
  • Galileo positioning system (Galileo) technology Galileo positioning system
  • QAZZ quasi-zenith satellite system
  • base station positioning technology base station positioning technology
  • WiFi positioning technology WiFi positioning technology
  • the GPS data stream obtained by the GPS positioning technique includes a plurality of GPS coordinates reported by the vehicle in real time at a given time frequency, wherein each GPS coordinate corresponds to the vehicle at each acquisition The location of the time point.
  • the vehicle is in a plurality of GPS coordinates uploaded in real time at a given time frequency, wherein each GPS coordinate corresponds to a location of the vehicle at each acquisition time point.
  • the GPS module on the smart device is used to obtain the current GPS coordinates of the vehicle in real time; the GPS data collected at a certain frequency is uploaded in real time through the long connection service through the taxi software.
  • address resolution unit 310 in processing module 210 in POI engine 110 may extract a plurality of GPS coordinates within a given time period associated with a given point in time from the GPS data stream.
  • the latitude, t represents the GPS data acquisition time point.
  • the POI engine 110 calculates the center point coordinates of the plurality of geographic coordinates, and the distance and direction distribution of each geographic coordinate to the center point coordinates. This step can be done by the computing sub-unit 385 in the processing module 210 in the POI engine 110.
  • the calculation sub-unit 385 is configured to calculate center point coordinates of a plurality of GPS coordinates; calculate Euclidean distances and radians for each GPS coordinate to center point coordinates; and calculate each for each Euclidean distance and each radian Normalized distance and direction distribution of GPS coordinates to the coordinates of the center point.
  • the Euclidean distance is one of the commonly used distance calculation methods in cluster analysis.
  • the distance calculation methods include, but are not limited to, Euclidean distance, Manhattan distance, Mahalanobis distance, and/or Hamming distance, and the like.
  • Equation 4 the Euclidean distance ⁇ (G j , g 0 ) and the radian ⁇ (G j , g 0 ) of each GPS coordinate to the coordinates of the center point are calculated.
  • the normalized distance S of each GPS coordinate to the coordinates of the center point is calculated based on each Euclidean distance ⁇ (G j , g 0 ) and each radian ⁇ (G j , g 0 ).
  • (G j , g 0 ) and the direction distribution ⁇ (G j , g 0 ) W in Equation 4 is the threshold selected based on experimental data and practical experience:
  • the state of the vehicle is determined based on the distance and direction distribution.
  • This step can be accomplished by decision unit 380 in processing module 210 in POI engine 110.
  • decision unit 380 and its calculation sub-unit 385 calculate an average normalized distance and a total direction distribution based on the normalized distance and direction distribution of each GPS coordinate to the center point coordinates; and based on the average
  • a normalized distance and a first threshold and a total direction distribution and a second threshold determine the state of the vehicle. For example, the normalized distance S(G j , g 0 ) and the direction distribution ⁇ (G j , g 0 ) of each GPS coordinate to the center point coordinate obtained by the calculation subunit 385 are calculated.
  • the vehicle state R is determined according to Equation 8, where 1 indicates that the vehicle is stationary, and 0 indicates that the vehicle is not stationary; Representing a first threshold, ⁇ represents a second threshold, and two thresholds are selected based on experimental data and actual experience.
  • the vehicle stationary state may also be a low speed driving state.
  • determining, by the POI engine 110, the state of the vehicle may further include: storing a state of the vehicle and coordinates of a center point; and transmitting coordinates of the vehicle state and the center point in response to the vehicle state query request.
  • the storage module 220 in the POI engine 110 can be used to store the state of the vehicle and the coordinates of the center point.
  • the passenger interface 230 and/or the driver interface 240 in the POI engine 110 can be used to transmit the vehicle state and coordinates of the center point in response to a vehicle status inquiry request.
  • the state R and the center point coordinate g_0 of the vehicle may be saved to the storage device; when the on-demand service system 105 sends the vehicle status query request, the vehicle corresponding to the query time point is read from the storage device The state R and the center point coordinate g 0 are sent to the on-demand service system 105.
  • the vehicle reports GPS data to the on-demand service system 105 at a frequency via the passenger terminal device 120 and/or the driver device 140.
  • the passenger interface 230 and/or the driver interface 240 in the POI engine 110 receives GPS data streams from the passenger end device 120 and/or the driver end device 140; the address resolution unit 310 acquires a plurality of GPS coordinates of the vehicle for a given period of time; The calculation sub-unit 385 calculates center point coordinates of the plurality of GPS coordinates, and a distance and direction distribution of each GPS coordinate to the center point coordinates; and based on the distance and the direction distribution, the determination unit 380 determines the state of the vehicle.
  • the determining unit 380 can store the state and center point coordinates of the vehicle in the storage module 220 and/or the database 130 in the POI engine 110, and in response to the vehicle status query request sent by the on-demand service system 105, from the storage module 220 and/or The vehicle state and center point coordinates corresponding to the query time point are read in the database 130, and the vehicle state data is transmitted to the on-demand service system 105.
  • computing unit 350 may calculate a service fee based on the state of the vehicle and/or multiple GPS coordinates within a given time period.
  • the computing unit 350 and the computing sub-unit 385 of the determining unit 380 can calculate a service fee based on the determined vehicle state.
  • computing unit 350 or computing sub-unit 385 can calculate a service fee based on the state of the vehicle and the duration of the different states of the vehicle.
  • the method of pricing by time that is, the service charge per minute is used.
  • one or more unit time rates can be set.
  • the threshold on which the low-speed driving state is determined may be a preset speed value, or may be a dynamic speed value determined based on factors such as the location and time of the vehicle.
  • the multiple phases of the low speed driving state may correspond to a plurality of different speed ranges. When there are multiple stages in the low-speed driving state, you can set different unit time rates for these states, or you can set the same unit time rate for two or more of them.
  • the method of counting by distance that is, the service cost per unit distance is used.
  • one or more unit distance rates can be set.
  • the threshold on which the high-speed driving state is determined may be a preset speed value, or may be a dynamic speed value determined based on factors such as the location and time of the vehicle.
  • the process of completing an order may include multiple transitions of the vehicle state, and the calculation sub-unit 385 may count the duration of the vehicle stationary state or the low speed operating state, and then calculated by the computing unit 350 or based on the unit time rate. Service costs for the stationary and low-speed driving phases.
  • the calculation sub-unit 385 can count the duration and distance of the high-speed running state of the vehicle, and then the calculation unit 350 calculates the service charge of the vehicle in the high-speed running state based on the unit distance rate. Based on the service charge of the stationary state phase, the low speed running state, and the high speed running state, the calculating unit 350 can finally calculate the total service fee for the entire process.
  • the service fee can be calculated during the transportation service process, ie the calculation of the fee is real-time.
  • the service fee can be calculated uniformly after the end of the transportation service.
  • the calculation unit 350 may also calculate the low speed running state at a unit distance rate.
  • the calculation unit 350 may calculate the high speed running state at a unit time rate. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of this application are intended to be included within the scope of the present application.
  • modules or steps of the present application can be implemented by a general computing device, which can be concentrated on a single computing device or distributed over a network composed of multiple computing devices. Alternatively, they may be implemented by program code executable by the computing device so that they may be stored in the storage device by the computing device, or they may be fabricated into individual integrated circuit modules, or many of them Module or step The steps are made into a single integrated circuit module.
  • the application is not limited to any particular combination of hardware and software.
  • the POI engine 110 can obtain a plurality of geographic coordinates of the passenger/driver for a given time period. This step can be accomplished by passenger interface 230 and/or driver interface 240.
  • location techniques are utilized to obtain location information for a plurality of geographic coordinates of a passenger/driver over a given time period.
  • the given time period may be a period of time determined based on historical experience and/or test data, for example, ten minutes, half an hour, one hour, and the like.
  • the passenger/driver uploads multiple coordinates at regular intervals, for example every 10 seconds, for a given period of time. Each coordinate indicates the location of the passenger/driver at the time of upload.
  • the POI engine 110 divides the plurality of geographic coordinates into a plurality of groups. This step can be done by the grouping unit 340 in the processing module 210 in the POI engine 110.
  • the plurality of geographic coordinates are divided into a plurality of groups using at least one clustering algorithm, wherein the clustering algorithm includes but is not limited to a K-MEANS algorithm; a K-MEDOIDS algorithm; and CLARANS A combination of one or more of algorithms and the like.
  • the clustering algorithm includes but is not limited to a K-MEANS algorithm; a K-MEDOIDS algorithm; and CLARANS A combination of one or more of algorithms and the like.
  • Each packet contains at least one data record
  • the algorithm first gives an initial grouping method, and later changes the grouping by iterative iteration, so that the improved grouping scheme is improved compared with the previous one.
  • the criterion for improvement may be that the records in the same group are as close to or related as possible to each other, and the records in the different groups are as far apart or different as possible.
  • the position coordinates are grouped based on the distance between the position coordinates. After the grouping is completed, the position coordinates in the same group are as close as possible to each other (ie, the distance between the coordinates is as small as possible), and the position coordinates in different groups are as Stay away (ie the distance between the coordinates is as large as possible).
  • a plurality of obtained positioning information may be divided into a plurality of groups (ie, multiple classes) by using a clustering algorithm, and the number of groups (ie, the number of classes) may be Values determined based on historical experience or experimental data, such as K (N ⁇ K > 0).
  • the POI engine 110 acquires location information for the center point in each packet, respectively, and the distance between each location and the location of the center point in the group to which it belongs. This step can be accomplished by address resolution unit 310 and computing unit 350 in processing module 210 in POI engine 110. According to some embodiments of the present application, separately obtaining location information of a center point in each packet includes: calculating an average value of all location information in each packet; and using the average value as the center in each packet The location information of the point.
  • the grouping unit 340 divides the N coordinates into K groups, and the calculation unit 350 calculates an average value for all the coordinates in each group, so that K average coordinate values can be obtained, and the K average coordinate values will be respectively taken as K The coordinates of the center point of the group.
  • the distance between each obtained position and the position of the center point in the group to which the position belongs is calculated based on the position information of the center point in each of the separately calculated groups. For example, for the N coordinates obtained by the positioning technique, the distance between each coordinate and the center point coordinates of the group in which the coordinates are located is calculated, so that a total of N distance values can be obtained.
  • the POI engine 110 obtains a maximum of the distance values of all geographic coordinates and the set of center points in each group. This step can be accomplished by decision unit 380 in processing module 210 in POI engine 110 and its computing sub-unit 385. For example, based on a total of N distance values obtained as described above, the maximum of all N distance values is calculated and determined, and can be set to R max .
  • the POI engine 110 determines whether the location information of the passenger/driver is abnormal based on the maximum value of the distance. This step may be performed by decision unit 380 in processing module 210 in POI engine 110. According to some embodiments of the present application, determining whether the location information of the passenger/driver is abnormal specifically comprises: comparing a maximum value of the distance with a predetermined threshold; and determining, based on a result of the comparing, whether the positioning information of the passenger/driver is abnormal.
  • the predetermined thresholds described herein are thresholds of distances determined from historical experience or experimental data. For example, in one scenario, the passenger/driver is in a state of motion, such as a driver in motion, a passenger in motion.
  • the threshold is set to 50 meters. Then, the driver/passenger position should be changed over a period of time (eg, 30 minutes). If the location information uploaded by the driver/passenger is too concentrated during this time (for example, R max ⁇ 50 meters), the driver/passenger's positioning information is abnormal during this time. At this time, the driver/passenger can be prompted to find out the cause of the positioning abnormality, for example, whether the positioning function of the positioning device is turned off or the like. As another example, in another scenario, the driver/passenger is in a non-exercise state or a slow motion state, such as a pedestrian who is stationary or slow walking, or a driver who experiences a serious traffic jam.
  • a non-exercise state or a slow motion state such as a pedestrian who is stationary or slow walking, or a driver who experiences a serious traffic jam.
  • the threshold is set to 1000 meters. Then, the driver/passenger position should be substantially constant or slowly changing over a period of time (eg, 5 minutes). Then, if the location information uploaded by the driver/passenger is too scattered during this time (for example, R max >1000 m), the driver/passenger positioning information is abnormal during this time.
  • the selection of the threshold and the determination of the driver/passenger location information anomaly according to the relationship between the maximum value and the threshold (eg, greater than, less than, equal to, not less than, no greater than, etc.) will depend on the specific scenario and implementation.
  • the driver/passenger setting in the mode will depend on the specific scenario and implementation. The driver/passenger setting in the mode.
  • computing unit 350 can calculate a service fee based on the positioning information and/or the plurality of geographic coordinates.
  • decision unit 380 and its calculation sub-unit 385 can further calculate the service fee based on the determined location information without anomalies.
  • the judgment of the abnormality of the positioning information can be used in different scenarios.
  • the judgment of the abnormality of the positioning information can be used to decide whether to push an order to a driver. For example, a driver gives his or her own position through the driver device 140 and requests the POI engine 110 to provide service to a passenger; if the POI engine 110 determines that the driver location information is abnormal, the driver's order may be refused to be assigned to the driver.
  • the determination of the abnormality of the positioning information can be used for pricing. If the driver's location information is found to be abnormal, the pricing of the service can be adjusted accordingly, or the POI engine 110 can issue a reminder to the passenger or driver.
  • example line flow diagrams may be described as a flowchart, a flow chart, a data flow diagram, a structural diagram, or a block diagram process.
  • a flowchart can describe a step as a sequential process, The process can also perform many operations in parallel, concurrently or simultaneously. In addition, the order of the steps can be rearranged. When the steps of the process are completed, the process can be terminated, but can also have additional steps not included in the figure.
  • Processes may correspond to methods, functions, programs, subroutines, subroutines, and the like.
  • the termination of the process may correspond to a return of the function to the calling function or the main function.
  • FIG. 15-A is an exemplary flow diagram of the POI engine 110 determining that the location information of the user is abnormal.
  • the user may be a consumer, a service party, etc., and may be a passenger or a driver.
  • the POI engine 110 may acquire first positioning information of the user within a preset time period. This step can be accomplished by passenger interface 230 and/or driver interface 240.
  • a plurality of geographic coordinate information of a user within a preset time period is acquired by using a positioning technique.
  • a positioning technique For the types and details of the positioning technology, refer to the foregoing description, and details are not described herein again.
  • GPS coordinate information obtained by the GPS positioning technique includes, but is not limited to, longitude, latitude, and time stamp information.
  • the passenger interface 230 and/or the driver interface 240 are configured to obtain first positioning information of the passenger terminal device 120 and/or the driver device 140 for a preset time period, wherein the first positioning information may be through GPS GPS coordinate information obtained by positioning technology.
  • the POI engine 110 obtains second location information of the passenger/driver for a preset period of time.
  • This step can be accomplished by passenger interface 230 and/or driver interface 240.
  • a positioning technique is used to acquire a plurality of places of a passenger/driver within a preset time period Coordinate information.
  • the second positioning information includes, but is not limited to, longitude, latitude and time stamp information. It should be noted that the preset time period in step 1510 and step 1520 is the same time period, and the first positioning information and the second positioning information are acquired by different positioning technologies.
  • the second location information of the passenger/driver is available through the passenger interface 230 and/or the driver interface 240 in accordance with base station location techniques or WiFi location techniques.
  • the POI engine 110 compares the first location information with the second location information. This step can be accomplished by decision unit 380 in processing module 210 in POI engine 110.
  • the calculation sub-unit 385 in the determination unit 380 calculates the deviation of the first positioning information and the second positioning information, and the determination unit 380 compares the deviation with the first preset threshold.
  • the deviation between the first positioning information and the second positioning information is a distance between the first positioning coordinate and the second positioning coordinate. The distance between the two is compared to a first predetermined threshold.
  • the first positioning information may be GPS coordinate information obtained by a GPS positioning technology
  • the second positioning information may be second coordinate information obtained by a base station positioning technology and/or a WiFi positioning technology.
  • the first preset threshold is set according to the error of the base station positioning or the WiFi positioning. Generally, the error of the base station positioning or the WiFi positioning is at the 100-meter level, and the first preset threshold may be set at the 100-meter level. .
  • it may directly jump to step 1550 to determine whether the positioning information is abnormal, and step 1540 is not required to be performed.
  • the POI engine 110 determines if the location information is abnormal. This step can be accomplished by decision unit 380 in processing module 210 in POI engine 110. If the determining unit 380 determines that the deviation is greater than or equal to the first preset threshold, it is determined that the first positioning information is abnormal.
  • the first positioning information may be GPS coordinate information, and when it is determined that the first positioning information is abnormal, the GPS coordinate information is determined to be forged coordinate information. If the determining unit 380 determines that the deviation is less than the first preset threshold, the method may further include:
  • step 1540 the POI engine may acquire a base station number within a range that is less than a preset distance from the current address of the passenger/driver and a signal strength of the base station within a preset time period; according to the GPS coordinate information, Base station number and location Describe the signal strength of the base station, and determine whether the GPS coordinate information is forged coordinate information. This step can be accomplished by the passenger interface 230 and/or the driver interface 240 in the POI engine 110.
  • the POI engine obtains the current address information of the passenger/driver through the passenger interface 230 and/or the driver interface 240 prior to step 1540; passes the address in the processing module 210 based on the acquired current address of the passenger/driver
  • the parsing unit 310 determines a base station that is less than a preset distance from the current address of the passenger/driver.
  • the current address of the passenger/driver may be coordinate information acquired by a base station positioning technology or a WiFi positioning technology.
  • step 1540 includes steps 1551-1553.
  • FIG. 15-B is an exemplary embodiment in which the POI engine 110 determines that the positioning information is abnormal.
  • the POI engine 110 may acquire a base station number within a range of a distance from the current address of the passenger/driver that is less than a preset distance and a signal strength of the base station within a preset time period.
  • the base station number is a serial number used to uniquely identify the base station.
  • One base station corresponds to one base station number. This step can be accomplished by the passenger interface 230 and/or the driver interface 240 in the POI engine 110.
  • the POI engine 110 may compare the change value of the GPS coordinates in the preset time period with the second preset threshold, and change the signal strength of the base station in the preset time period to a third preset threshold. Compare. This step can be accomplished by decision unit 380 in processing module 210 in POI engine 110 and its computing sub-unit 385.
  • the change value of the GPS coordinates in the preset time period refers to the difference between the GPS coordinates of the start time point of the preset time period and the GPS coordinates of the end time point of the preset time period.
  • the change value of the signal strength of the base station in the preset time period refers to the difference between the signal strength of the base station at the start time point of the preset time period and the signal strength of the same base station at the end time point of the preset time period.
  • the preset time period is from 1:10 to 1:30.
  • the GPS coordinate change value in the preset time period is the GPS coordinate of the terminal at 1:10, and the GPS coordinate of the terminal at 1:30.
  • the change value of the signal strength of the base station in the preset time period is the difference between the signal strength of the base station at 1:10 and the signal strength of the same base station at 1:30. It should be noted that the preset time period can be adjusted according to actual conditions and/or actual needs, and can be 5 minutes, 20 minutes, 30 minutes, 1 hour, and the like.
  • the POI engine determines if the first location information is abnormal. This step can be accomplished by decision unit 380 in processing module 210 in POI engine 110. If the determining unit 380 determines that the change value of the GPS coordinate is greater than a second preset threshold, and the base station number does not change If the change value of the signal strength of the base station is smaller than the third preset threshold, it is determined that the first positioning information is abnormal, that is, the GPS coordinate information in the predetermined time period is forged coordinate information.
  • the determining unit 380 determines that the change value of the GPS coordinate is less than or equal to a second preset threshold, and the base station number changes or the change value of the signal strength of the base station is greater than or equal to a third preset threshold, determining the first positioning
  • the information is abnormal, that is, the GPS coordinate information within the predetermined time period is determined to be forged coordinate information.
  • computing unit 350 can calculate a service fee based on the positioning information and/or the plurality of geographic coordinates.
  • decision unit 380 and its calculation sub-unit 385 can further calculate the service fee based on the determined location information without anomalies.
  • the determination of the location information anomaly may also be dedicated to the processing of the passenger location information.
  • the determination of the location information anomaly can be applied to the determination of whether the POI engine 110 responds to the passenger order request.
  • a passenger provides his/her location information through the passenger terminal device 120 and requests a driver to provide service to the POI engine 110; if the POI engine 110 determines that the passenger location information is abnormal, the POI engine 110 may further request more information from the passenger. Or prompting the passenger to locate the information abnormally, or sending a relocation request, or rejecting the passenger's order request.
  • the passenger requests on-demand service at different locations in a short period of time (eg, at different intervals relative to the time interval).
  • the POI engine 110 can further query the passenger for more information about different service requests, such as whether different service requests are for the same passenger, if it is for a different passenger, another passenger's contact information, confirmation of the order method, and the like. If the departure point entered by the passenger on the passenger terminal device 120 is far from the current position of the passenger terminal device 120, for example, 10 kilometers, and the specified departure time is relatively close according to the current system time of the passenger terminal device 120, for example, 10 In minutes or 20 minutes, the POI engine 110 may further send a confirmation message to the passenger terminal device 120 requesting the passenger to confirm the entered departure location and/or departure time.
  • the POI engine 110 can also request other information from the passenger, such as the surrounding Public or commercial facilities, important landmark buildings, street names, etc., to determine if there is a positioning anomaly in the passenger equipment 120.
  • the components therein are logically divided according to the functions to be implemented, but the application is not limited thereto, and the components may be re-divided as needed. Alternatively, for example, some components may be combined into a single component, or some components may be further broken down into more subcomponents.
  • the various component embodiments of the present application can be implemented in hardware, or in a software module running on one or more processors, or in a combination thereof.
  • a microprocessor or digital signal processor may be used in practice to implement some or all of the functionality of some or all of the components in accordance with embodiments of the present application.
  • the application can also be implemented as a device or device program (e.g., a computer program and a computer program product) for performing some or all of the methods described herein.
  • Such a program implementing the present application may be stored on a computer readable medium or may be in the form of one or more signals. Such signals may be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.
  • Figure 16 depicts the structure of a mobile device that can be used to implement a particular system disclosed in this application.
  • the user device for displaying and interacting with location related information is a mobile device 1600 including, but not limited to, a smartphone, a tablet, a music player, a portable game console, a Global Positioning System (GPS) receiver, Wearable computing devices (such as glasses, watches, etc.), or other forms.
  • the mobile device 1600 in this example includes one or more central processing units (CPUs) 1640, one or more graphics processing units (GPUs) 1630, a display 1620, a memory 1660, and an antenna 1610, such as A wireless communication unit, storage unit 1690, and one or more input output (I/O) devices 1650.
  • CPUs central processing units
  • GPUs graphics processing units
  • any other suitable components including but not limited to a system bus or controller (not shown), may also be included in the mobile device 1600.
  • a mobile operating system 1670 such as iOS, Android, Windows Phone, etc.
  • applications 1680 can be loaded into memory 1660 from storage unit 1690 and executed by central processor 1640.
  • Application 1680 may include a browser or other mobile application suitable for receiving and processing location related information on mobile device 1600.
  • the passenger/driver interaction with the location related information may be obtained by the input/output system device 1650 and provided to the POI engine 110, and/or other components of the system 100, such as through the network 150.
  • a computer hardware platform can be utilized as a hardware platform for one or more of the elements described above (eg, POI engine 110, and/or FIG. 1 Other components of system 100 described in -15).
  • the hardware elements, operating systems, and programming languages of such computers are common in nature, and it is assumed that those skilled in the art are familiar enough with these techniques to be able to provide the information needed for on-demand services using the techniques described herein.
  • a computer containing user interface elements can be used as a personal computer (PC) or other type of workstation or terminal device, and can be used as a server after being properly programmed.
  • PC personal computer
  • Those skilled in the art will be recognized to be familiar with such structures, programs, and general operations of such computer devices, and thus all drawings do not require additional explanation.
  • Figure 17 depicts an architecture of a computer device that can be used to implement a particular system disclosed in this application.
  • the particular system in this embodiment utilizes a functional block diagram to describe a hardware platform that includes a user interface.
  • a computer can be a general purpose computer or a computer with a specific purpose. Both computers can be used to implement the particular system in this embodiment.
  • Computer 1700 can be used to implement any component that currently provides the information needed for on-demand service.
  • the POI engine 110 can be implemented by a computer such as the computer 1700 through its hardware devices, software programs, firmware, and combinations thereof.
  • FIG. 17 only one computer is depicted in FIG. 17, but the related computer functions described in this embodiment for providing the information required for on-demand services can be implemented in a distributed manner by a similar set of platforms. Dispose of the processing load of the system.
  • Computer 1700 includes a communication port 1750 to which is connected a network that implements data communication.
  • Computer 1700 also includes a central processing unit (CPU) unit for executing program instructions comprised of one or more processors.
  • An exemplary computer platform includes an internal communication bus 1710, Different forms of program storage unit and data storage unit, such as hard disk 1770, read only memory (ROM) 1730, random access memory (RAM) 1740, various data files that can be used for computer processing and/or communication, and CPU Possible program instructions executed.
  • Computer 1700 also includes an input/output component 1760 that supports input/output data flow between the computer and other components, such as user interface 1780. Computer 1700 can also accept programs and data over a communications network.
  • Tangible, permanent storage media includes the memory or memory used by any computer, processor, or similar device or associated module.
  • various semiconductor memories, tape drives, disk drives, or the like that can provide storage functions for software at any time.
  • All software or parts of it may sometimes communicate over a network, such as the Internet or other communication networks.
  • Such communication can load software from one computer device or processor to another.
  • a system that loads from a management server or host computer of an on-demand service system to a computer environment, or other computer environment that implements the system, or a similar function associated with the information needed to provide on-demand services. Therefore, another medium capable of transmitting software elements can also be used as a physical connection between local devices, such as light waves, electric waves, electromagnetic waves, etc., through cable, fiber optic cable or air.
  • Physical media used for carrier waves such as cables, wireless connections, or fiber optic cables can also be considered as media for carrying software.
  • a computer readable medium can take many forms, including but not limited to, a tangible storage medium, carrier medium or physical transmission medium.
  • Stable storage media include: optical or magnetic disks, as well as storage systems used in other computers or similar devices that enable the implementation of the system components described in the figures.
  • Unstable storage media include dynamic memory, such as the main memory of a computer platform.
  • Tangible transmission media include coaxial cables, copper cables, and fiber optics, including the circuitry that forms the bus within the computer system.
  • Carrier transmission medium can transmit electrical signals, electromagnetic signals, and acoustic signals Or lightwave signals, which can be generated by radio frequency or infrared data communication methods.
  • Typical computer readable media include hard disks, floppy disks, magnetic tape, any other magnetic media; CD-ROM, DVD, DVD-ROM, any other optical media; perforated cards, any other physical storage media containing aperture patterns; RAM, PROM , EPROM, FLASH-EPROM, any other memory slice or tape; a carrier, cable or carrier for transmitting data or instructions, any other program code and/or data that can be read by a computer. Many of these forms of computer readable media appear in the process of the processor executing instructions, passing one or more results.

Abstract

一种为按需服务提供信息的方法，包括：接收来自一个乘客端设备（120）的一个乘客的服务请求信息，所述服务请求信息包括所述乘客的始发地位置；获取与所述乘客相关的历史服务请求信息；至少部分基于所述乘客的始发地位置与所述历史服务请求信息，确定出行路径相关信息。同时披露了一种实施上述方法的系统（105）。

Description

一种为按需服务提供信息的方法及系统
交叉引用
本申请要求以下申请的优先权：
2015年1月27日提交的编号为CN201510039939.3的中国申请；
2015年1月29日提交的编号为CN201510048217.4的中国申请；
2015年2月10日提交的编号为CN201510070073.2的中国申请；
2015年3月10日提交的编号为CN201510105381.4的中国申请；
2015年4月1日提交的编号为CN201510151590.2的中国申请；
2015年5月12日提交的编号为CN201510239402.1的中国申请；
2015年5月28日提交的编号为CN201510284601.4的中国申请；
2015年7月31日提交的编号为CN201510464596.5的中国申请；
2015年9月16日提交的编号为CN201510591079.4的中国申请；
2015年12月25日提交的编号为CN201510991394.6的中国申请；以及
2015年12月25日提交的编号为CN201511000093.9的中国申请。
上述申请的内容以引用方式被包含于此。
技术领域
本申请涉及为按需服务提供信息的系统及方法，尤其是涉及应用移动互联网技术和数据处理技术预测出行目的地的方法及系统。
背景技术
目前，按需服务应用的使用越来越普遍。例如，随着城市的快速发展，交通服务已成为社会各阶层人士的普遍需求。同时，移动互联网的高速发展，以及智能设备特别智能导航与智能手机的普及，打车系统平台的使用已经越来越普遍，对人们的出行带来了极大的便利。
对于交通服务的系统后台，如果能够根据乘客/司机的出行规律，预测乘客/司机的目的地或出行路径，可以提高交通服务双方的用户体验。
简述
根据本申请的一个方面，提供了一种为按需服务提供信息的方法，该方法包括接收来自一个乘客端设备的一个乘客的服务请求信息，所述服务请求信息包括所述乘客的始发地位置；获取与所述乘客相关的历史服务请求信息；至少部分基于所述乘客的始发地位置与所述历史服务请求信息，确定出行路径相关信息。
根据本申请的另一个方面，提供了一种为按需服务提供信息的系统，包括：一种计算机可读的存储媒介，被配置为存储可执行模块，包括：服务请求方接口模块，被配置为接收来自一个乘客端设备的一个乘客的服务请求信息，所述服务请求信息包括所述乘客的始发地位置；处理模块，被配置为：1)获取与所述乘客相关的历史服务请求信息；2)至少部分基于所述乘客的始发地位置与所述历史服务请求信息，确定出行路径相关信息；一个处理器，所述处理器能够执行所述计算机可读的存储媒介存储的可执行模块。
根据本申请的一个实施例，所述服务请求信息包括一个时间信息。
根据本申请的一个实施例，所述出行路径相关信息包括至少一种下列信息：一个目的地；一个由所述乘客的当前位置到达所述目的地的路径；上述路径的距离。
根据本申请的一个实施例，所述目的地是基于一种分类模型所确定的。
根据本申请的一个实施例，所述分类模型是基于至少一个地点类型的。
根据本申请的一个实施例，为按需服务提供信息的方法进一步包括将所述出行路径相关信息发送给所述乘客端设备。
根据本申请的一个实施例，为按需服务提供信息的方法进一步包括接收来自所述乘客端设备的乘客对所述出行路径相关信息的处理。
根据本申请的一个实施例，所述历史服务请求信息包括至少一种下列信息：一个历史始发地；一个历史目的地；一个由所述乘客的历史始发地到达所述历史目的地的历史路径；上述历史路径的距离。
根据本申请的一个实施例，为按需服务提供信息的方法进一步包括确定一个服务费用。
根据本申请的一个实施例，确定所述服务费用包括：获取来自一个司机在多个时间点的多个位置信息；至少部分基于所述多个位置信息，计算所述服务费用。
附图描述
在此所述的附图用来提供对本申请的进一步理解，构成本申请的一部分，本申请的示意性实施例及其说明用于解释本申请，并不构成对本申请的限定。各图中相同的标号表示相同的部件。
图1-A是根据本申请的一些实施例所示的一个包含按需服务系统的网络环境的示意图；
图1-B是根据本申请的一些实施例所示的一个包含按需服务系统的网络环境的另一个示意图；
图2是根据本申请的一些实施例所示的一种按需服务系统的示例性系统图；
图3是根据本申请的一些实施例所示的POI引擎中的处理模块示例性框图；
图4-A是根据本申请的一些实施例所示的POI引擎中的乘客接口的示例性框图；
图4-B是根据本申请的一些实施例所示的POI引擎中的司机接口的示例性框图；
图5是根据本申请的一些实施例所示用户端设备的示例性框图；
图6是根据本申请的一些实施例所示的数据库的示例性框图；
图7是根据本申请的一些实施例所示的确定目的地相关信息的流程图；
图8是根据本申请的一些实施例所示的乘客端设备上接收目的地相关信息的示例性实施例；
图9-A是根据本申请的一些实施例所示的预测当前目的地相关信息的示例性实施例；
图9-B是根据本申请的一些实施例所示的乘客端设备上接收并处理目的地相关信息的示例性实施例；
图10-A是根据本申请的一些实施例所示的生成目的地相关信息的示例性流程图；
图10-B是根据本申请的一些实施例所示的建立POI分类模型的示例性流程图；
图11是根据本申请的一些实施例所示的POI引擎向用户提供出行路径的示例性流程图。
图12-A是根据本申请的一些实施例所示的POI引擎向用户提供出行方式规划的示例性流程图；
图12-B是根据本申请的一些实施例所示的POI引擎处理出行信息的示例性流程图；
图13是根据本申请的一些实施例所示的POI引擎检测车辆状态的示例性流程图；
图14是根据本申请的一些实施例所示的POI引擎确定用户的定位信息异常的示例性流程图；
图15-A是根据本申请的一些实施例所示的POI引擎确定用户的定位信息异常的示例性流程图；
图15-B是根据本申请的一些实施例所示的POI引擎判断定位信息异常的示例性流程图；
图16显示的是一个移动设备的结构，该移动设备可以实施本申请中披露的特定系统；和
图17显示的是一个计算机的结构，该计算机可以实施本申请中披露的特定系统。
具体描述
为了更清楚地说明本申请的实施例的技术方案，下面将对实施例描述中所需要使用的附图作简单的介绍。显而易见地，下面描述中的附图仅仅是本申请的一些示例或实施例，对于本领域的普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图将本申请应用于其他类似情景。除非从语言环境中显而易见或另做说明，图中相同标号代表相同结构 或操作。
如本申请和权利要求书中所示，除非上下文明确提示例外情形，“一”、“一个”、“一种”和/或“该”等词并非特指单数，也可包括复数。一般说来，术语“包括”与“包含”仅提示包括已明确标识的步骤和元素，而这些步骤和元素不构成一个排它性的罗列，方法或者设备也可能包含其他的步骤或元素。
虽然本申请对根据本申请的实施例的系统中的某些模块做出了各种引用，然而，任何数量的不同模块可以被使用并运行在客户端和/或服务器上。所述模块仅是说明性的，并且所述系统和方法的不同方面可以使用不同模块。
本申请中使用了流程图用来说明根据本申请的实施例的系统所执行的操作。应当理解的是，前面或下面操作不一定按照顺序来精确地执行。相反，可以按照倒序或同时处理各种步骤。同时，也可以将其他操作添加到这些过程中，或从这些过程移除某一步或数步操作。
本申请的实施例可以应用于不同的运输系统，不同的运输系统包括但不限于陆地、海洋、航空、航天等中的一种或几种的组合。例如，出租车、专车、顺风车、巴士、火车、动车、高铁、地铁、船舶、飞机、飞船、热气球、无人驾驶的交通工具、收/送快递等应用了管理和/或分配的运输系统。本申请的不同实施例应用场景包括但不限于网页、浏览器插件、客户端、定制系统、企业内部分析系统、人工智能机器人等中的一种或几种的组合。应当理解的是，本申请的系统及方法的应用场景仅仅是本申请的一些示例或实施例，对于本领域的普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图将本申请应用于其他类似情景。例如，其他类似的服务接单系统。
本申请描述的“乘客”、“顾客”、“需求者”、“服务请求者”、“服务请求方”、“消费者”、“消费方”、“使用需求者”等是可以互换的，是指需要或者订购服务的一方，可以是个人，也可以是工具。同样地，本申请描述的“司机”、“提供者”、“供应者”、“服务提供者”、“服务提供方”、“服务者”、“服务方”等也是可以互换的，是指提供服务或者协助提供服务的个 人、工具或者其他实体等。另外，本申请描述的“用户”可以是需要或者订购服务的一方，也可以是提供服务或者协助提供服务的一方。
根据本申请的一些实施例，图1-A所示的是一个网络环境100的示意图。该网络环境100可以包括一个按需服务系统105、一个或多个乘客端设备120、一个或多个数据库130、一个或多个司机端设备140、一个或多个网络150、一个或多个信息源160。该按需服务系统105可以包含一个POI(Point of Interest)引擎110。在一些实施例中，POI引擎110可以是对收集的信息进行分析加工以生成分析结果的系统。POI引擎110可以是一个服务器，也可以是一个服务器群组，群组内的各个服务器通过有线的或无线的网络进行连接。一个服务器群组可以是集中式的，例如数据中心；一个服务器群组也可以是分布式的，例如一个分布式系统。POI引擎110可以是集中式的，也可以是分布式的。
乘客端120和司机端140可以统称为用户，它可以是直接与服务订单相关联的个人、工具或者其他实体，例如服务订单的请求者与提供服务者。乘客可以是服务需求方。在本文中，“乘客”、“乘客端”和“乘客端设备”可以互换使用。乘客还可以包括乘客端设备120的使用者。在一些实施例中，该使用者可以不是乘客本人。例如，乘客端设备120的使用者A可以使用乘客端设备120为乘客B请求按需服务，或接受按需服务或按需服务系统105发送的其他信息或指令。为简便起见，在本文中该乘客端设备120的使用者也可以简称为乘客。司机可以是服务提供方。在本文中，“司机”、“司机端”和“司机端设备”可以互换使用。司机还可以包括司机端设备140的使用者。在一些实施例中，该使用者可以不是司机本人。例如，司机端设备140的使用者C可以使用司机端设备140为司机D接受按需服务或按需服务系统105发送的其他信息或指令。为简便起见，在本文中该司机端设备120的使用者也可以简称为司机。在一些实施例中，乘客端120可以包括台式电脑120-1、笔记本电脑120-2、机动车的内置设备120-3、移动设备120-4等中的一种或几种的组合。进一步地，机动车的内置设备120-3，可以为车载电脑(carputer)等；移动设备120-4，可以为智能手机、个人数码助理(personal digital assistance(PDA))、平板电脑、掌上游戏 机、智能眼镜、智能手表、可穿戴设备、虚拟显示设备或显示增强设备(如Google Glass、Oculus Rift、Hololens、Gear VR)等中的一种或多种。司机端140也可以包括类似的设备中的一种或多种。
POI引擎110可以直接访问和/或存取储存在数据库130的数据信息，也可以直接通过网络150访问和/或存取用户端120/140的信息。在一些实施例中，数据库130可以泛指具有存储功能的设备。数据库130主要用于存储从乘客120和/或司机140收集的数据和POI引擎110工作中所利用、产生和输出的各种数据。数据库130可以是本地的，也可以是远程的。数据库130与按需服务系统105或其一部分(例如，POI引擎110)的连接或通信可以是有线的，也可以是无线的。
网络150可以是单个网络，也可以是多个不同网络的组合。例如，网络150可能是一个局域网(local area network(LAN))、广域网(wide area network(WAN))、公用网络、私人网络、专有网络、公共交换电话网(public switched telephone network(PSTN))、互联网、无线网络、虚拟网络或者上述网络的任何组合。网络150也可以包括多个网络接入点，例如，如基站150-1、基站150-2、互联网交换点等在内的有线或无线接入点，通过这些接入点，任何数据源可以接入网络150并通过网络150发送信息。为理解方便，现以交通服务中的司机端140为例说明，但本申请并不局限于此实施例范围内。例如司机端设备140可以是手机或平板电脑，司机端设备140的网络环境100可以分为无线网络(蓝牙、wireless local area network(WLAN)、Wi-Fi等)、移动网络(2G、3G、4G信号等)、或其他连接方式(virtual private network(VPN))、共享网络、near field communication(NFC)、ZigBee等)。
信息源160是为系统提供其他信息的一个源。信息源160可以用于为系统提供与服务相关的信息，例如，天气情况、交通信息、法律法规信息、新闻事件、生活资讯、生活指南信息等。信息源160可以是以一个单独的中央服务器的形式存在，也可以是以多个通过网络连接的服务器形式存在，还可以是以大量的个人设备形式存在。当信息源以大量个人设备形式存在 时，这些设备可以通过一种用户生成内容(user-generated contents)的方式，例如向云端服务器上传文字、声音、图像、视频等，从而使云端服务器连同与其连接的众多个人设备一起组成信息源。
以交通服务为例，信息源160可以是包含有地图信息与城市服务信息的市政服务系统、交通实时播报系统、天气播报系统、新闻网络等。信息源160可以是实物信息源，如常见的测速设备、传感、物联网设备，例如司机的车载测速仪、道路上的雷达测速仪、温湿度传感器。信息源160也可以是获取新闻、资讯、道路实时信息等的源，例如一个网络信息源。网络信息源可以包括基于Usenet的互联网新闻组、Internet上的服务器、天气信息服务器、道路状况信息服务器等中的一种或多种。以送餐服务为例，信息源160可以是存储有某一地域众多餐饮服务商的系统、市政服务系统、交通路况系统、天气播报系统、新闻网络、存储有关所在地域的法律法规信息的规则系统等中的一种或多种。上述举例并非用于局限此处的信息源的范围，也并非局限于所举实例这几类服务范围，本申请可以适用于各种服务任何能够提供与相应服务有关的信息的设备、网络，都可以被归为信息源。
在一些实施例中，该按需服务系统105及所处网络环境100内不同部分之间的信息交流可以通过订单方式进行。订单的客体可以是任一产品。在一些实施例中，产品可以是有形产品或无形产品。一个有形产品可以是任何有形状大小或的实物，例如食品、药品、日用品、化工产品、电器、衣物、汽车、房产、奢侈品等中的一种或几种的组合。一个无形产品可以包括服务性产品、金融性产品、知识性产品、互联网产品等中的一种或几种的组合。一个互联网产品可以是任一满足人们对信息、娱乐、沟通或商务需要的产品。有很多分类方法。以其承载平台分类为例，互联网产品可以包括个人主机产品、Web产品、移动互联网产品、商用主机平台产品、嵌入式产品等中的一种或几种的组合。移动互联网产品可以是用在移动终端的软件、程序或系统。其中的移动终端包括但不限于笔记本、平板电脑、手机、个人数码助理(PDA)、电子手表、POS机、车载电脑、电视机等中的一种或几种的组合。例如，在电脑或手机上使用的各类社交、购物、 出行、娱乐、学习、投资等软件或应用。其中的出行软件或应用又可以是旅行软件、交通工具预定、地图等软件或应用等。其中的交通预定软件或应用是指可以用来预约马匹、马车、人力车(例如，两轮自行车、三轮车等)、汽车(例如，出租车、公交车等)、火车、地铁、船只、飞行器(例如，飞机、直升机、航天飞机、火箭、热气球等)等中的一种或几种的组合。
图1-B所示的是一个网络环境100的另一个示意图。图1-B与图1-A类似。图1-B中，数据库130是独立的，可以直接与网络150相连。按需服务系统105，或其一部分(例如，POI引擎110)，和/或用户端120/140可以通过网络150直接访问数据库130。
图1-A或图1-B中数据库130与按需服务系统105，或其一部分(例如，POI引擎110)，和/或用户端120/140的连接方式可以是不同。各方对数据库130的访问权限可以是有限制的。例如，按需服务系统105，或其一部分(例如，POI引擎110)，对数据库130有最高的访问权限，可以从数据库130中读取或修改大众的或个人的信息；乘客端设备120或司机端设备140在满足一定条件时可以读取部分大众的信息或与用户相关的个人信息。例如，按需服务系统105可以根据一位用户(乘客或司机)的一次或多次使用按需服务系统105的经历更新/修改数据库130中大众的或与该位用户相关的信息。又例如，一位司机140在收到一位乘客120的服务订单时，可以查看数据库130中关于该乘客120的部分信息；但该司机140不可以自主修改数据库130中关于该乘客120的信息，而只能向按需服务系统105汇报，由按需服务系统105决定是否修改数据库130中关于该乘客120的信息。再例如，一位乘客120，在收到一位司机140的提供服务的请求时，可以查看数据库130中关于该司机140的部分信息(如用户评分信息，驾驶经验等)；但该乘客120不可以自主修改数据库130中关于该司机140的信息，而只能向按需服务系统105汇报，由按需服务系统105决定是否修改数据库130中关于该司机140的信息。
需要注意的是，以上对于基于位置的服务系统的描述，仅为描述方便，并不能把本申请限制在所举实施例范围之内。可以理解，对于本领域的技 术人员来说，在了解该系统的原理后，可能在不背离这一原理的情况下，对各个模块进行任意组合，或者构成子系统与其他模块连接，对实施上述方法和系统的应用领域形式和细节上的各种修正和改变。例如，数据库130可以是具有数据存储功能的云计算平台，包括但不限于公用云、私有云、社区云和混合云等。诸如此类的变形，均在本申请的保护范围之内。
根据本申请的一些实施例，图2所示的是一种示例性系统图。为描述方便，按需服务系统105没有显示，而是以POI引擎110为例来说明。POI引擎110可以包括一个或多个处理模块210、一个或多个存储模块220、一个或多个乘客接口230、以及一个或多个司机接口240。POI引擎110中的模块可以是集中式的也可以是分布式的。POI引擎110的模块中的一个或多个模块可以是本地的也可以是远程的。在一些实施例中，POI引擎110可以是网页服务器、文件服务器、数据库服务器、FTP服务器、应用程序服务器、代理服务器、邮件服务器等中的一种或几种的组合。
在一些实施例中，POI引擎110可以用于通过乘客接口230从乘客端设备120接收信息，或将处理后的信息通过乘客接口230发送给乘客端设备120。在一些实施例中，POI引擎110可以用于通过司机接口240从司机端设备140接收信息，或将处理后的信息通过司机接口240发送给司机端设备140。接收和发送信息的方式可以是直接的(例如直接通过乘客接口230或司机接口240由网络150从一个或多个乘客端设备120和/或一个或多个司机端设备140获取信息，也可以是从信息源160接收信息)，也可以是间接的。处理模块210可以通过向一个或多个信息源160发送请求，以获取需要的信息。信息源160中的信息可以包括但不限于天气情况、道路状况、交通条件等，或者上述信息的任意组合。POI引擎110可以与数据库130通信。在一些实施例中，POI引擎110可以提取数据库中的信息，例如地图数据，历史订单信息等。上述历史订单信息可以包括历史订单的出发地、历史订单的目的地、历史订单发生的时间、历史订单中每个订单的价格等中的一种或多种的组合。POI引擎110还可以将从乘客接口230和/或司机接口240接收到的信息发送到数据库130中。POI引擎110中处理模块210对信息的处理结果也可以发送到数据库130中。
在一些实施例中，处理模块210可以用于相关信息的处理。处理模块210可以将处理后的信息发送至乘客接口230和/或司机接口240。信息处理的方式可以包括但不限于对信息进行存储、分类、筛选、转换、计算、检索、预测、训练等中的一种或几种的组合。在一些实施例中，处理模块210可以包括但不限于中央处理器(Central Processing Unit(CPU))、专门应用集成电路(Application Specific Integrated Circuit(ASIC))、专用指令处理器(Application Specific Instruction Set Processor(ASIP))、物理处理器(Physics Processing Unit(PPU))、数字信号处理器(Digital Processing Processor(DSP))、现场可编程逻辑门阵列(Field-Programmable Gate Array(FPGA))、可编程逻辑器件(Programmable Logic Device(PLD))、处理器、微处理器、控制器、微控制器等中的一种或几种的组合。
在一些实施例中，乘客接口230与司机接口240可以分别从乘客端设备120与司机端设备140接收各自发送的信息。上述接收的信息可以是服务的请求信息、乘客和/或司机的当前定位信息、乘客端设备120/司机端设备140的发送的文本、乘客端设备120/司机端设备140发送的的其他信息(例如所上传的图像、视频、音频信息等)。所接收的信息，可以被存储于存储模块220中，也可以由处理模块210进行计算与处理，还可以发送到数据库130。
在一些实施例中，乘客接口230与司机接口240接收的信息可以发送给处理模块210进行处理，生成的处理后的信息。上述处理模块210生成的信息可以是乘客和/或司机的当前位置信息的优化，可以是关于订单的起始位置和/或目的地信息。在一些实施例中，上述处理模块210生成的信息可以是乘客和/或司机位置的确认信息，如确认乘客和/或司机的位置是否存在异常情况。在一些实施例中，上述处理模块210生成的信息可以包括出行方式、采用每种出行方式或者出行方式的组合时订单的成交率等中的一种或多种的组合。上述出行方式包括专车、顺风车、出租车、巴士、火车、动车、高铁、地铁、船舶、飞机等中的一种多种的组合。在一些实施例中，上述处理模块210生成的信息可以是路径相关信息。上述路径相关的信息可以包括路径的个数、每条路径的起点和终点、采用不同出行方式 时每条路径所需要花费的时间、价格等。
在一些实施例中，处理模块210生成的信息可以经过乘客接口230和/或司机接口240发送给乘客端设备120和/或司机端设备140。在一些实施例中，处理模块210生成的信息可以存储在数据库130、存储模块220或者按需服务系统105内其他具有存储功能的模块或单元。
在一些实施例中，数据库130可以设置在按需服务系统105的后台(如图1-A中所示)。在一些实施例中，数据库130可以是独立的，直接与网络150连接(如图1-B中所示)。在一些实施例中，数据库130可以是按需服务系统105的一部分。在一些实施例中，数据库130可以是POI引擎110的一部分。数据库130可以泛指具有存储功能的设备。数据库130主要用于存储从用户端设备120/140和/或信息源160收集的数据和POI引擎110工作中产生的各种数据。数据库130或系统内的其他存储设备泛指所有可以具有读/写功能的媒介。数据库130或系统内其他存储设备可以是系统内部的，也可以是系统的外接设备。数据库130与系统内其他存储设备的连接方式可以是有线的，也可以是无线的。数据库130或系统内其他存储设备可以包括但不限于层次式数据库、网络式数据库和关系式数据库等其中的一种或几种的组合。
数据库130或系统内其他存储设备可以将信息数字化后再以利用电、磁或光学等方式的存储设备加以存储。数据库130或系统内其他存储设备可以用来存放各种信息例如程序和数据等。数据库130或系统内其他存储设备可以是利用电能方式存储信息的设备，例如各种存储器、随机存取存储器(Random Access Memory，RAM)、只读存储器(Read Only Memory，ROM)等。其中随机存储器包括但不限于十进计数管、选数管、延迟线存储器、威廉姆斯管、动态随机存储器(dynamic random access memory，DRAM)、静态随机存储器(static random access memory，SRAM)、晶闸管随机存储器(thyristor random access memory，T-RAM)、零电容随机存储器(zero-capacitor random access memory，Z-RAM)等中的一种或几种的组合。只读存储器包括但不限于磁泡存储器、磁钮线存储器、薄膜存储器、磁镀线存储器、磁芯内存、磁鼓存储器、光盘驱动器、硬盘、磁带、 早期非易失存储器(non-volatile random access memory，NVRAM)、相变化内存、磁阻式随机存储式内存、铁电随机存储内存、非易失SRAM、闪存、电子抹除式可复写只读存储器、可擦除可编程只读存储器、可编程只读存储器、屏蔽式堆读内存、浮动连接门随机存取存储器、纳米随机存储器、赛道内存、可变电阻式内存、可编程金属化单元等中的一种或几种的组合。数据库130或系统内其他存储设备可以是利用磁能方式存储信息的设备，例如硬盘、软盘、磁带、磁芯存储器、磁泡存储器、U盘、闪存等。数据库130或系统内其他存储设备可以是利用光学方式存储信息的设备，例如CD或DVD等。数据库130或系统内其他存储设备可以是利用磁光方式存储信息的设备，例如磁光盘等。数据库130或系统内其他存储设备的存取方式可以是随机存储、串行访问存储、只读存储等中的一种或几种的组合。数据库130或系统内其他存储设备可以是非永久记忆存储器，也可以是永久记忆存储器。以上提及的存储设备只是列举了一些例子，该系统可以使用的存储设备并不局限于此。数据库130或系统内其他存储设备可以是本地的，也可以是远程的。
需要注意的是，上述处理模块210和/或数据库130可以实际存在于用户端120/140中，也可以通过云计算平台完成相应功能。其中，云计算平台包括但不限于存储数据为主的存储型云平台、以处理数据为主的计算型云平台以及兼顾数据存储和处理的综合云计算平台。用户端120/140所使用的云平台可以是公共云、私有云、社区云或混合云等。例如，根据实际需要，用户端120/140接收的一些订单信息和/或非订单信息，可以通过用户云平台进行计算和/或存储。另一些订单信息和/或非订单信息，可以通过本地处理模块和/或系统数据库进行计算和/或存储。
应当理解，图2所示的POI引擎110可以利用各种方式来实现。例如，在一些实施例中，POI引擎110可以通过硬件、软件或者软件和硬件的结合来实现。其中，硬件部分可以利用专用逻辑来实现；软件部分则可以存储在存储器中，由适当的指令执行系统，例如微处理器或者专用设计硬件来执行。本领域技术人员可以理解上述的方法和系统可以使用计算机可执行指令和/或包含在处理器控制代码中来实现，例如在诸如磁盘、CD或 DVD-ROM的载体介质、诸如只读存储器(固件)的可编程的存储器或者诸如光学或电子信号载体的数据载体上提供了这样的代码。POI引擎110及其模块不仅可以有诸如超大规模集成电路或门阵列、诸如逻辑芯片、晶体管等的半导体、或者诸如现场可编程门阵列、可编程逻辑设备等的可编程硬件设备的硬件电路实现，也可以用例如由各种类型的处理器所执行的软件实现，还可以由上述硬件电路和软件的结合(例如，固件)来实现。
需要注意的是，以上对于POI引擎110的描述，仅为描述方便，并不能把本申请限制在所举实施例范围之内。可以理解，对于本领域的技术人员来说，在了解该引擎的原理后，可能在不背离这一原理的情况下，对各个模块进行任意组合，或者构成子系统与其他模块连接，对实施上述方法和系统的应用领域形式和细节上的各种修正和改变。例如，处理模块210、存储模块220、乘客接口230、司机接口240和数据库130可以是体现在一个系统中的不同模块，也可以是一个模块实现上述的两个或两个以上模块的功能。例如乘客接口230与司机接口240可以是同一个接口，同时与乘客端设备120与司机端设备140交互。又例如，数据库130可以位于POI引擎110之内，由同一个存储设备实现数据库130与存储模块220的全部功能。诸如此类的变形，均在本申请的保护范围之内。
根据本申请的一些实施例，图3所示的是POI引擎110中的处理模块210的示意图。处理模块210可以包括以下单元：地址解析单元310、图像处理单元320、语音处理单元330、分组单元340、计算单元350、路径处理单元360、排序单元370、判定单元380、文本处理单元390、以及模型训练单元395。判定单元380可以进一步包括一个计算子单元385。应当注意的是，上面对于POI引擎110中处理模块210的结构描述只是示例性的，不构成对本申请的限制。在一些实施例中，处理模块210还可以包含有其他的单元。在一些实施例中，上述单元中的而某些单元可以不存在。在一些实施例中，上述单元中的一些单元可以合并为一个单元共同作用。在一些实施例中，上述单元可以是独立的。在一些实施例中，上述单元可以是相互联系的。
地址解析单元310可以将接收到的地址信息进行处理。上述地址信息 可以来自于乘客接口230、司机接口240、数据库130、信息源160、或处理模块210中的其他单元或子单元。上述信息的处理的方式可以包括解析地址信息或者逆解析地址信息。逆解析是指将一个地址坐标转换为坐标所在位置的文字描述信息。解析是指将一个地点的文字描述信息转换为一个地址坐标信息。地址坐标可以是，例如，经纬度坐标。文字描述信息可以是，例如，地点的常用名称、地点的街道门牌号码、地点的地标建筑名称等等具有标志性、代表性的惯用名称等中的一种或几种。地址解析单元310还可以将处理后的地址信息发送给其他单元，包括但不限于图像处理单元320、音频处理单元330、路径处理单元360、排序单元370、判定单元370、乘客接口230、司机接口240等中的一种或多种的组合。
图像处理单元320可以将接收到的图像(静止图片或视频)信息进行处理，以得到处理后的信息。其处理方式可以包括，例如，图像增强、图像识别、图像分割、图像测量(角度、距离、透视关系的计算)等中的一种或多种图像处理手段。图像处理单元320接收的图像的来源包括乘客接口230、司机接口240、数据库130、信息源160、或处理模块210中的其他单元或子单元中的一种或多种的组合。图像处理单元320所识别出的图像信息可以输入至地址解析单元310中，供其查找出相应的地址信息。在一些实施例中，图像处理单元320生成的处理后的结果可以发送到路径规划单元360。
语音处理单元330可以对来自乘客端设备120和/或司机端设备140的音频信息进行处理。处理的方式包括降噪、语音识别、语义识别、人物识别等。语音处理单元330可以将识别出的音频信息输出到其他单元进行处理，如将识别出的地址信息输出至地址解析单元310、路径规划单元360等。
分组单元340可以对接收到的信息进行分组。分组的个数可以是一个、两个、三个、四个、五个等。在一些实施例中，上述信息可以是乘客和/或司机的位置信息，包括位置坐标和位置名称。例如，分组单元340可以对接收到的来自司机接口240的车辆当前的GPS坐标进行分组，然后根据分组的结果判断车辆的状态。分组采用的方法可以是一种或多种聚类算法， 包括K-MEANS算法、K-MEDOIDS算法或CLARANS算法等聚类算法中的一种或多种。在一些实施例中，分组单元340可以将信息进行分类输出。例如，分组单元340可以根据历史订单中的起始位置与乘客当前位置的距离以及在一定时间内订单使用频率，将历史订单进行分组。分组单元340生成的结果可以进一步发送给处理模块中的其他单元或子单元进行处理，例如，路径处理单元360，也可以发送到乘客接口230和/或司机接口240进行输出。
根据本申请的一些实施例，上述聚类算法包括但不限于，分割聚类算法、层次聚类算法、基于约束的聚类算法、机器学习中的聚类算法、用于高维数据的聚类算法等的一种或多种。
分割聚类算法包括但不限于基于密度的聚类(density-based methods)、基于网格的聚类算法(grid-based methods)、基于图论的聚类算法(graph theory-based methods)、基于平方误差的迭代重分配聚类算法。基于密度的聚类算法包括但不限于Density-Based Spatial Clustering of Applications with Noise(DBSCAN)算法、Ordering Points to Identify the Clustering Structure(OPTICS)算法、DENsity-based CLUstEring(DENCLUE)算法、Clustering Using References and Density(CURD)算法等。基于网格的聚类算法包括但不限于STatistical INformation Grid(STING)算法、Clustering In QUEst(CLIQUE)算法、WAVE-CLUSTER算法等。基于平方误差的迭代重分配聚类算法包括但不限于概率聚类算法(probability-based clustering)、最近邻聚类算法(nearest neighbor clustering)、K-Medoids算法、K-Means算法和CLARANS算法等。层次聚类算法包括但不限于聚合聚类和分解聚类两种，其中CURE，ROCK和CHAMELEON算法是聚合聚类中最具代表性的三个方法，聚合聚类又包括但不限于基于最近距离(Single-Link)、最远距离(Complete-Link)和平均距离(Average-Link)的三类算法。机器学习中的聚类算法包括但不限于人工神经网络方法和基于进化理论的方法，其中基于进化理论的方法包括模拟退火算法(Simulated Annealing，简称SA)和遗传算法(Genetic Algorithms，简称GA)等。用于高维数据的聚类算法包括但不限于子空间聚类算法(subspace  clustering)和联合聚类算法(joint clustering)。
计算单元350可以对接收到的信息进行计算。上述信息可以来自于乘客接口230、司机接口240、数据库130、信息源160、或处理模块210中的其他单元或子单元，例如，地址解析单元310等。上述计算的内容包括距离、时间、订单成交率或所需费用等中的一种或多种的组合。在一些实施例中，计算单元350可以计算历史出行路径的概率。在一些实施例中，计算单元350可以计算历史订单中始发位置和/或终止位置的出现概率。在一些实施例中，计算单元350可以计算乘客当前位置与历史订单中的起始位置的距离。在一些实施例中，计算单元350可以计算在特定位置处和特定时间点采用某种出行方式时订单的成交率以及所需的费用。在一些实施例中，计算单元350可以计算订单的始发地与订单的终止位置之间的距离、所需的时间、所需的费用、以及需要步行的距离等中的一种或多种的组合。计算单元350可以将计算的结果发送到其他单元，例如，路径处理单元360、排序单元370等。
路径处理单元360可以用于基于来自乘客端设备120和司机端设备140的定位信息，计算并规划乘客的出行路径与司机开往乘客的行驶路径等。路径处理单元360可以基于来自于其他单元的信息进行路径规划。上述其他单元可以包括自地址解析单元310、图像处理单元320、语音处理单元330、分组单元340、计算单元350、排序单元370等中的一种或多种的组合。在一些实施例中，路径处理单元360可以基于来自数据库130和/或信息源160中的信息进行路径规划。在一些实施例中，路径处理单元360还可以将接收到的数据库130中的历史订单、地图数据、分类模型以及信息源160中的与服务相关的信息进行综合分析处理，从而生成不同的路径以供乘客和/或司机选择。上述历史订单包括历史订单的起始位置、历史订单的终止位置、历史订单成交的时间、成交率、费用等中的一种或多种的组合。上述地图数据可以包括街道、桥梁、建筑等人造物体的地理坐标，各种水体、山脉、森林、湿地等自然地貌的地理坐标，以及上述物体的描述性名称或标识等(街道号码、大厦名称、河流名称、商店名称等)，上述物体的图像信息等。上述与服务相关的信息可以包括天气情况、交通 信息、法律法规信息、新闻事件、生活资讯、生活指南信息等中的一种或多种的组合。路径处理单元360生成的结果可以经乘客接口230和/或司机接口240发送给乘客端设备120和/或司机端设备140。在一些实施例中，路径处理单元360生成的结果还可以发送到排序单元370进行处理以生成具有一定顺序或优先级的结果。
排序单元370可以对接收的信息基于一定规则进行排序。上述规则可以是概率大小、距离的长短、时间的先后顺序、花费时间的长短、所需费用的多少、采用的出行方式的多少等中的一种或多种的组合。排序单元370处理的信息的来源可以是计算单元350。在一些实施例中，排序单元370可以根据历史订单中始发地和/或目的地出现的次数或概率对备选的始发地或目的地进行排序，并根据上述次数的从多到少顺序发送给乘客端设备120和/或司机端设备140以供乘客和/或司机选择。在一些实施例中，排序单元370可以根据所需费用的多少对出行方式和/或者路径进行排序。在一些实施例中，排序单元370可以可以根据花费时间的长短对出行方式和/或路径进行排序。排序的结果可以是按照从大到小的顺序或从小到大的顺序。在一些实施例中，排序单元370可以将参与排序的信息都进行输出。在一些实施例中，排序单元370可以在预设条件下将参与排序的信息中的一条信息进行输出。上述预设条件可以是某一地址使用频率最高、路径花费最少、所需时间最短、乘客步行距离最短、所需出行方式最少中的一种或多种的组合。
判定单元380可以判定乘客和/或司机的状态。在一些实施例中，判定单元380可以判断乘客端设备120和/或司机端设备140所发送的位置信息是否精确。在一些实施例中，判定单元380可以判断车辆的状态，例如，是否静止，是否运动、运动的方向、运动的速度、运动的加速度等中的一种或多种的组合。上述对于车辆的状态的判断可以用于计算某个订单的所需费用。对上述所需费用的计算可以由判定单元380中的计算子单元385完成。在一些实施例中，判定单元380可以判断司机端设备140发送的采用第一种定位技术的定位结果与采用第二种定位技术或多种定位技术的定位结果之间的偏差。上述偏差可由计算子单元385计算得到。根据上述 偏差可以判断第一种定位技术的定位信息是否异常。根据判定结果，POI引擎110可以决定是否发送订单信息给该司机端设备140。
文本处理单元390可以对处理模块210接收到的文本信息进行处理。在一些实施例中，上述对文本信息的处理可以包括对上述文本信息进行分词、对文本信息中的特征文本进行提取、对上述特征文本进行分类等中的一种或多种的组合。在一些实施例中，文本处理模块390可以对上述文本信息中的满足特定条件的内容进行删除等处理。上述文本信息可以来自于乘客接口230、司机接口240、数据库130、信息源160、存储模块220或处理模块210中的其他单元或子单元。文本处理单元390生成的结果可以发送到其他单元进一步处理。
模型训练单元395可以用来对地点分类器和/或POI分类模型进行训练。模型训练单元395可以接收来自数据库130、信息源160、或按需服务系统中其他模块或单元的信息，并利用上述接收到信息训练地点分类器和/或POI分类模型。在一些实施例中，模型训练单元395可以分辨一个位置信息或文本地址数据中包含的地址所属的地址分类类型。在一些实施例中，模型训练单元395可以根据一个用户(例如，乘客)的历史订单信息判断出该乘客历史上的出行目的或出行轨迹。根据该出行目的或出行轨迹就可以响应乘客的服务请求，为乘客推荐合适的目的地和/或出发地。
需要注意的是，以上对POI引擎110中处理模块210的描述只是示例性的，并不能把本申请限制在所列举的是实施例范围之内。可以理解，对于本领域的技术人员来说，在了解处理模块所执行的功能后，可能在实现上述功能的情况下，对各个模块、单元或子单元进行任意组合，对实施上述方法和系统的应用领域形式和细节上的各种修正和改变。例如，在一些实施例中，计算单元350和计算子单元385可以集成为同一个单元或模块来完成计算功能。又例如，在一些实施例中，处理模块210还可以包括一个独立的计价单元来实现对订单所需费用的计算。在一些实施例中，有些单元不是必需的，例如，文本处理单元390。在一些实施例中，处理模块210可以包含其他的单元或子单元。诸如此类的变形，均在本申请的保护范围之内。
根据一些实施例，图4-A显示了POI引擎110中的乘客接口230的框图。乘客接口230可以包括一个乘客信息接收单元410、一个乘客信息解析单元420、与一个乘客信息发送单元430。乘客信息接收单元410可以用于接收乘客端设备120发来的信息，并对这些信息进行识别、整理和归类。从内容上来看，乘客端设备120所发送的信息可以是经定位技术所确定的乘客端设备120的当前位置、乘客输入的当前位置/出发位置、乘客当前位置相关的其他信息、当前系统时间、乘客预期的出发时间/到达时间/旅途时间等、乘客对服务的选择/要求/描述信息、乘客对希望接受到的信息的内容/格式/时间/数量、乘客在乘客端设备120上打开或开启服务应用等信息中的一种或几种。从信息类型或格式上看，乘客端设备120所发送的信息可以是乘客在乘客端设备120上所输入的自然语言文本信息、乘客端设备120所发送的二进制信息、乘客端设备120输入输出模块510所记录的音频信息(包括乘客的语音输入)、乘客端设备120输入输出模块510所拍摄的图像(静止图片或视频)信息等的一种或多种(见图5)。乘客端设备120通过网络150可以将上述信息提供给乘客接口230中的乘客信息接收单元410。
乘客信息解析单元420可以用于将乘客信息接收单元410所收到的乘客信息进行解析操作。这里的解析操作可以包括对乘客信息进行整理或分类，并且进行格式的转换或信息内容的提取、分析或变换，以转换为处理模块210或存储模块220能够计算、处理或存储的格式。乘客信息解析单元420还可以用于将处理模块210所处理后的信息或存储模块220中的信息，按照乘客端设备120的指令或偏好，转换为乘客端设备120所能读取或选择的信息格式，并提供给乘客信息发送单元430。乘客信息发送单元430可以用于将POI引擎110需要向乘客端设备120发送的信息通过网络150发送给乘客端设备120。乘客信息接收单元410可以是由一个有线的或无线的接收设备所组成，通过网络150与乘客端设备120建立联系。类似的，乘客信息发送单元430可以是由有线或无线的发送设备所组成，通过网络150与乘客端设备120建立联系。
根据一些实施例，图4-B显示了POI引擎110中的司机接口240的框 图。如图中所示，司机接口240可以包括一个司机信息接收单元415、一个司机信息解析单元425、与一个司机信息发送单元435。司机信息接收单元415可以用于司机的设备上接收司机发送的信息，并对这些信息进行识别、整理和归类。从内容上来看，司机所发送的信息可以是经定位技术所确定的司机当前位置、司机所行驶的速度、司机所反馈的当前服务状态(载客、等待载客、空驶)、司机对服务请求的选择/确认/拒绝信息、司机在司机端设备140上打开/开启服务应用等的一种或多种。从信息类型上看，司机端设备140所发送的信息可以是司机在设备上所输入的自然语言文本信息、司机端设备140所发送的二进制信息、司机端设备140所记录的音频信息(包括司机的语音输入)、司机端设备140所拍摄的图像(静止图片或视频)信息以及其他类型的多媒体信息等的一种或多种。司机端设备140通过网络150可以将上述信息提供给司机接口240中的司机信息接收单元415。
司机信息解析单元425可以用于将司机信息接收单元415所收到的司机信息进行解析操作。这里的解析操作可以包括对司机信息进行整理或分类，并且进行格式的转换或信息内容的提取、分析或变换，以转换为处理模块210或存储模块220能够计算、处理或存储的格式。司机信息解析单元425还可以用于将处理模块210所处理后的信息或存储模块220中的信息，按照司机端设备140的指令或偏好，转换为司机端设备140所能读取或选择的信息格式，并提供给司机信息发送单元435。司机信息发送单元435可以用于将POI引擎110需要向司机端设备140发送的信息通过网络150发送给司机端设备140。司机信息接收单元415可以是由一个有线的或无线的接收设备所组成，通过网络150与司机端设备140建立联系。类似的，司机信息发送单元435可以是由有线或无线的发送设备所组成，通过网络150与司机端设备140建立联系。
根据一些实施例，图5是乘客端设备120和司机端设备140框图。以乘客端设备120为例，如图5中所示，乘客端设备120可以包括输入输出模块510、显示模块520、定位模块530、通信模块540、处理模块550和存储模块560。乘客端设备120也可以包含更多的模块或组件。
输入输出模块510可以用于接收乘客对按需服务应用图形界面、地图界面、以及输入输出操作界面的一种或多种形式的输入，并且将待提供给乘客的信息通过一种或多种形式输出。输入输出模块510还可以用于通过信号转换等手段，将乘客或外界(如周边环境)的光学、声学、电磁学、力学等信息中的一种或几种以静止图片、视频、音频、机械振动等形式予以采集和记录。输入或输出的形式可以包括声音信号、光信号、机械振动信号等的一种或多种。显示模块520可以用于显示按需服务应用的图形界面、地图界面、输入输出的操作界面、操作系统界面等。定位模块530可以基于一种或多种定位/测距技术，确定乘客的位置和/或其运动状态。具体地，确定乘客的位置及其运动状态可以包括计算乘客的位置、速度、加速度、角速度、路径等等运动参数中的一种或多种。通信模块540可以用于将乘客端设备120待发送或待接收的信息通过有线或无线通信的方式发送或接收。例如，通信模块540可以与POI引擎110中的乘客接口230通信以实现乘客端设备120向POI引擎110发送或从POI引擎110接收信息。在一些实施例中，乘客端设备120还可以通过通信模块540与司机端设备140进行通信，例如，通信方式包括蓝牙通信、红外通信。司机端设备140和乘客端设备120开启蓝牙后可以直接测量司机与乘客之间的距离。处理模块550可以用于对乘客端设备120所获得的信息进行计算、处理。存储模块560可以用于将输入输出模块510、定位模块530、通信模块540、处理模块550所获取、生成、计算或处理后的信息进行存储。
上述定位技术包括但不限于该定位技术可以选自全球定位系统(GPS)技术、全球导航卫星系统(GLONASS)技术、北斗导航系统技术、伽利略定位系统(Galileo)技术、准天顶卫星系统(QAZZ)技术、基站定位技术、Wi-Fi定位技术。测距技术包括但不限于测距技术可以是基于电磁波的、声波的、或其他波动的一种或多种。例如，电磁波的测距技术可以利用无线电波，红外线，可见光等中的一种或多种。利用无线电波的测距技术可以利用蓝牙波段，或其他微波波段。利用红外线的测距技术可以利用近红外线中红外线、远红外线等中的一种或多种。声波的测距技术可以是基于超声波的次声波的，或其他频段的声波等中的一种或多种。利用电 磁波或声波的测距技术可以基于多种原理中的一种或多种对距离进行测量。例如，利用电磁波或声波的测距技术可以基于波形所传播的时间、多普勒效应、信号强度、信号衰减特性等中的一种或多种。
以上对乘客端设备120的描述适用于司机端设备140。
需要注意的是，以上对于用户端设备120/140的描述，仅为描述方便，并不能把本申请限制在所举实施例范围之内。可以理解，对于本领域的技术人员来说，在了解用户端设备所执行的功能后，可能在实现上述功能的情况下，对各个模块进行任意组合，或者构成子系统与其他模块连接，对实施上述方法和系统的应用领域形式和细节上的各种修正和改变。例如，输入输出模块510与显示模块520可以是体现在一个系统中的不同模块，也可以是一个模块实现上述的两个或两个以上模块的功能。又例如，定位模块530与通信模块540可以是不同的模块，也可以是集成于同一个硬件中的同一模块。诸如此类的变形，均在本申请的保护范围之内。
图6是数据库130的结构示意图。数据库130可以存储多种不同内容的信息，例如，历史订单数据库610、地图数据库620、用户数据库630、分类模型数据库640等。当POI引擎110或其他的模块或单元需要一类或几类信息时，可以从数据库130中调取。
历史订单数据库610可以包括历史订单的始发地、目的地、始发地的类型、目的地类型、历史订单的起始/终止时间、乘客与司机的汇合位置、出行里程、出行、订单服务金额、订单服务小费、订单服务的历程费率、订单服务的时间费率、订单行驶时间、服务过程中不同时刻下的乘客位置和行驶速度、平均行驶速度、乘客和/或司机对历史订单的评价等内容。
地图数据库620可以包括街道、桥梁、建筑等人造物体的地理坐标，各种水体、山脉、森林、湿地等自然地貌的地理坐标，以及上述物体的描述性名称或标识等(街道号码、大厦名称、河流名称、商店名称等)，上述物体的图像信息等。
用户数据库630所存储的信息可以包括用户120/140的服务相关信息，如账号名称、显示名称(昵称)、证件(驾照、ID卡等)号码、注册时间、用户等级/级别、交通违规记录、酒驾记录、司机140的交通工具信息。用 户数据库630还可以存储用户120/140的其他社会信息，如信用记录、犯罪记录、荣誉与奖励记录等。用户数据库630还可以存储用户120/140的基本资料信息，如年龄、性别、国籍、住址、工作地点、族群、宗教信仰、受教育程度、工作经历、婚姻状况、情感状况、语言能力、专业技能、政治倾向、兴趣爱好、喜爱的音乐/电视节目/电影/书籍等。
分类模型数据库640可以用于存储与地点关联的地点类型信息、各类地点描述性名称与地点类型的映射关系信息以及地点类型之间的关联信息等。例如，某一类地点描述性名称与某一地点类型的相关系数、一种地点类型与另一种地点类型的相关系数、一种地点类型与另一种地点类型的集合关系等。一个地点类型可以认为是一个地点集合，包括属于该地点类型的至少一个地点。一个地点类型还可以包含其他的地点类型作为其子类型。两个地点类型之间可以有交叉重合的部分，亦即，同一个地点可以同时属于一个或更多的地点类型。从集合的角度，地点类型可以是康托集，也可以是模糊集。每一类地点类型可以有明确清晰的定义或“边界”，也可以没有明确的“边界”。对于模糊集的地点类型，其元素可以有一个隶属度，用于表征其属于该地点类型的可能性或几率。该隶属度可以是小于1，也可以是等于1的。上述信息的存储可以是在一个数据库130中的不同模块或组件所实现的。上述信息的存储也可以是由多个数据库130所分别实现的，这些数据库可以通过有线或无线的通信连接相互交换信息。
根据本申请的一些实施例，图7是系统105确定目的地相关信息的流程图。需要注意的是，在一些实施例中，目的地相关信息可以包括目的地的位置、目的地的地点类型、乘客到达目的地的时间、由始发地到达目的地的路径、由始发地到达目的地的平均速度、由始发地到达目的地的交通方式、由始发地到达目的地的费用等等中的至少一种信息。目的地相关信息可以是与一个目的地有关的，也可能是与多个备选目的地有关的。
如图7所示，在步骤710，系统105的POI引擎110可以通过其乘客接口230，经网络150接收来自一个乘客端设备120的位置相关信息。上述位置相关信息可以包括但不限于乘客当前位置、在未来某个时刻的乘客位置、未来某个时间段内的乘客位置、乘客指定的始发地、当前时间、乘 客指定的出发时间等。
乘客的当前位置可以由乘客端设备120的定位模块530采集，也可以由输入输出模块510所获得。乘客的当前位置可以是由一种或多种定位技术确定的乘客位置坐标，或者乘客输入的当前所在位置的描述性名称等。在一些实施例中，上述当前位置相关信息还包括乘客和/或司机当前位置的附近的其他信息，如商圈、住宅区、景点，医院、学校、大型建筑、汽车站、火车站、地铁站、飞机场、桥梁、交叉路口等中的一种或多种。在一些实施例中，上述位置相关信息还包括从乘客端设备120和/或司机端设备140上传的关于其当前位置周围的图片、视频、音频等。上述图片、视频、音频信息可以通过输入输出模块510所获得(见图5)。例如，乘客可以用其手机摄像头拍下其所在周围的标志性建筑物，并上传到POI引擎110。又例如，乘客端设备120可以获取关于其当前位置周围情况的语音或一段视频，并发送到POI引擎110。
乘客指定的始发地，泛指乘客(或其他乘客端设备120使用者)在乘客端设备120上所指定的始发地。在一些实施例中，乘客(或其他乘客端设备120使用者)可以在其设备120的输入输出模块510所提供的输入框或列表、图标阵列上输入或选择始发地。在另一些实施例中，乘客也可以在设备120上显示模块520所展示的地图界面上通过操作指针、图钉等图标指定始发地。在又一些实施例中，乘客还可以通过语音输入的方式向乘客端设备120提供始发地信息。
当前时间可以通过乘客端设备120上的处理模块550获取操作系统的系统时间。乘客指定的出发时间可以通过设备120上的输入输出模块510输入。指定的出发时间可以是一个具体的时刻，也可以是一个时间范围。时间范围的长度和起始时刻、终止时刻可以随着应用场景、乘客当前需求、交通服务状况的不同而不同。
POI引擎110在步骤720从一个数据库130获取历史信息。数据库130的结构与功能参见图6及其对应的文字描述。历史信息可以包括历史订单数据库610所存储的与历史订单相关的信息。历史信息也可以包括地图数据库620所存储的地图信息。历史信息还可以包括用户数据库630所存储 的用户服务相关信息、其他社会信息、基本资料信息等。上述各种信息的内容参见图6及其对应的文字描述，在此不再赘述。
需要注意，尽管编号上步骤720是在步骤710之后的，但上述编号并不代表或暗示任何时间先后顺序，而是仅仅起到标识作用，以供描述的方便。上述步骤720可以与步骤710同步进行，或者早于步骤710进行。
在步骤730，根据所接收到的位置相关信息与获取的历史信息，POI引擎110的处理模块210确定目的地相关信息。
基于历史信息与位置相关信息，POI引擎110处理模块210可以预测乘客想要到达的目的地位置/描述性名称/地点类型。处理模块210还可以基于上述始发地位置与目的地位置，规划出从始发地到达目的地的至少一条路径。处理模块210还可以根据路径规划算法，预估与路径相关的信息。与路径相关的信息包括但不限于旅行距离、旅行时间、到达该目的地时间、堵车时间、燃料消耗量、行驶速度、红绿灯数量、旅行费用、过路费用等因素。
根据本申请的一些实施例，处理模块210的路径处理单元360可以利用一种或多种路径优化算法，计算确定上述由始发地到达目的地的路径。
确定上述路径的标准可以是一个最优的总成本。上述总成本可以表现为不同形式。这些形式可以包括，例如，路径距离、路径的旅行时间、路径的预估堵车时间、路径的预估燃料消耗量、路径的预估行驶速度、路径的红绿灯数量、路径的预估费用、路径的过路费用等中的一种或多种。总成本可以依赖于上述形式中的一种或多种。
上述路径优化算法包括但不限于传统路径规划算法、图形学算法、智能仿生学算法以及其他算法等。传统的路径规划算法包括但不限于模拟退火算法(simulated annealing(SA))、人工势场法(artificial potential method)、模糊逻辑算法(fuzzy logic arithmetic)和禁忌搜索算法(Tabu Search(TS))等。图形学的方法包括但不限于C空间法(又称可视图空间法)、自由空间法和栅格(grid)法等。智能仿生学算法包括但不限于蚁群算法、神经网络算法、遗传算法(genetic algorithms(GA))和粒子群算法(POS)等。其他算法包括但不限于Dijkstra算法、最短路径快速算法(Shortest path  faster algorithm(SPFA))、Bellman-Ford算法、Johnson算法、Fallback算法和Floyd-Warshall算法等。
基于上述算法所确定的路径，计算模块350可以对上述路径进行计算和处理，以获得与路径相关的信息。与路径相关的信息的细节参见上文的描述，在此不再赘述。
在计算上述路径有关的信息时，计算模块350可以利用来自于数据库130和/或信息源160的信息。所利用的信息包括但不限于，来自历史订单数据库610的历史订单信息、来自地图数据库620的地图数据、来自其他信息源160的关于天气、日历、节假日、社会活动、法律法规等一种或多种类型的信息。上述信息的内容参见图1-A与图6及其相应的描述，在此不再赘述。
在确定了目的地相关信息后，POI引擎110在步骤740通过其乘客接口230将确定的目的地相关信息经网络150发送给乘客端设备120，以供乘客端设备120显示及后续处理之用。所发送的目的地相关信息，可以是目的地的本身，也可以是从乘客端设备120的当前位置或乘客指定的始发地到达该目的地的路径，还可以是上文中所提到的与路径相关的信息。
根据本申请的一些实施例，发送的目的地相关信息可以是与一个目的地关联的，也可以是与多个目的地关联的。在一些实施例中，与多个目的地关联的相关信息是以列表的形式表示的。进一步地，处理模块210中的排序单元370可以对多个目的地进行排序，排序的标准可以是基于上述与路径相关的信息，例如，预估的路径距离、预估的旅行时间、预估的燃料消耗量、预估的总费用等中的一种或多种。排序单元370可以依据上述标准进行升序或者降序排列。
在步骤750，POI引擎110可以通过其乘客接口230经网络150接收来自乘客端设备120的乘客对目的地相关信息的处理。乘客对目的地相关信息的处理可以是乘客对目的地信息的确认、否认、选择、增加、修改等中的一种或多种。
在接收到乘客的处理后，可选地，POI引擎110的处理模块210还可以对处理进行分析与计算，以得到一个处理结果。该处理结果可以对应一 个乘客所确定的目的地，还可以对应一个到达该目的地的路径和/或路径相关信息。
在步骤760，POI引擎110的司机接口240将处理结果经网络150发送给至少一个司机端设备140。在步骤770，POI引擎110的司机接口240接收来自司机端设备140的司机对处理结果的响应。该响应的内容可以是愿意/不愿为乘客提供交通服务、向乘客提供交通服务的附加条件、司机的当前位置信息等的一种或多种。在步骤780，POI引擎110可以对上述响应进行处理，以确认司机的响应。在一些实施例中，当司机确认愿意为乘客提供交通服务后，POI引擎110的乘客接口230可以将该司机提供交通服务的意愿、附加条件与当前位置信息发送给乘客端设备120。乘客接口230还可以将司机的其他信息发送给乘客端设备120。该类信息可以包括用户服务相关信息、其他社会信息、基本资料信息等的一种或多种。
需要注意的是，上述对POI引擎110确定目的地相关信息流程的描述仅仅是示例性的，并不能把本申请限制在所列举的是实施例范围之内。可以理解，对于本领域的技术人员来说，在了解上述流程的原理后，可能在实现上述功能的情况下，对各个步骤进行任意组合，对实施上述方法的过程与步骤进行形式和细节上的各种修正和改变。从步骤710到步骤780的一个或者若干个步骤可以被跳过或者省略，同时在上述步骤之余还可以插入新的步骤。例如，步骤780之后，POI引擎可通过其乘客接口230和/或司机接口240接收来自乘客端设备120和/或司机端设备140的交易报告。又例如，在一些实施例中，在POI引擎确定了乘客目的地相关信息后，可以直接将这一信息发送给司机端设备140，即跳过步骤740与750，提前向司机通知预测的乘客始发地与目的地。诸如此类的变形和变换，都不脱离本申请的范围。
根据本申请的一些实施例，图8展示的是乘客端设备上接收目的地相关信息的示例性实施例。
在步骤810，乘客端设备120借助其定位模块530和/或输入输出模块510获取一个位置相关信息。
在步骤820，乘客端设备120经网络150将所获取的位置相关信息通 过通信模块540向外发送。发送的目标可以是系统105，也可以是其他乘客端设备120，还可以是一个或多个司机端设备140。
在一些实施例中，乘客端设备120将位置相关信息发送至系统105，以供POI引擎110处理并生成目的地相关信息。
步骤820之后，乘客端设备120进入步骤830，通过通信模块540接收来自系统105的目的地相关信息。上述目的地相关信息，参见图7及其相应描述，在此不再赘述。
在一些实施例中，乘客端设备120接收到的目的地相关信息是与多个目的地相关的。进一步地，与多个目的地相关的信息可以是以列表形式表示或呈现的。
在步骤830之后，乘客端设备120可以通过其显示模块520对上述接收到的信息予以显示。信息可以也可以是以纯文本的形式进行显示，还可以以超文本形式进行显示。进一步地，在一些实施例中，目的地相关信息以超文本标记语言(hypertext marking language(HTML))的形式予以表示或显示。在一些实施例中，目的地相关信息可以显示在一个地图界面中。
在步骤840，乘客端设备120的输入输出模块510接收来自乘客对目的地相关信息的处理。
在接收乘客对目的地相关信息的处理后，乘客端设备120的通信模块540可以在步骤850中向外发送这一处理。发送的目标可以是系统105，也可以是其他乘客端设备120，或者是一个或多个司机端设备140。
在步骤850之后，乘客端设备120还可以自外界接收信息。这些信息可以是来自系统105、其他乘客端设备120、一个或多个司机端设备140。来自系统105的信息可以包含但不限于下列内容：收到乘客处理的回执、基于乘客的处理所生成的目的地处理结果、系统105将乘客信息发送至一个或多个司机端设备140的通知、一个或多个司机端设备140对处理结果的响应等等。
需要注意，上述对于乘客端设备120获取目的地相关信息的流程或步骤的描述仅仅是示例性的，不构成对本申请的限制。可以理解，对于本领域的技术人员来说，在了解乘客端设备120在上述流程中所执行的操作和 所获取、提供的信息后，可能在达到相同效果的情况下，对各个步骤进行任意组合，对实施上述方法的流程进行形式和细节上的各种修正和改变。例如，在一些实施例中，步骤840与850可以被跳过，乘客端设备120可以在接受目的地相关信息后，不进行相关操作。诸如此类的变形，均在本申请的保护范围之内。
根据本申请的一些实施例，图9-A展示的是系统105预测当前目的地相关信息的示例性实施例。
步骤910，POI引擎110通过乘客接口230获取来自一个乘客端设备120的当前始发地信息与出发时间信息。
步骤920，POI引擎110从一个数据库130获取与上述乘客端设备120所关联的历史订单信息。
POI引擎110可以获取与上述乘客端设备120所关联的全部历史订单信息，也可以只获取在一个时间段内的历史订单信息。上述时间段可以随着乘客端设备120所关联的用户账户信息、用户历史订单的频次、所在的地域、当前的交通情况等因素的改变而改变。上述时间段也可以被预先设定，其时间长度可以取任意可能长度，例如但不限于，1个月、3个月、6个月、1年或者其他的时间长度。
POI引擎110可以获取上述乘客端设备120所关联的在所有地域历史订单信息，也可以获取其关联的在当前位置附近历史订单信息。这里所说的当前位置附近可以是指距离在一个阈值内的区域，也可以是指一个确定的地域范围。上述阈值可以是人为预设的距离值，例如1公里、2公里、5公里、10公里，也可以是其他的距离值。上述阈值还可以是一个可变动的距离值，随着乘客端设备120所关联的用户账户信息、乘客端设备120所处的位置、当前交通服务情况等因素的变化而变化。该地域范围可能是任何大小的行政区划、商业区域、公共区域、居住区域或者任何其他人为划定的区域。该地域范围还可以是没有明确边界的自然地理分区(例如，以地貌、气候、动植物分布等因素划分的地理分区)或者由河流、山脉等划界的区域等。
上述历史订单信息的内容可以有多种，可以包括历史订单的始发地信 息、出发时刻、目的地信息、到达时刻、行驶时间、全程平均行驶速度等因素中的一种或多种。
步骤930，基于当前始发地信息、出发时间信息以及与上述乘客端设备120所关联的历史订单信息，POI引擎110可以生成一个或多个备选目的地信息。处理模块210中的计算单元350可以根据已有的始发地信息，预测目的地信息。这一预测可以根据当前始发地与历史订单中始发地之间的关联程度来进行评估。
根据一些实施例，当历史订单的始发地与当前乘客的始发地接近时，历史订单与当前订单有较高的关联度。根据一些实施例，当历史订单的出发时间与当前乘客的出发时间接近时，历史订单与当前订单有较高的关联度。这里的历史订单与当前订单的时间接近，可以是指两者之间在年份、月份、天、上/下午、小时、分钟上接近。
根据一些实施例，当历史订单的出发时间与当前乘客的出发时间具有某种周期性规律时，历史订单与当前订单有较高的关联度。这里的周期性规律，可以是指两个订单具有一定的重复性或相似性，而间隔了一个时间周期。该周期可以是1年、1个月、1天等单位时间长度的整数倍，当然也可以是其他时间长度的整体倍。
处理模块210中的计算单元350对当前订单与历史订单之间关联程度的评估可以是通过计算一个分数指标来进行的。根据本申请的一些实施例，与各历史始发地对应的历史目的地的得分可以利用大数据运算得到。在一些实施例中，与各历史始发地对应的历史目的地的得分可以用公式1计算得到：
Figure PCTCN2016072357-appb-000001
Figure PCTCN2016072357-appb-000002
(公式1)
其中，time为当前出发时刻；source为当前始发地；POIi为一条历史数据，包括历史始发地、历史目的地和历史出发时刻；d表示当前出发时刻和历史数据POIi的间隔天数；在一些实施例中，与当前出发时间点间隔天数越少的历史数据参考意义越大；s表示当前出发时刻和历史数据POIi的间隔秒数，对于1天之内的短期目的地加权，距 离当前出发时刻越近，得分越高；h表示当前出发时刻和历史数据POIi出发时刻在小时粒度的间隔，与当前出发出发时刻间隔的小时数越少的历史数据参考意义越大；POIi.source表示在POIi历史数据中的历史始发地；f(x,y)代表两个始发地之间的相关程度。在一些实施例中，若当前始发地与历史数据POIi的历史始发地相同或相距在某一距离阈值以内，则f(x,y)＝1；若当前始发地与历史数据POIi的历史始发地不同或相距在上述距离阈值以外，则f(x,y)为大于0小于1的数。例如，f(x,y)可以是0.1、0.2、0.3等小数，也可以是其他小数。上述距离阈值可以是一个人为设定的值，例如50米、100米、200米、500米，也可以是其他距离值。再根据上述公式1得到各个历史目的地得分后，可以由处理模块210中的排序单元370对上述历史目的地进行排序，并确定出得分最高的历史目的地。
根据一些实施例，若所述得分最大的历史目的地的得分大于某一个第一阈值，则获取得分最大的历史目的地可以做进一步处理，以判断是否可以将该历史目的地设为默认目的地。该处理可以由计算单元350实现。例如，得分最大的历史目的地的得分可以与其他历史目的地的得分进一步比较。举例说明，可以计算得分最大的历史目的地的得分和多个历史目的地的总得分的比值；若该比值大于第二阈值，则确定该得分最大的历史目的地为默认目的地。
根据本申请的一些实施例，某乘客有三次历史出行信息，第一次去A地的得分为2，第二次去A地的得分为1.5，第三次去B地的得分为1，则对于历史目的地A来说，其得分为3.5，历史目的地B的得分为1。第一阈值设置为2，第二阈值设置为0.75。此时，处理模块210中的判定单元380可以将历史目的地A的得分与第一阈值进行比较，若历史目的地A的得分大于第一阈值，则判断历史目的地A的得分(3.5)与历史目的地A和B的得分的和(4.5)的比值是否大于第二阈值，若该比值(3.5/4.5)大于第二阈值，则确定历史目的地A为预测目的地。上述第一阈值和第二阈值可根据需要进行设定。
以上关于确定默认目的地的描述仅仅是示例性的，并不构成对本申请 的限制。可以理解，处理模块210也可以根据得分的高低确定出多个默认目的地，而不是仅将最高得分的历史目的地确定为默认的。处理模块210可以在确定了多个默认目的地后，对这些默认目的地进行排序。按照上述得分的高低，排序规则可以升序排列，也可以降序排列。需要说明的是，在确定预测目的地的过程中设定第一阈值和第二阈值的目的是为了确保该乘客出行目的地的预测方法的准确性，只有准确性较高时才会向目标乘客端设备120发送预测目的地。
获得了备选目的地后，处理模块210中的地址解析单元310还可以进一步将备选目的地信息进行解析或逆解析，即将地理坐标表示的备选目的地转换为描述名称表示的备选目的地，或者将以描述名称表示的备选目的地转换为地理坐标表示的备选目的地。所发送的备选目的地信息可以是由描述名称表示的，也可以是由地理坐标表示，还可以是由两者同时表示。
在生成了备选目的地信息后，POI引擎110可在步骤940中通过乘客接口230将备选目的地信息经网络150发送给乘客端设备120。在一些实施例中，POI引擎110还可以将备选目的地信息通过司机接口240发送给一个或多个司机端设备140。
在步骤950中，POI引擎110可以通过乘客接口230接收来自乘客端设备120的对备选目的地信息的处理。
步骤950之后，POI引擎110还可以对上述处理进行分析和计算，以生成处理结果。在此之后POI引擎110还可以有若干后续操作。生成处理结果以及后续操作的细节参见图7及其相关描述，在此不再赘述。
需要注意，上述对于POI引擎110基于历史订单信息与乘客当前始发地位置与出发时间预测目的地信息的流程或步骤的描述仅仅是示例性的，不构成对本申请的限制。可以理解，对于本领域的技术人员来说，在了解POI引擎110在上述流程中所执行的操作和所获取、提供的信息后，可能在达到相同效果的情况下，对各个步骤进行任意组合，对实施上述方法的流程进行形式和细节上的各种修正和改变。例如，在一些实施例中，步骤940与950可以被跳过。POI引擎110可以在发送目的地相关信息后，不进行相关操作。又例如，POI引擎110在步骤910还可以利用来自乘客端 设备120或者信息源160的其他相关信息，包括但不限于，乘客端设备120在之前一段时间内的至少一个位置信息、乘客端设备120所获取的乘客其他信息(生理健康信息，例如心跳、脉搏、血压；社交信息，例如社交网络上的活动、好友约会等)、天气信息、当前社会活动、节假日信息、法律法规等信息，共同地确定备选目的地信息。诸如此类的变形，均在本申请的保护范围之内。
根据本申请的一些实施例，图9-B展示的是乘客端设备上接收并处理目的地相关信息的示例性实施例。
在步骤915，乘客端设备120获取当前始发地信息及当前出发时间。
根据本申请的实施例，当前始发地可以是当前位置，也可以是乘客所设定或指定的始发地。
当前始发地为当前位置时，该当前始发地可以通过乘客端设备120的通信模块540根据一种或多种定位技术来确定，也可以通过乘客端设备120的输入输出模块接收乘客的输入指令而确定。
根据本申请的实施例，通信模块530可以根据两种或更多种定位技术确定出较精确的当前位置。例如，通信模块540能够通过与GPS定位卫星和通信基站进行通信，得到GPS定位信息和基站定位信息，并由处理模块550处理以确定比较精确的当前位置。处理模块550可以将该当前位置作为当前始发地位置。
当前始发地为乘客在乘客端设备120上所设定或指定的位置时，当前始发地可以是乘客所输入或选择的。
根据本申请的实施例，乘客端设备120可以监测目的地输入框中是否有输入指令。当存在输入指令时，乘客端设备120输入输出模块510获取乘客端设备120的当前出发地信息。处理模块550可以同时获取乘客输入指令的对应时间。
根据本申请的实施例，乘客端设备120还可以存储并记录乘客所预先设定的几个常用目的地。当乘客需要交通服务时，乘客可以在乘客端设备120上调出上述常用目的地，将常用目的地通过显示模块520予以显示，并通过输入输出模块510进行选择。
在步骤925，乘客端设备120将上述当前始发地信息及当前出发时间通过通信模块540发送给系统105。除了当前始发地信息与出发时间外，乘客端设备120还可以发送其他内容的信息，包括但不限于，乘客的生理健康信息、乘客对交通服务的任何要求/偏好/期待、乘客其他信息等。
在步骤935，乘客端设备120通信模块540接收来自系统105乘客接口230所发送的备选目的地信息。
在步骤935之后，乘客端设备120可以通过其显示模块520对上述接收到的信息予以显示。信息可以也可以是以纯文本的形式进行显示，还可以以超文本形式进行显示。进一步地，在一些实施例中，目的地相关信息以超文本标记语言(hyper text marking language，HTML)的形式予以表示或显示。在一些实施例中，目的地相关信息可以显示在一个地图界面中。
在步骤945，乘客端设备120可以通过输入输出模块510接收乘客对于备选目的地信息的处理。上述处理包括但不限于删除/选择/指定一个或多个备选目的地以及添加一个新的目的地信息。
在接收乘客的处理后，可选地，乘客端设备120可以在步骤955中将上述处理发送出去。发送的目标可以是系统105，也可以是一个或多个其他乘客端设备120，还可以是一个或多个司机端设备140。
需要注意，上述对于乘客设备120提供乘客当前信息并处理备选目的地信息的流程或步骤的描述仅仅是示例性的，不构成对本申请的限制。可以理解，对于本领域的技术人员来说，在了解乘客端设备120在上述流程中所执行的操作和所获取、提供的信息后，可能在达到相同效果的情况下，对各个步骤进行任意组合，对实施上述方法的流程进行形式和细节上的各种修正和改变。例如，在一些实施例中，步骤945与955可以被跳过，乘客端设备120可以在接收到备选目的地信息后，不进行任何操作。又例如，乘客端设备120在步骤915还可以获取其他相关信息，包括但不限于，乘客端设备120在之前一段时间内的至少一个位置信息、乘客其他信息(健康信息，例如心跳、脉搏、血压)等信息。上述乘客其他信息可以由乘客端设备120的输入输出模块510中传感组件(图5中未画出)所获取，也可以由其他设备，例如，可穿戴设备、健康设备所获取。乘客端设备120 还可以在步骤925中将上述信息发送出去。诸如此类的变形，均在本申请的保护范围之内。
根据本申请的一些实施例，图10-A是POI引擎110根据特定的POI分类模型生成目的地相关信息的示例性流程。在步骤1010，POI引擎110接收乘客的地理信息。对地理信息的接收可以由乘客接口230完成。上述地理信息可以包括位置信息和时间信息。上述位置信息可以包括乘客当前所在的位置、订单的起始位置。上述时间信息可以包括当前的时间、乘客发出服务请求的时间、乘客设定的时间等。乘客当前所在的位置与订单的起始位置可以相同也可以不同。上述乘客的当前位置和/或订单的起始位置可以是由特定的定位技术定位得到的，也可以是通过乘客手动输入具体的地址名称得到的。定位技术的描述可以参见本说明书中其他部分，如图5及其相关描述，在此不再赘述。
在步骤1020，POI引擎110可以根据特定的POI分类模型生成备选的目的地。该步骤可以由处理模块210完成。在一些实施例中，上述的特定的POI分类模型是与乘客相关的。每个乘客都有与其对应的POI分类模型。上述POI分类模型可以存储在用户数据库630、存储模块220、或按需服务系统105中其他具有存储功能的模块或单元中。关于上述特定的POI分类模型的确定过程参考图10-B中的描述。POI引擎110可以根据上述POI分类模型判断乘客当前所在的位置或者订单的起始位置的所属的POI分类类型。进一步的，POI引擎110可以根据乘客所在的位置或者订单的起始位置的所属的POI分类类型确定出订单终止位置的POI分类类型。在一些实施例中，POI引擎110可以根据乘客所在的位置或者订单的起始位置的所属的POI分类类型以及当前的时间、乘客发出服务请求的时间、或者乘客设定的出发时间来确定订单终止位置的POI分类类型。根据订单终止位置的POI分类类型，POI引擎110可以生成至少一个备选的目的地信息。
上述备选的目的地的数量可以是任意的，例如，一个、两个、三个、四个、五个等。上述备选的目的地可以属于相同的POI分类类型，也可以属于不同的POI分类类型，例如，两个POI分类类型、三个POI分类类型等。上述生成的备选的目的地的数量和/或目的地所属的POI分类类型的 数量可以是固定的，也可以是可调整的。例如，在一些实施例中，POI引擎110可以接收来自乘客端设备120对于目的地数量的设置为N1，将目的地所属的POI分类类型的数量设置成N2。每个POI分类类型中的目的地数量可以是固定的，也可以是可调整的。
在一些实施例中，POI引擎110还可以对生成的备选的目的地按照特定的排序规则进行排序，例如步骤1030。上述排序可以由处理模块210中的排序单元370完成。上述特定的排序规则可以是依据包括概率大小、距离的长短、时间的先后顺序、花费时间的长短、所需费用的多少、采用的出行方式的多少等中的一种或多种的组合。在一些实施例中，POI引擎110可以通过计算单元350计算从订单的起始位置到达备选的目的地的时间、距离、所需的费用、所需要的出行方式的种类、不同出行方式对应的订单成交率等中的一种或多种。排序单元370可以根据计算单元350的结果，对备选的目的地进行排序。在一些实施例中，排序单元370可以按照上述备选的目的地的使用次数或者频率对备选的目的地进行排序。在步骤1040，POI引擎110可以通过乘客接口230发送排序后的备选的目的地给乘客端设备120。发送给乘客端设备120的备选的目的地的数目可以上述参与排序的备选的目的地中的一个或多个。
在一些实施例中，步骤1020生成的目的地信息中可以包含一种推荐的出行方式或多种出行方式的组合，还可以包括选择不同出行方式或者不同出行方式组合的所需的费用。在步骤1030中，POI引擎110可以按照出行方式的多少或者所需费用的多少对备选的目的地信息进行排序。
在步骤1040，POI引擎110可以发送备选的目的地到乘客端设备120和/或司机端设备140。上述发送的备选的目的地可以是经过排序的也可以是未经过排序的。
在一些实施例中，POI引擎110可以发送步骤1020中生成的全部的备选的目的地给乘客端设备120。在一些实施例中，POI引擎110可以发送步骤1020中备选的目的地中按照一定规则排序后的排名前N的目的地给乘客端设备120。N的取值可以包括2、3、4、5、6、7、8、9、10、或者大于10。在一些实施例中，POI引擎110可以将上述N个目的地经过排序 后发送给乘客端设备120。排序可以基于一种或多种规则，如使用次数从大到小、频率从高到低、出行方式从少到多、花费时间从短到长、所需费用从少到多、不同出行方式对应的订单成交率等。在一些实施例中，该排序规则可以是POI引擎110自动设置的。在一些实施例中，该排序规则可以是乘客预设的。在一些实施例中，该排序规则可以是乘客根据一次订单(如当前订单或符合一个条件的订单)指定的。例如，POI引擎110可以提供一种或多种排序方式供乘客选择。乘客可以指定其中的一种或多种排序方式和/或适用条件。又例如，POI引擎110允许乘客自己定义一种或多种排序方式和/或适用条件。举例说明，排序可以是基于多个因素，POI引擎110允许乘客自己定义各因素在计算排序时的权重。在一些实施例中，POI引擎110可以将上述N个目的地按照随机的排序进行发送。
在一些实施例中，POI引擎110可以进一步接收来自乘客端设备120对于备选的目的地的处理。在一些实施例中，上述处理可以包括直接选择其中的一个目的地发送给POI引擎110。在一些实施例中，上述处理包括选择其中的多个发送给POI引擎110。在一些实施例中，上述处理包括删除一个或多个备选的目的地。需要注意的是，以上关于对于POI引擎110发送的至少一个备选的目的地的处理的描述只是示例性的描述，不构成对本申请的限制。在一些实施例中，还可以包括其他的处理方式。POI引擎110接收到来自乘客端设备120的处理结果之后可以将处理结果发送给司机端设备140。例如，POI引擎110将接收到的来自乘客端设备120对于上述备选的目的地的选择，并将这个选择作为订单的终止位置。POI引擎110可以将包含订单的起始位置和上述订单的终止位置的订单发送给司机端设备140。
需要注意的是，以上对生成目的地的实施例的描述仅仅是具体的示例，不应被视为是唯一可行的实施方案。显然，对于本领域的专业人员来说，在了解生成目的地的基本原理后，可能在不背离这一原理的情况下，对生成目的地的具体方式与步骤进行形式和细节上的各种修正和改变。但是这些修正和改变仍在以上描述的范围之内。在一些实施例中，上述流程中的一些步骤是可以省略的，例如，步骤1030。POI引擎110可以直接将生成 的备选的目的地进行发送，而不需要经过排序。在一些实施例中，上述流程还可以包括其他步骤，如存储。上面描述的步骤的中间处理结果和/或最终处理结果可以进行存储。存储的位置可以是存储模块220、数据库130或按需服务系统105内其他具有存储功能的模块或单元。
在一些实施例中，步骤1010也不是必需的。当POI引擎110接收到乘客的服务请求信号时，可以直接根据当前的时间判断出乘客可能的出行轨迹，而不必采集乘客当前所在位置和/或订单的起始位置。上述服务请求信号可以包括POI引擎110检测到的提供服务的应用被打开。在一些实施例中，上述出行轨迹可以指订单的起始位置和终止位置。以上对于生成备选的目的地的描述也同样适用于生成备选的出行轨迹的描述，这里不再赘述。诸如此类的变形，均在本申请的保护范围之内。
根据本申请的一些实施例，图10-B展示的是建立POI分类模型的示例性实施例。在一些实施例中，POI分类模型是与乘客个人相关的，例如，与乘客的账号名称相关联。每个乘客都有其特定的POI分类模型。为了说明方便，下面只针对一个乘客的情况进行描述。在步骤1015，POI引擎110可以获取与该乘客(或其他乘客端设备120使用者)相关的历史订单信息。上述历史订单信息可以是与该乘客相关的所有历史订单信息，也可以是在预设时间段内的与该乘客相关的历史订单信息。上述预设的时间段可以包括一天或几天、一周或几周、一个月或几个月、一个季度或几个季度、一年或几年等。在一些实施例中，上述预设的时间段可以是两个月。在一些实施例中，上述预设的时间段可以是随机给出的，也可以是一个固定的值。在一些实施例中，上述预设的时间段可以根据历史经验或者实验数据确定。上述历史订单信息可以包括历史订单的起始位置、历史订单的终止位置、乘客发出历史服务请求的时间、或者乘客设定的历史出发时间等中的一种或多种的组合。上述历史订单信息可以来自于数据库130中的历史订单数据库610、存储模块220、或按需服务系统105内其他具有存储功能的模块或单元。
在步骤1025，POI引擎110可以根据按需服务系统预先建立的地点分类器对上述乘客的历史订单信息进行处理。上述地点分类器的建立方法可 以参考本说明书下文的相关描述。上述历史订单信息可以包括位置信息、时间信息、所需费用信息等中的一种或多种的组合。上述位置信息可以包括订单的起始位置和/或终止位置。上述时间信息可以包括乘客发出服务请求的时间或乘客设定的出发时间。上述处理包括对上述历史订单中的起始位置和/或终止位置进行地址分类，生成历史订单的起始位置和/或终止位置对应的地址分类类型。上述地址分类类型可以包括交通设施、房产小区、办公区、餐饮美食、酒店宾馆、休闲娱乐、地址地名、购物消费等。
在一些实施例中，在步骤1035，POI引擎110可以根据历史订单中起始位置和/或终止位置的地址分类结果确定该乘客的POI类型。上述POI类型可以是一种多种。通过对该乘客的所有历史订单或者历史上的一定时间段内的历史订单中的起始位置和/或终止位置的地址分类类型，POI引擎110就可以预测出该乘客的历史上的出行目的和/或出行轨迹。上述历史上的一段时间可以是一周或几周、一个月或几个月、一个季度或几个季度、一年或几年等。例如，POI引擎110确定的该乘客在历史上或历史上的一定时间段内的POI类型为“餐饮美食”和“房产小区”，那么就可以确定该乘客在是历史上或历史上的一定时间段内主要在居住地和餐厅之间走动。从而可以知道该乘客在历史上或历史上的一定时间段内更倾向于饮食消费。
在一些实施例中，在步骤1035，POI引擎110可以根据历史订单中的时间信息以及历史订单中的地址信息确定乘客的POI类型。上述POI类型可以是一种多种。上述历史订单中的时间信息可以包括一天中的任意时间点或时间段。通过该乘客的所有历史订单或者历史上的一定时间段内的历史订单中的起始位置和/或终止位置的地址分类类型，并根据该乘客发出服务请求的时间或者该乘客设定的出发时间，POI引擎110就可以预测出该乘客在历史上或历史上的一定时间内的出行目的和/或出行轨迹。例如，在上午8点到10点之间，该乘客的历史订单的起始位置在历史上或历史上的一段时间内的地址分类类型为“房产小区”。该乘客的历史订单的终止位置在历史上或历史上的一段时间内的地址分类类型为“办公区”，该乘客的POI类型就是“房产小区”和“办公区”。那么就可以确定该乘客在 历史上或历史上的一段时间内主要在居住地和工作场所之间走动。从而可以推知，该乘客在历史上或历史上的一段时间内更倾向于工作。
基于上述确定的乘客的POI类型就可以得到POI分类模型。根据上述POI分类模型，就可以推测出乘客的行为习惯。进而，在获得了某一乘客的当前位置信息和/或时间信息，就可以推测出成该乘客的目的地所属的地址分类类型，进而可以推测出乘客的目的地。
下面是对步骤1025中地点分类器的建立方法的具体描述。需要注意的是，以下描述只是示例性的，不构成对本申请的限制。建立地点分类器的过程可以包括以下步骤：(a)处理模块210可以获取多个已知地址分类类型的文本地址数据；(b)文本处理单元390可以采用预设的分词方法对上述多个已知地址分类类型的文本地址数据进行分词处理，生成多个特征文本；(c)模型训练单元395可以将上述多个特征文本作为训练数据对上述多个特征文本进行训练，生成一个地点分类器。训练上述地点分类器的方法可以包括朴素的贝叶斯算法、权重贝叶斯算法、决策树、Rocchio、神经网络、线性最小平方拟合、K-近邻、遗传算法、最大熵、线性回归模型训练方法等中的一种或多种的组合。上述线性回归模型可以包括逻辑斯特回归模型和支持向量机模型。本申请所描述的训练地点分类器的方法还可以包括其他算法或模型。在一些实施例中，地点分类器还可以不经过数据训练而直接根据经验数值获得。
在一些实施例中，处理模块210还可以包含一个样本均衡单元(没有在图3中画出)。在获得多个已知地址分类类型的文本地址数据之后，样本均衡单元可以对上述多个已知地址分类类型的文本地址数据进行样本均衡。上述样本均衡包括：根据上述已知地址分类类型的文本地址数据的数量以及地址分类类型的数量，计算单元350可以计算每个地址分类类型的文本地址数据的平均数量。在一些实施例中，上述样本均衡可以采用“有放回抽样”的方法。如果某一地址分类类型实际拥有的文本地址数据的数量小于上述平均数量，则增加若干该地址分类类型的文本地址数据，使得该地址分类类型拥有的文本地址数据的数量等于上述平均值。反之，如果某一地址分类类型实际拥有的文本地址数据的数量大于上述平均数量，则 去除若干该地址分类类型的文本地址数据，使得该地址分类类型拥有的文本地址数据的数量等于上述平均值。
在步骤(b)中，文本处理单元390可以对每个已知地址分类类型的文本地址数据进行分词，生成多个特征文本。上述特征文本可以看作为一个向量，即X＝(x1,x2,x3,…,xm)，X中每个元素可以称为一个特征文本，m表示的是一个文本地址数据经分词后得到的特征本文的数量。例如，“北京上地地铁站”分词的结果为“北京”、“上地”、和“地铁站”三个特征文本。在一些实施例中，处理模块210还可以包括一个冗余去除单元。在一些实施例中，上述冗余去除单元可以包含在文本处理单元390中。上述文本去除单元可以去除掉特征文本中长度小于一个阈值的特征文本。在一些实施例中，上述阈值可以为2、3、4等。例如，“我在北京西二旗地铁站”分词的结果为“我”、“在”、“北京”、“西二旗”、和“地铁站”。由于“我”和“在”的长度较短，可以删除长度小于2的特征文本，那么剩余的特征文本为“北京”、“西二旗”、和“地铁站”。
在步骤(c)中，模型训练单元395可以将上述多个特征文本作为训练数据对上述多个特征文本进行训练，生成一个地点分类器。在一些实施例中，模型训练单元395可以采用朴素贝叶斯算法训练地点分类器。为了描述方便，记地址分类类型集合为Y＝(y1,y2,y3,…,yq)，其中Y中的元素表示的是不同的地址分类类型。计算单元350可以计算X和Y的每一种组合的后验概率P(Y|X)。根据贝叶斯公式，P(Y|X)＝P(X|Y)*P(Y)/P(X)。P(Y|X)表示的是文本地址数据X属于某种分类类型的概率。
处理模块210中的计算单元350可以计算文本地址数据属于每种地址分类类型的概率。在一些实施例中，上述文本地址数据属于每个地址分类类型的概率可由公式2得到：
Figure PCTCN2016072357-appb-000003
Figure PCTCN2016072357-appb-000004
(公式2)
其中，P(Y＝yj)表示的是地址分类类型集合中地址分类类型yj所占的比例；P(xj|Y＝yj)表示的是地址分类类型yj中特征文本xi所占的比例； P(X)是上述订单的起始位置或终止位置出现的概率。计算单元350可以基于数据统计得到P(Y＝yj)和P(xi|Y＝yj)。
处理模块210中的计算单元350可以计算上述文本地址数据属于每种地址分类类型的概率。为了描述方面，将地址分类类型的概率按照从大到小的顺序依次记为P1、P2、P3、…、Pq，其中，q为地址分类类型的总数。根据上述不同的地址分类类型的概率，处理模块210可以判断上述文本地址数据所属的地址分类类型。在一些实施例中，POI引擎110中的处理单元210可以将上述概率中最大的一个概率值所对应的的地址分类类型作为上述文本地址数据的地址分类类型。在一些实施例中，POI引擎110可以选出上述概率中最大的两个概率值(即P1和P2)进行比较。如果P1>Z*P2，且Z大于1，那么可以将P1所对应的的地址分类类型作为上述文本地址数据的地址分类类型。Z的取值可以是1～2、2～3、3～4、4～5、5～6、或大于6。在一些实施例中，Z的取值为3～5。例如，“上地地铁站”所属地址分类类型为“交通设施”的概率为0.6，所属地址分类类型为“地址地名”的概率为0.1，且设置Z的取值为3。0.6>3*0.1，因此，处理单元210可以确定“上地地铁站”所述的地址分类类型为“交通设施”。
以上描述的是生成地点分类器的过程。基于上述地点分类器就可以对一个订单的起始位置和/或终止位置进行地址分类，判断该订单的起始位置和/或终止位置所属的地址分类类型。需要注意的是，以上描述只是示例性的，并不能把本申请限制在所列举的是实施例范围之内。可以理解，对于本领域的技术人员来说，在了解生成地点分类器的基本原理后，对实施上述方法的形式和细节上进行各种修正和改变。诸如此类的变形，均在本申请要保护的范围之内。
根据本申请的一些实施例，图11是POI引擎110向用户提供出行路径的示例性流程图。如图11所示，在步骤1110，POI引擎110可以获取用户的至少一条出行路径。用户可以是乘客，也可以是司机。该步骤可以由乘客接口230和/或司机接口240完成。在一些实施例中，上述出行路径可以来自乘客端设备120和/或司机端设备140、数据库130或信息源160。需要注意的是，获取用户的至少一条出行路径的方式有多种。例如，用户 可以预先设定多个常用的出行路径；或者，根据用户日常出行数据、消费习惯等运用大数据运算出用户可能的至少一条出行路径。根据本申请的一些实施例，所述出行路径包括始发地址和目的地址。
在步骤1120，POI引擎110可以计算上述至少一条出行路径的概率。对上述至少一条出行路径的概率计算可以由POI引擎中的处理模块210完成。例如，在一些实施例中，POI引擎110可以基于所述历史概率和/或与出行路径相关的信息，通过POI引擎110中的处理模块210中的计算单元350，从而计算所述至少一条出行路径的概率。每一条出行路径的历史概率可以通过对用户历史出行数据的计算获得。在一些实施例中，计算单元350用于计算每一条出行路径的历史概率。在一些实施例中，计算单元350用于根据所述历史概率和/或与出行路径相关的信息，计算所述每一条出行路径的概率。根据本申请的一些实施例，所述与出行路径相关的信息包括但不限于当前位置，当前天气情况，当前日期和/或当前时间等的一种或几种的组合。例如，所获取的用户的出行路径分别为R1、R2、……、Rn；每一条出行路径所对应的已出行的次数分别为C1、C2、……、Cn。假设用户至少曾经出行一次，即
Figure PCTCN2016072357-appb-000005
那么每一条出行路径的历史概率分别为
Figure PCTCN2016072357-appb-000006
Figure PCTCN2016072357-appb-000007
可以得出，对于所获取的用户预先设定的出行路径Ri，如果用户从未按此路径出行，即Ci＝0，则该路径Ri的历史概率为0。所述的与出行路径相关的信息具体指会对用户选择出行路径造成影响的因素可以包括用户当前位置、当前天气情况、当前日期、当前时间等中的一种或几种的组合。用户的消费行为可以指用户受需求动机的影响而做出消费决定并完成消费过程的行为。消费行为过程既是用户的思维、心理过程，也是不断采取行动、产生方案、解决问题的过程。用户选择出行路径可以是一种消费行为的过程。用户可以根据自身以及外界的各种条件来确定自身的出行需求。例如，在工作日的上班时间，乘客当前的位置可以是在家，则乘客最有可能选择打车去公司；在工作日的下班时间，乘客当前的位置在公司，则乘客最有可能选择打车回家；而如果是周末的下班时间，则乘客很有可能选择打车去酒吧或者电 影院等娱乐场所。又例如，对于雨雪天气，乘客的出行欲望可能不强烈，一旦选择出行，最有可能的目的地是距离不太远的日常生活相关的主要场所，如餐馆、银行、医院或者超市等。
在一些实施例中，计算每一条出行路径的概率可以基于计算的历史概率获得。例如，所获取的乘客/司机出行路径分别为R1、R2、……、Rn；相应的计算出的历史概率分别为H1、H2、……、Hn；则可以认为每一条出行路径的当前概率分别为H1、H2、……、Hn。在一些实施例中，计算每一条出行路径的概率也可以基于计算的历史概率和与出行路径相关的信息获得。例如，所获取的乘客/司机出行路径分别为R1、R2、……、Rn；相应的计算出的历史概率分别为H1、H2、……、Hn。为了描述方便，这里仅考虑只有一个与出行路径相关的信息：当前位置。乘客/司机的出行路径可以分为两组：始发地址为当前位置的路径集合G，假设其中包含的路径数为k，分别为R1、R2、……、Rk，相应的计算出的历史概率为H1、H2、……、Hk；以及始发地址不是当前位置的路径集合G2，其中包含的路径数为n-k，分别为Rk+1、Rk+2、……、Rn，相应的计算出的历史概率为Hk+1、Hk+2、……、Hn。对于集合G2中的每条路径，由于始发地址都不是当前位置，所以G2中的每条路径的当前概率为0；而对于集合G1中的每条路径，由于始发地址都是当前位置，所以“当前位置”对其中每条路径的影响系数相同。因此集合G1中的每条路径的概率为
Figure PCTCN2016072357-appb-000008
……、
Figure PCTCN2016072357-appb-000009
集合G2中的每条路径的概率为0。从而乘客/司机的出行路径R1、R2、……、Rn的当前概率分别为
Figure PCTCN2016072357-appb-000010
Figure PCTCN2016072357-appb-000011
……、
Figure PCTCN2016072357-appb-000012
0、……、0。在一些实施例中，计算每一条出行路径的概率也可以基于与出行路径相关的信息获得。例如，假设所获取的乘客/司机的出行路径如表1所示：
表1所获取的乘客/司机出行路径列表
出行路径ID 始发地址 目的地址
R1 某小区 少年宫
R2 某小区 老年活动中心
根据一些实施例，可能影响乘客/司机选择出行路径的因素(即与出行路径相关的信息)为时间和天气。分别对于每一个因素分配一个影响系数，用于表示该因素对于乘客/司机最终选择出行路径的影响的大小，如表2和表3所示：
表2时间因素对于乘客/司机选择出行路径的影响系数
出行路径ID 工作日 周末 节假日 敬老日
R1 50 100 150 20
R2 0 30 50 200
表3天气因素对于乘客/司机选择出行路径的影响系数
出行路径ID 晴天 雨天 雪天
R1 1 0.5 0
R2 1 0.5 0
如果当前是节假日并且是晴天，那么两条路径的选择系数分别为：R1的选择系数为150×1＝150；R2的选择系数为50×1＝50。因此，两条出行路径的概率分别为：R1的概率为150/(150+50)＝75％；R2的概率为50/(150+50)＝25％。如果当前是敬老日并且是晴天，那么两条路径的选择系数分别为：R1的选择系数为20×1＝20；R2的选择系数为200×1＝200。因此，两条出行路径的概率分别为：R1的概率为20/(20+200)＝9.1％；R2的概率为200/(20+200)＝90.9％。
本领域的技术人员应当理解，以上示例仅为本申请的可选的实施例，仅用于说明的目的，并不能把本申请限制在所举实施例范围之内。考虑到可以存在多种与出行路径相关的信息，以及每种信息对每条路径的影响多种多样，因此，可以针对各种不同的与出行路径相关的信息建立更复杂的数学模型，从而计算出每条路径的最终概率。
在步骤1130，POI引擎110可以根据计算的概率对该乘客/司机的出行路径进行排序。通过POI引擎110中的处理模块210中的排序单元370，按照所述计算的概率从大到小的顺序，对所述乘客/司机的出行路径进行排 序。
在步骤1140，POI引擎110将上述排序后的出行路径列表发送给乘客端设备120和/或司机端设备140。该步骤可以由乘客接口230和/或司机接口240完成。在一些实施例中，该出行路径列表可在乘客端设备120和/或司机端设备140中的显示单元520中显示并供乘客和/或司机选择。在一些实施例中，该出行路径列表中概率最大的出行路径可直接作为默认的出行路径填入相应的服务请求信息中。
需要注意的是，POI引擎110可以直接发送获取的乘客或司机的出行路径，而不必执行步骤1120和/或步骤1130。例如，当只获取乘客/司机的一条出行路径时，可以不必计算该出行路径的概率，直接向该乘客/司机发送出行路径。又例如，当只获取乘客/司机的一条出行路径时，计算该出行路径的概率为100％，并直接将该出行路径发送给该乘客/司机而不必执行步骤1130。
显然，本领域的技术人员应该明白，上述的本申请的各模块或各步骤可以用通用的计算装置来实现，它们可以集中在单个的计算装置上，或者分布在多个计算装置所组成的网络上，可选地，它们可以用计算装置可执行的程序代码来实现，从而可以将它们存储在存储装置中由计算装置来执行，或者将它们分别制作成各个集成电路模块，或者将它们中的多个模块或步骤制作成单个集成电路模块来实现。这样，本申请不限制于任何特定的硬件和软件结合。
以上所述仅为本申请可选实施例，并不用于限制本申请，对于本领域的技术人员来说，本申请可以有各种更改和变化。凡在本申请的精神和原则之内，所作的任何修改、等效替换、改进等，均应包含在本申请的保护范围之内。
根据本申请的一些实施例，图12-A是POI引擎110向乘客/司机提供出行方式规划的示例性流程图。如图12-A所示，在步骤1210，POI引擎110可以接收交通服务请求相关信息。该步骤可以由乘客接口230和/或司机接口240完成。根据本申请的一些实施例，通过乘客接口230和/或司机接口240，接收乘客设备发送的交通服务请求，并获取所述交通服务请求 的相关特征信息和基础信息。其中，所述基础信息包括但不限于出发时间、始发地及目的地信息等中的一种或几种的组合。所述相关特征信息包括但不限于始发地及目的地POI信息、实时天气信息、实时路况信息、各出行方式对应的司机偏好信息、预设范围内各出行方式对应的空闲司机数量、路面距离等中的一种或几种的组合。
在步骤1220，POI引擎110根据所述相关特征信息、基础信息，确定各单一出行方式对应于所述交通服务请求的出行信息。该步骤可以由POI引擎110中的处理模块210中的判定单元380完成。判定单元380用于根据所述相关特征信息、基础信息，确定各单一出行方式的出行信息。其中，所述出行信息可包括订单成交率、耗时、费用及行走距离等。则单一出行方式对应于所述打车请求的出行信息是指：基于该打车请求，每种出行方式的订单成交率、耗时、费用及行走距离等。在一些实施例中，判定单元380用于根据所述始发地及目的地信息，分别确定所述始发地及目的地对应的兴趣点POI信息；针对每种出行方式，根据所述始发地POI信息、目的地POI信息、出发时间、实时路况信息、该出行方式对应的司机偏好信息、空闲司机数量，对该出行方式的订单成交率进行估计；根据所述始发地、目的地及出行方式进行出行路线规划，获得路面距离、行程时间及拥堵程度，从而对总费用、行走距离及耗时进行估计。
在一些实施例中，所述判定单元380还可以用于对于多个预设的附加金额值，确定每个预设的附加金额值对应的订单成交率及乘客对该预设的附加金额值的接受率；根据每个预设的附加金额值对应的订单成交率及乘客的接受率，获取最佳附加金额值，并将所述最佳附加金额值对应的订单成交率作为最终的订单成交率。具体来说，服务端接收到打车请求，分析始发地、目的地对应的兴趣点(Point of Interest，简称POI)信息，如分析其是否为医院、小区、商圈等。进一步地，针对每种出行方式，根据实时交通、时间、起终点以及周边司机信息对订单成交率进行预估。而对于存在小费的出行方式，可输出一个订单成交率的预估值以及建议小费值，该建议小费值用于提高订单成交率。进一步地，针对每种出行方式，根据路线规划结果形成的路线对应的路面距离、行程时间、拥堵程度给出费用、 耗时及行走距离的预估，并将该费用和消费之相加得到总费用。从而得到多个单一出行方式的出行信息。
在一些实施例中，步骤1220具体包括如下子步骤1221，1222，和1223。图12-B是POI引擎110处理出行信息的示例性流程图。在步骤1221，根据所述始发地及目的地信息，分别确定所述始发地及目的地对应的兴趣点POI信息。在步骤1222，针对每种出行方式，根据所述始发地POI信息、目的地POI信息、出发时间、实时路况信息、该出行方式对应的司机偏好信息、空闲司机数量，对该出行方式的订单成交率进行估计。具体来说，该步骤可通过如下方式实现：采用预先建立的预测模型，预测各出行方式对所述打车请求的订单成交率。其中，所述预测模型为根据各出行方式在预设时间段内的历史订单的相关特征信息建立的预测模型，将所述打车请求的相关特征信息为所述预测模型的预测变量，各出行方式对所述打车请求的订单成交率为所述预测模型的目标变量。
进一步地，步骤1222中对该出行方式的订单成交率进行估计之后，该方法还包括：在步骤A01，根据多个预设的附加金额值，确定每个预设的附加金额值对应的订单成交率及乘客对该预设的附加金额值的接受率。其中，附加金额值即为小费。通过对多个预设的消费值对应的订单成交率和乘客的接受率进行预测，从而选取其中最佳的小费值。可理解的是，本步骤也可通过步骤1222中建立预测模型的方式，获取订单成交率及乘客对预设的附加金额值的接受率。其中，附加金额值为预测模型中的一个特性数据。在步骤A02，根据每个预设的附加金额值对应的订单成交率及乘客的接受率，获取最佳附加金额值，并将所述最佳附加金额值对应的订单成交率作为最终的订单成交率。
在步骤1223，根据所述始发地、目的地及出行方式进行出行路线规划，获得路面距离、行程时间及拥堵程度，以对总费用、行走距离及耗时进行估计。
通过上述步骤，可得到多种单一出行方式的小费、订单成交率、总费用、行走距离及耗时等出行信息。
回到图12-A，在步骤1230，POI引擎110根据各单一出行方式的出 行信息，采用全局优化算法确定组合出行方式，并获得所述组合出行方式对应于所述交通服务请求的出行信息。该步骤可以由POI引擎110中的处理模块210中的判定单元380中的计算子单元385完成。计算子单元385根据各单一出行方式的出行信息，采用全局优化算法确定组合出行方式，并通过判定单元380获得所述组合出行方式的出行信息。在一些实施例中，全局优化算法可为贪心算法等。在一些实施例中，判定单元380及其计算子单元385根据各单一出行方式的订单成交率、耗时、费用及行走距离，采用贪心算法，以节省时间为目标确定耗时从少到多的多个组合出行方式，并获取所述多个组合出行方式对应于所述打车请求的出行信息；和/或，根据各单一出行方式的订单成交率、耗时、费用及行走距离，采用贪心算法，以节省费用为目标确定费用从少到多的多个组合出行方式，并获取所述多个组合出行方式对应于所述打车请求的出行信息。举例来说，将多个单一出行方式进行综合，采用贪心算法找出最合适的组合出行方式。而组合出行方式对应于所述打车请求的出行信息是指：基于该交通服务请求，每种组合出行方式的订单成交率、耗时、费用及行走距离等。在一些实施例中，步骤1230具体包括如下步骤：
在步骤1231，根据各单一出行方式的订单成交率、耗时、费用及行走距离，采用贪心算法，以节省时间为目标确定耗时从少到多的多个组合出行方式，并获取所述多个组合出行方式对应于所述打车请求的出行信息；在步骤1232，根据各单一出行方式的订单成交率、耗时、费用及行走距离，采用贪心算法，以节省费用为目标确定费用从少到多的多个组合出行方式，并获取所述多个组合出行方式对应于所述打车请求的出行信息。由此可见，全局优化算法中可按照节省时间和节省费用两个方向分别输出，如此方便乘客后续根据自己的需要选择出行方式。步骤1231和步骤1232可以都执行，或只执行其中一步。
在步骤1240，根据所述各单一出行方式的出行信息、所述组合出行方式的出行信息，将所有单一出行方式、组合出行方式按照预设的出行条件进行排序并发送至所述用户端设备。该步骤可以由POI引擎110中的处理模块210中的排序单元370以及乘客接口230和/或司机接口240完成。根 据所述各单一出行方式的出行信息、所述组合出行方式的出行信息，排序单元370按照预设的出行条件对单一出行方式、组合出行方式进行排序并通过乘客接口230和/或司机接口240发送出行方式列表。在一些实施例中，排序单元370用于根据各单一出行方式的订单成交率、耗时、费用及行走距离，各组合出行方式的订单成交率、耗时、费用及行走距离，按照预设的出行条件对所有单一出行方式及所有组合出行方式进行排序。其中，所述预设的出行条件可以包括预设的行走距离范围、预设的费用及预设的耗时中的一个或多个。具体来说，本步骤主要是对多种单一出行方式、组合出行方式进行综合排序，按照乘客输入或者系统默认的出行条件或排序方式排序。进一步地，该方法还可以包括如下步骤：所述乘客端设备120和/或司机端设备140接收按序排列的各单一出行方式及组合出行方式并显示，以供乘客对出行方式进行选择。其中，乘客端设备120和/或司机端设备140包括显示单元520，用于显示接收的按序排列的各单一出行方式及组合出行方式列表，以供乘客对出行方式进行选择。
在一些实施例中，步骤1240可以包括根据各单一出行方式的订单成交率、耗时、费用及行走距离，各组合出行方式的订单成交率、耗时、费用及行走距离，按照预设的出行条件对所有单一出行方式及所有组合出行方式进行排序。其中，所述预设的出行条件包括：预设的行走距离范围、预设的费用及预设的耗时中的一个或多个。即出行条件可设置为多个，如最省钱且行走距离小于1km。
由此可见，本实施例利用按需服务系统105的全局数据以及地理信息系统的知识，主动帮助乘客找到最适合的出行方式。比如后台发现乘客当前周边订单的出租车成交率非常低，而乘客的订单质量也并不是很高，也就是说该乘客发出租车订单失败的几率会非常高；而此时，系统后台发现专车成交率相对高很多，可以优先推荐使用专车。又或者后台发现乘客目前正处于一个大巴站台周边，5分钟后会有一辆合适的大巴经过，可以将乘客拉到离目的地非常近的位置。这样后台可以为乘客推荐使用大巴出行，并告知大巴到达时间。再或者后台可以综合利用大巴车或者出租车，先通过大巴将乘客拉往一个成交率非常高的位置，那里的订单相对少而司机也 相对更喜欢当前乘客的这种订单。因此最终后台会给出多种推荐出行方式，并给出乘客的预估价格，预估时间，再由乘客自己选择出行方式。
本实施例提供了一种出行方式的规划方法，由打车软件平台综合多方面信息获得多条推荐出行方式，多条推荐出行方式包括单一出行方式及组合出行方式；并将多条推荐出行方式按照预设的排序方式进行排序，如按照费用、耗时或行走距离由少到多进行排序，以供乘客选择，从而有效提升订单成交率，节省打车时间或费用，优化乘客打车体验。
为了更好地理解与应用本申请提出的一种出行方式的规划方法，本申请进行以下示例，且本申请不仅局限于以下示例。
例如，乘客A想立刻从北京回龙观北去协和医院，发出订单后，打车软件服务端检测到该订单为实时请求订单，并分析出目的地属于医院，在前门商圈。将这些信息发往各个产品线(即多个出行方式)的订单接收程序，各个产品线结合交通数据、对应产品线司机偏好、空闲司机数等特征对成交率进行预测，并按照对应各个小费值对应的成交概率和乘客的接收程度，给出各个产品线的最佳小费值及成交概率。比如结果如下：{{出租车：小费5元；成交概率0.8；总费用：90元；行走距离：700米；耗时：1.15小时}{专车：小费0元；成交概率0.9；总费用：120元；行走距离：200米：耗时：1.05小时}{顺风车：小费5元；成交概率0.8；总费用60元；行走距离：800米；耗时：1.2小时}{大巴车:小费0元；成交概率：1.0；总费用：10元；行走距离：3km；耗时：2小时}}。
进一步地，数据请求到了路线综合程序，路线综合程序按照系统默认的优化方式或者乘客指定的优化方式，按照贪心优化的算法进行逐步调优。假如，目前选择的优化方向是最省钱方向且要求行走距离小于1千米。则先从现有线路中最省钱的大巴车出发，按照大巴车停泊的多个站台分别计算选择顺风车、出租车、专车的总费用，此时发现在大巴车的第三站下车后做顺风车的总费用为20元；耗时为1.4小时，行走距离为900米。因此最终选择输出大巴车做3站之后做顺风车出行的方式。由此可见，全局优化采用的贪心算法，优先从优化方向最优的产品线出发。当第一个最优方案不符合约束条件时，选择第二个备选最优方案(比如顺风车)。
应当注意的是，在本申请的系统的各个部件中，根据其要实现的功能而对其中的部件进行了逻辑划分，但是，本申请不受限于此，可以根据需要对各个部件进行重新划分或者组合，例如，可以将一些部件组合为单个部件，或者可以将一些部件进一步分解为更多的子部件。
本申请的各个部件实施例可以以硬件实现，或者以在一个或者多个处理器上运行的软件模块实现，或者以它们的组合实现。本领域的技术人员应当理解，可以在实践中使用微处理器或者数字信号处理器(DSP)来实现根据本申请实施例的系统中的一些或者全部部件的一些或者全部功能。本申请还可以实现为用于执行这里所描述的方法的一部分或者全部的设备或者装置程序(例如，计算机程序和计算机程序产品)。这样的实现本申请的程序可以存储在计算机可读介质上，或者可以具有一个或者多个信号的形式。这样的信号可以从因特网网站上下载得到，或者在载体信号上提供，或者以任何其他形式提供。
以上实施方式仅适于说明本申请，而并非对本申请的限制，有关技术领域的普通技术人员，在不脱离本申请的精神和范围的情况下，还可以做出各种变化和变型，因此所有等同的技术方案也属于本申请的范畴，本申请的专利保护范围应由权利要求限定。
根据本申请的一些实施例，图13是POI引擎110检测车辆状态的示例性流程图。如图13所示，在步骤1310，POI引擎110可以接收来自车辆的地理数据流，并获取车辆在给定时间段内的多个地理坐标。该步骤可以由乘客接口230和/或司机接口240完成。根据本申请的一些实施例，地理数据流可以利用定位技术获取，所述定位技术包括但不限于全球定位系统(GPS)技术；全球导航卫星系统(GLONASS)技术；北斗导航系统技术；伽利略定位系统(Galileo)技术；准天顶卫星系统(QAZZ)技术；基站定位技术；以及WiFi定位技术。根据本申请的一些实施例，所述通过GPS定位技术获得的GPS数据流包括所述车辆按给定时间频率实时上报的多个GPS坐标，其中每个GPS坐标对应于所述车辆在每个采集时间点的位置。在一些实施例中，所述车辆按给定时间频率实时上传的多个GPS坐标，其中每个GPS坐标对应于所述车辆在每个采集时间点的位置。例如，可以利 用智能设备上的GPS模块，实时获取所在车辆当前的GPS坐标；通过打车软件通过的长连接服务，实时上传按一定频率采集的GPS数据。在一些实施例中，POI引擎110中的处理模块210中的地址解析单元310可以从GPS数据流中提取与给定时间点相关的给定时间段内的多个GPS坐标。例如，通过GPS定位技术获得的GPS实时数据流Gi＝{sxi，syi，ti}，其中，i＝1,2,3，……n，其中sx表示GPS数据中的经度，sy表示GPS数据中的纬度，t表示GPS数据采集时间点。根据给定的时间点t。可以获取时间区间t-tj<ε中的多个GPS坐标Gj＝{sxj，syj}，其中j＝1，2，3，……k。
在步骤1320，POI引擎110计算多个地理坐标的中心点坐标，以及每个地理坐标到该中心点坐标的距离和方向分布。该步骤可以由POI引擎110中的处理模块210中的计算子单元385完成。在一些实施例中，计算子单元385用于计算多个GPS坐标的中心点坐标；计算每个GPS坐标到中心点坐标的欧式距离和弧度；以及基于每个欧式距离和每个弧度，计算每个GPS坐标到所述中心点坐标的归一化距离和方向分布。其中，所述欧式距离是在聚类分析中常用距离计算方法的一种。在一些实施例中，距离计算方法包括但不限于欧式距离、曼哈顿距离、马氏距离和/或汉明距离等。例如，通过地址解析单元310获取的车辆在给定时间段内的多个GPS坐标，即Gj＝{sxj，syj}，其中j＝1，2，3，……k。首先，按如下公式3来计算多个GPS坐标的中心点坐标g_0：
Figure PCTCN2016072357-appb-000013
  (公式3)
其次，计算每个GPS坐标到中心点坐标的欧式距离ω(Gj,g0)和弧度ψ(Gj,g0)。然后，按公式4和公式5，基于每个欧式距离ω(Gj,g0)和每个弧度ψ(Gj,g0)，计算每个GPS坐标到中心点坐标的归一化距离S(Gj,g0)和方向分布θ(Gj,g0)，公式4中的W是依据试验数据和实际经验所选择的阈值：
Figure PCTCN2016072357-appb-000014
(公式4)
和
Figure PCTCN2016072357-appb-000015
 (公式5)
在步骤1330，基于距离和方向分布，确定车辆的状态。该步骤可以由POI引擎110中的处理模块210中的判定单元380完成。在一些实施例中，判定单元380及其计算子单元385基于每个GPS坐标到所述中心点坐标的归一化距离和方向分布，计算平均归一化距离和总的方向分布；以及基于平均归一化距离和第一阈值以及总的方向分布和第二阈值，确定所述车辆的状态。例如，通过计算子单元385获得的每个GPS坐标到中心点坐标的归一化距离S(Gj,g0)和方向分布θ(Gj,g0)。首先，按公式6和公式7来计算平均归一化距离Savg和总的方向分布θsum：
Figure PCTCN2016072357-appb-000016
(公式6)
和
Figure PCTCN2016072357-appb-000017
(公式7)
然后，按公式8确定车辆状态R，其中1表示车辆静止，0表示车辆非静止；
Figure PCTCN2016072357-appb-000018
表示第一阈值，η表示第二阈值，两个阈值依据试验数据和实际经验来选择。在一些实施例中，车辆静止状态也可以是低速行驶状态。
Figure PCTCN2016072357-appb-000019
(公式8)
应当理解，示例性流程图可以描述为流程图、流程图表、数据流程图、结构图或者框图的过程。当过程的步骤完成时，过程可以结束，也可以具有图中未示出的额外的步骤。根据本申请的一些实施例，POI引擎110确定车辆的状态可以进一步包括：存储车辆的状态和中心点的坐标；以及响应于车辆状态查询请求，发送车辆状态和中心点的坐标。在一些实施例中，POI引擎110中的存储模块220可以用于存储所述车辆的状态和所述中心点的坐标。在一些实施例中，POI引擎110中的乘客接口230和/或司机接口240可以用于响应车辆状态查询请求，发送所述车辆状态和所述中心点 的坐标。例如，在打车平台中，可以将车辆的状态R和中心点坐标g_0保存到存储设备中；当按需服务系统105发送车辆状态查询请求时，从存储设备中读取对应于查询时间点的车辆的状态R和中心点坐标g0并发送至按需服务系统105。在一些实施例中，车辆经由乘客端设备120和/或司机端设备140以一定频率将GPS数据上报给按需服务系统105。POI引擎110中的乘客接口230和/或司机接口240接收来自乘客端设备120和/或司机端设备140的GPS数据流；地址解析单元310获取车辆在给定时间段内的多个GPS坐标；计算子单元385计算多个GPS坐标的中心点坐标，以及每个GPS坐标到所述中心点坐标的距离和方向分布；以及基于所述距离和所述方向分布，判定单元380确定车辆的状态。判定单元380可以将车辆的状态和中心点坐标存储在POI引擎110中的存储模块220和/或数据库130，并且响应于按需服务系统105发送的车辆状态查询请求，从存储模块220和/或数据库130中读取对应于查询时间点的车辆状态和中心点坐标，并将车辆状态数据发送至按需服务系统105。在一些实施例中，计算单元350可以根据给定时间段内的车辆的状态和/或多个GPS坐标计算服务费用。在一些实施例中，计算单元350及判定单元380的计算子单元385可以根据确定的车辆状态计算服务费用。
在一些实施例中，计算单元350或计算子单元385可以根据车辆的状态以及车辆不同状态的持续时间计算服务费用。在一些实施例中，当车辆处于静止状态或低速行驶状态(例如，平均行驶速度低于某一阈值)时，采用按照时间计价的方式，即按照每分钟的服务费用计价。可选地，可以设定一个或多个单位时间费率。
需要注意，确定低速行驶状态所基于的阈值可以是一个预先设定的速度值，也可以是基于车辆所在位置与时间等因素所确定的动态速度值。低速行驶状态可以有一个，也可以有多个。低速行驶状态的多个阶段可以对应多个不同的速度范围。当低速行驶状态有多个阶段时，可以为这些状态设置各自不同的单位时间费率，也可以为其中两个或更多的状态设置相同的单位时间费率。
在一些实施例中，当车辆处于运动状态时，或车辆处于高速行驶状态 (例如，平均行驶速度超过某一阈值)时，采用按照距离计价的方式，即按照每单位距离的服务费用计价。可选地，可以设定一个或多个单位距离费率。
需要注意，确定高速行驶状态所基于的阈值可以是一个预先设定的速度值，也可以是基于车辆所在位置与时间等因素所确定的动态速度值。高速行驶状态可以有一个，也可以有多个。高速行驶状态的多个阶段可以对应多个不同的速度范围。当高速行驶状态有多个阶段时，可以为这些状态设置各自不同的单位距离费率，也可以为其中两个或更多的状态设置相同的单位距离费率。
在一些实施例中，完成一个订单的过程中可能包含多次车辆状态的转变，计算子单元385可以统计车辆静止状态或低速运行状态的持续时间，然后由计算单元350或根据单位时间费率计算出静止状态与低速行驶状态阶段的服务费用。另外，计算子单元385可以统计车辆高速运行状态的持续时间和距离，然后由计算单元350根据单位距离费率计算出车辆处于高速行驶状态的服务费用。根据静止状态阶段、低速行驶状态与高速行驶状态的服务费用，计算单元350最终可以计算全程的总服务费用。在一些实施例中，服务费用可以在交通服务过程中计算，即费用的计算是实时的。在一些实施例中，服务费用可以在交通服务结束之后统一计算。
以上所述仅为交通服务定价的可选实施例，并不用于限制交通服务定价的机制或远离，对于本领域的技术人员来说，交通服务定价的实施方式可以有各种更改和变化。例如，计算单元350也可以对低速行驶状态按照单位距离费率进行计价。又例如，计算单元350也可以对高速行驶状态按照单位时间费率进行计价。凡在本申请的精神和原则之内，所作的任何修改、等效替换、改进等，均应包含在本申请的保护范围之内。
显然，本领域的技术人员应该明白，本申请的上述各模块或各步骤可以用通用的计算装置来实现，它们可以集中在单个的计算装置上，或者分布在多个计算装置所组成的网络上，可选地，它们可以用计算装置可执行的程序代码来实现，从而可以将它们存储在存储装置中由计算装置来执行，或者将它们分别制作成各个集成电路模块，或者将它们中的多个模块或步 骤制作成单个集成电路模块来实现。这样，本申请不限制于任何特定的硬件和软件结合。
以上所述仅为本申请可选实施例，并不用于限制本申请，对于本领域的技术人员来说，本申请可以有各种更改和变化。凡在本申请的精神和原则之内，所作的任何修改、等效替换、改进等，均应包含在本申请的保护范围之内。
根据本申请的一些实施例，图14是POI引擎110确定乘客/司机的定位信息异常的示例性流程图。如图14所示，在步骤1410，POI引擎110可以获取乘客/司机在给定时间段内的多个地理坐标。该步骤可以由乘客接口230和/或司机接口240完成。根据本申请的一些实施例，利用定位技术，来获取乘客/司机在给定时间段内的多个地理坐标的位置信息。根据本申请的一些实施例，给定的时间段可以是根据历史经验和/或试验数据确定的一段时间，例如，十分钟，半个小时，一个小时等。乘客/司机在给定的时间段内以一定的时间间隔，例如每隔10秒，上传多个坐标。每个坐标指示乘客/司机在上传时刻所处的位置。
在步骤1420，POI引擎110将多个地理坐标分为多个分组。该步骤可以由POI引擎110中的处理模块210中的分组单元340完成。根据本申请的一些实施例，利用至少一种聚类算法将所述多个地理坐标划分为多个分组，其中所述聚类算法包括但不限于K-MEANS算法；K-MEDOIDS算法；以及CLARANS算法等中的一种或几种的组合。给定一个有N个分组或者记录的数据集，使用聚类算法将其构造为K个分组，每一个分组就代表一个聚类，K<N。而且这K个分组满足下列条件：
(1)每一个分组至少包含一个数据记录；
(2)每一个数据记录属于且仅属于一个分组(注意：这个要求在某些模糊聚类算法中可以不做严格限定)。
对于给定的分组数K，算法首先给出一个初始的分组方法，以后通过反复迭代的方法改变分组，使得改进之后的分组方案都较前一次有所改善。在这里，有所改善的标准可以是：同一分组中的记录尽可能相互接近或相关，而不同的分组中的记录尽可能远离或不同。根据本申请的一些实施例， 基于位置坐标之间的距离来对位置坐标进行分组，完成分组后，同一分组中的位置坐标尽可能相互接近(即坐标之间的距离尽可能小)，而不同的分组中的位置坐标尽可能远离(即坐标之间的距离尽可能大)。根据本申请的一些实施例，可以利用聚类算法将获得的多个定位信息(例如，N个坐标)分为多个分组(即多个类)，分组的数量(即类的数量)可以是根据历史经验或者试验数据确定的数值，例如K个(N≥K>0)。
在步骤1430，POI引擎110分别获取每个分组中的中心点的位置信息，以及每个位置与所属分组中的中心点的位置之间的距离。该步骤可以由POI引擎110中的处理模块210中的地址解析单元310和计算单元350完成。根据本申请的一些实施例，分别获取每个分组中的中心点的位置信息包括：计算每个分组中的所有位置信息的平均值；以及将所述平均值作为每个分组中的所述中心点的位置信息。例如，分组单元340将N个坐标，分为了K个分组，计算单元350对每个分组中的所有坐标计算平均值，从而可以得到K个平均坐标值，该K个平均坐标值将分别作为K个分组的中心点坐标。根据本申请的一些实施例，基于分别计算的每个分组中的中心点的位置信息，计算获得的每个位置与该位置所属的分组中的中心点的位置之间的距离。例如，针对通过定位技术获得的N个坐标，分别计算每个坐标与该坐标所在的分组的中心点坐标之间的距离，因此一共可以得到N个距离的值。
在步骤1440，POI引擎110获取每一分组中所有地理坐标与该组中心点的距离值中的最大值。该步骤可以由POI引擎110中的处理模块210中的判定单元380及其计算子单元385完成。例如，根据上述获得的一共N个距离值，则计算并判定所有N个距离值中的最大值，可设定为Rmax。
在步骤1450，POI引擎110基于距离的最大值，确定乘客/司机的定位信息是否异常。该步骤可以由由POI引擎110中的处理模块210中的判定单元380完成。根据本申请的一些实施例，确定乘客/司机的定位信息是否异常具体包括：将距离的最大值与预定的阈值进行比较；以及基于所述比较的结果，确定所述乘客/司机的定位信息是否异常。在此所述的预定的阈值是根据历史经验或者试验数据确定的距离的阈值。例如，在一种场景 中，乘客/司机处于运动状态，例如，驾驶中的司机、运动中的乘客。在此场景下，例如阈值设为50米。那么，在一段时间(例如，30分钟)内，司机/乘客的位置应当是变化的。如果在这段时间中，司机/乘客上传的定位信息过于集中(例如，Rmax<50米)，则说明在这段时间期间，司机/乘客的定位信息异常。这时，可以向司机/乘客提示以查明定位异常的原因，例如，是否是定位设备的定位功能关闭等等。又例如，在另一种场景中，司机/乘客处于非运动状态或者缓慢运动状态，例如，静止或者缓慢行走的行人，或者遭遇严重堵车的司机。在此场景下，例如阈值设为1000米。那么，在一段时间(例如，5分钟)内，司机/乘客的位置应当是基本不变或者缓慢变化的。那么，如果这段时间中，司机/乘客上传的定位信息过于分散(例如，Rmax>1000米)，则说明在这段时间期间，司机/乘客的定位信息异常。阈值的选择以及根据最大值和阈值之间的何种关系(例如，大于、小于、等于、不小于、不大于等)来确定司机/乘客的定位信息异常，将取决于具体的场景以及具体实施方式中司机/乘客的设置。在此详细描述的示例只用于说明的目的，而不对本步骤的具体实施方式作精确的限定。应当认为，任何基于最大值和阈值的比较来判断用户的定位信息异常的方法都落入本申请的保护范围中。在一些实施例中，计算单元350可以根据定位信息和/或多个地理坐标计算服务费用。在一些实施例中，判定单元380及其计算子单元385可以基于判定的定位信息无异常从而进一步计算服务费用。
定位信息异常的判断可以用在不同场景。例如，定位信息异常的判断可以用在决定是否给一位司机推送订单。举例说明，一位司机通过司机端设备140给出自己的方位并向POI引擎110请求为一位乘客提供服务；如果POI引擎110判断司机定位信息异常，则可以拒绝把乘客订单分配给该司机。又例如，定位信息异常的判断可以用于计价。如果发现司机的定位信息异常，该服务的计价可以做相应调整，或者POI引擎110可以给乘客或司机发出相关提醒。
应当指出，可以将示例行流程图描述为流程图、流程图表、数据流程图、结构图或者框图的过程。尽管流程图可以将步骤描述为顺序的过程， 所述过程也可以并行地、并发地或者同时地执行许多操作。此外，步骤的顺序可以被重排。当过程的步骤完成时，过程可以被终止，但是也可以具有不包括在图中的额外的步骤。过程可以对应于方法、功能、程序、子例程、子程序等。当过程对应于功能时，过程的终止可以对应于功能对调用函数或者主函数的返回。此外，本领域的技术人员应该理解，上述的本申请的各装置、各单元或各步骤可以用通用的计算装置来实现，它们可以集中在单个的计算装置上，或者分布在多个计算装置所组成的网络上，可选地，它们可以用计算装置可执行的程序代码来实现，从而可以将它们存储在存储装置中由计算装置来执行，或者将它们分别制作成各个集成电路模块，或者将它们中的多个模块或步骤制作成单个集成电路模块来实现。这样，本申请不限制于任何特定的硬件和软件结合。
以上所述仅为本申请可选实施例，并不用于限制本申请，对于本领域的技术人员来说，本申请可以有各种更改和变化。凡在本申请的精神和原则之内，所作的任何修改、等效替换、改进等，均应包含在本申请的保护范围之内。
根据本申请的一些实施例，图15-A是POI引擎110确定用户的定位信息异常的一种示例性流程图。其中，所述用户可以是消费方、服务方等，可以是乘客或司机。如图15-A所示，在步骤1510，POI引擎110可以获取用户在预设时间段内的第一定位信息。该步骤可以由乘客接口230和/或司机接口240完成。根据本申请的一些实施例，利用定位技术，来获取用户在预设时间段内的多个地理坐标信息。所述定位技术的种类和细节参见前文的描述，在此不再赘述。根据本申请的一些实施例，由所述GPS定位技术获得的GPS坐标信息包括但不限于经度、纬度及时间戳信息。在一些实施例中，乘客接口230和/或司机接口240用于获取乘客端设备120和/或司机端设备140在预设时间段内的第一定位信息，其中第一定位信息可以是通过GPS定位技术获得的GPS坐标信息。
在步骤1520，POI引擎110获取乘客/司机在预设时间段内的第二定位信息。该步骤可以由乘客接口230和/或司机接口240完成。根据本申请的一些实施例，利用定位技术，来获取乘客/司机在预设时间段内的多个地 理坐标信息。根据本申请的一些实施例，所述第二定位信息包括但不限于经度、纬度及时间戳信息。需要说明的是，步骤1510中和步骤1520中的预设时间段为相同的时间段，而第一定位信息和第二定位信息是通过不同的定位技术所获取的。在一些实施例中，根据基站定位技术或WiFi定位技术，通过乘客接口230和/或司机接口240均可获得乘客/司机的第二定位信息。
在步骤1530，POI引擎110比较第一定位信息和第二定位信息。该步骤可以由POI引擎110中的处理模块210中的判定单元380完成。根据本申请的一些实施例，判定单元380中的计算子单元385计算所述第一定位信息和第二定位信息的偏差，并由判定单元380对所述偏差与第一预设阈值进行比较。具体来说，所述第一定位信息与所述第二定位信息的偏差为第一定位坐标与第二定位坐标之间的距离。则将两者之间的距离与第一预设阈值进行比较。在一些实施例中，第一定位信息可以是通过GPS定位技术获得的GPS坐标信息，第二定位信息可以是通过基站定位技术和/或WiFi定位技术获得的第二坐标信息。在一些实施例中，第一预设阈值根据基站定位或WiFi定位的误差进行设置，一般来说，基站定位或WiFi定位的误差在百米级别，则第一预设阈值可设置在百米级别。在一些实施例中，根据第一定位信息和第二定位信息的比较结果可以直接跳到步骤1550，确定定位信息是否异常，而不需要执行步骤1540。
在步骤1550，POI引擎110确定定位信息是否异常。该步骤可以由POI引擎110中的处理模块210中的判定单元380完成。若判定单元380确定所述偏差大于等于第一预设阈值，则判定所述第一定位信息异常。在一些实施例中，第一定位信息可以是GPS坐标信息，当判定第一定位信息异常时，即判定GPS坐标信息为伪造坐标信息。若判定单元380确定所述偏差小于第一预设阈值，该方法还可以进一步包括：
在一些实施例中，根据步骤1530的结果还不能确定定位信息是否异常，这样就需要执行步骤1540。在步骤1540中，POI引擎可以获取与所述乘客/司机当前地址的距离小于预设距离的范围内的基站编号及预设时间段内所述基站的信号强度；根据所述GPS坐标信息、所述基站编号及所 述基站的信号强度，判定所述GPS坐标信息是否为伪造坐标信息。该步骤可以由POI引擎110中的乘客接口230和/或司机接口240完成。在一些实施例中，POI引擎在步骤1540之前通过乘客接口230和/或司机接口240获取所述乘客/司机的当前地址信息；根据获取的所述乘客/司机当前地址通过处理模块210中的地址解析单元310确定与所述乘客/司机当前地址的距离小于预设距离的基站。其中，所述乘客/司机的当前地址可以是通过基站定位技术或WiFi定位技术获取的坐标信息。具体来说，步骤1540包括步骤1551-1553。
图15-B是对POI引擎110判断定位信息异常的示例性实施例。在步骤1551，POI引擎110可以获取与所述乘客/司机当前地址的距离小于预设距离的范围内的基站编号及预设时间段内所述基站的信号强度。其中，基站编号是用于唯一标识基站的序列号。一个基站对应一个基站编号。该步骤可以由POI引擎110中的乘客接口230和/或司机接口240完成。
在步骤1552，POI引擎110可以将预设时间段内的GPS坐标的变化值与第二预设阈值进行比较，并将预设时间段内的基站的信号强度的变化值与第三预设阈值进行比较。该步骤可以由POI引擎110中的处理模块210中的判定单元380及其计算子单元385完成。具体来说，预设时间段内GPS坐标的变化值是指预设时间段的开始时间点的GPS坐标与预设时间段的结束时间点的GPS坐标的差值。则预设时间段内的基站的信号强度的变化值是指预设时间段的开始时间点的基站的信号强度与预设时间段的结束时间点的同一基站的信号强度的差值。举例来说，预设时间段是1点10分至1点30分，预设时间段内的GPS坐标的变化值即1点10分时终端的GPS坐标与1点30分时终端的GPS坐标的差值。预设时间段内的基站的信号强度的变化值即1点10分时基站的信号强度与1点30分时同一基站的信号强度的差值。需要注意的是，预设时间段可以根据实际情况和/或实际需求调整，可以是5分钟，20分钟，30分钟，1小时等。
在步骤1553，POI引擎确定第一定位信息是否异常。该步骤可以由POI引擎110中的处理模块210中的判定单元380完成。若判定单元380确定所述GPS坐标的变化值大于第二预设阈值，并且所述基站编号没有变 化且所述基站的信号强度的变化值小于第三预设阈值，则判定第一定位信息异常，即所述预定时间段内的GPS坐标信息为伪造的坐标信息。具体来说，当预设时间段内乘客/司机的GPS坐标发生明显变化，但是乘客/司机附近基站编号不变且基站信号强度没有明显变化，则表明预设时间段内GPS坐标为伪造的坐标信息。若判定单元380确定所述GPS坐标的变化值小于等于第二预设阈值，并且所述基站编号发生变化或所述基站的信号强度的变化值大于等于第三预设阈值，则判定第一定位信息异常，即判定所述预定时间段内的GPS坐标信息为伪造的坐标信息。具体来说，当预设时间段内乘客/司机的GPS坐标没有明显变化，但是乘客/司机附近基站编号变化或基站信号强度发生明显变化，则表明预设时间段内GPS坐标为伪造的坐标信息。在一些实施例中，计算单元350可以根据定位信息和/或多个地理坐标计算服务费用。在一些实施例中，判定单元380及其计算子单元385可以基于判定的定位信息无异常从而进一步计算服务费用。
需要注意的是，定位异常的判断有很多方法，并不限于上文的描述。在一些实施例中，定位信息异常的判断还可以专用于对乘客定位信息的处理。例如，定位信息异常的判断可以应用于POI引擎110是否响应乘客订单请求的判断。举例说明，一位乘客通过乘客端设备120提供自己的位置信息并向POI引擎110请求一位司机提供服务；如果POI引擎110判断乘客定位信息异常，则POI引擎110可以进一步向乘客请求更多信息，或者提示乘客定位信息异常，或者发送重新定位请求，或者拒绝该乘客的订单请求。在一些实施例中，乘客在短时间内在不同地点请求按需服务(例如，在相对于时间间隔而言，不同地点间间隔较远)。POI引擎110可以进一步向乘客询问不同服务请求的更多信息，例如，不同服务请求是否是为同一乘客，如果是为不同乘客，另一位乘客的联系方式，确认订单方式等。如果乘客在乘客端设备120上所输入的出发地点与乘客端设备120当前的位置距离较远，例如，10公里，同时所指定的出发时间据乘客端设备120的当前系统时间较接近，例如10分钟或20分钟，则POI引擎110可以进一步向乘客端设备120发送一个确认信息，要求乘客确认所输入的出发地点和/或出发时间。POI引擎110还可以向乘客要求其他信息，例如周边的 公共或商业设施、重要地标建筑、街道名称等，以确定乘客端设备120是否存在定位异常。
应当注意的是，在本申请的系统的各个部件中，根据其要实现的功能而对其中的部件进行了逻辑划分，但是，本申请不受限于此，可以根据需要对各个部件进行重新划分或者组合，例如，可以将一些部件组合为单个部件，或者可以将一些部件进一步分解为更多的子部件。
本申请的各个部件实施例可以以硬件实现，或者以在一个或者多个处理器上运行的软件模块实现，或者以它们的组合实现。本领域的技术人员应当理解，可以在实践中使用微处理器或者数字信号处理器(DSP)来实现根据本申请实施例的系统中的一些或者全部部件的一些或者全部功能。本申请还可以实现为用于执行这里所描述的方法的一部分或者全部的设备或者装置程序(例如，计算机程序和计算机程序产品)。这样的实现本申请的程序可以存储在计算机可读介质上，或者可以具有一个或者多个信号的形式。这样的信号可以从因特网网站上下载得到，或者在载体信号上提供，或者以任何其他形式提供。
以上实施方式仅适于说明本申请，而并非对本申请的限制，有关技术领域的普通技术人员，在不脱离本申请的精神和范围的情况下，还可以做出各种变化和变型，因此所有等同的技术方案也属于本申请的范畴，本申请的专利保护范围应由权利要求限定。
图16描述了一种移动设备的结构，该移动设备能够用于实现实施本申请中披露的特定系统。在本例中，用于显示和交互位置相关信息的用户设备是一个移动设备1600，包括但不限于，智能手机、平板电脑、音乐播放器、便携游戏机、全球定位系统(GPS)接收器、可穿戴计算设备(如眼镜、手表等)，或者其他形式。本例中的移动设备1600包括一个或多个中央处理器(CPUs)1640，一个或多个图形处理器(graphical processing units(GPUs))1630，一个显示1620，一个内存1660，一个天线1610，例如一个无线通信单元，存储单元1690，以及一个或多个输入/输出(input output(I/O))设备1650。任何其他合适的组件，包括但不限于系统总线或控制器(图上未显示)，也可能被包括在移动设备1600中。如图16所 示，一个移动操作系统1670，如iOS、Android、Windows Phone等，以及一个或多个应用1680可以从存储单元1690加载进内存1660中，并被中央处理器1640所执行。应用1680可能包括一个浏览器或其他适合在移动设备1600上接收并处理位置相关信息的移动应用。乘客/司机关于位置相关信息的交互可以通过输入/输出系统设备1650获得并提供给POI引擎110，以及/或系统100的其他组件，例如：通过网络150。
为了实现不同的模块、单元以及在之前的披露中所描述的他们的功能，计算机硬件平台可以被用作以上描述的一个或多个元素的硬件平台(例如：POI引擎110，和/或图1-15中描述的系统100的其他组件)。这类计算机的硬件元素、操作系统和程序语言在自然界中是常见的，可以假定本领域技术人员对这些技术都足够熟悉，能够利用这里描述的技术提供按需服务所需要的信息。一台包含用户界面元素的计算机能够被用作个人计算机(personal computer(PC))或其他类型的工作站或终端设备，被适当程序化后也可以作为服务器使用。可以认为本领域技术人员对这样的结构、程序以及这类计算机设备的一般操作都是熟悉的，因此所有附图也都不需要额外的解释。
图17描述了一种计算机设备的架构，这种计算机设备能够被用于实现实施本申请中披露的特定系统。本实施例中的特定系统利用功能框图描述了一个包含用户界面的硬件平台。这种计算机可以是一个通用目的的计算机，也可以是一个有特定目的的计算机。两种计算机都可以被用于实现本实施例中的特定系统。计算机1700可以用于实施当前描述地提供按需服务所需要的信息的任何组件。例如：POI引擎110能够被如计算机1700的计算机通过其硬件设备、软件程序、固件以及他们的组合所实现。为了方便起见，图17中只绘制了一台计算机，但是本实施例所描述的提供按需服务所需要的信息的相关计算机功能是可以以分布的方式、由一组相似的平台所实施的，分散系统的处理负荷。
计算机1700包括通信端口1750，与之相连的是实现数据通信的网络。计算机1700还包括一个中央处理系统(CPU)单元用于执行程序指令，由一个或多个处理器组成。示例的计算机平台包括一个内部通信总线1710， 不同形式的程序储存单元以及数据储存单元，例如硬盘1770，只读存储器(ROM)1730，随机存取存储器(RAM)1740，能够用于计算机处理和/或通信使用的各种数据文件，以及CPU所执行的可能的程序指令。计算机1700还包括一个输入/输出组件1760，支持计算机与其他组件(如用户界面1780)之间的输入/输出数据流。计算机1700也可以通过通信网络接受程序及数据。
以上概述了提供按需服务所需要的信息的方法的不同方面和/或通过程序实现其他步骤的方法。技术中的程序部分可以被认为是以可执行的代码和/或相关数据的形式而存在的“产品”或“制品”，是通过计算机可读的介质所参与或实现的。有形的、永久的储存介质包括任何计算机、处理器、或类似设备或相关的模块所用到的内存或存储器。例如各种半导体存储器、磁带驱动器、磁盘驱动器或者类似任何时间能够为软件提供存储功能的设备。
所有软件或其中的一部分有时可能会通过网络进行通信，如互联网或其他通信网络。此类通信能够将软件从一个计算机设备或处理器加载到另一个。例如：从按需服务系统的一个管理服务器或主机计算机加载至一个计算机环境的硬件平台，或其他实现系统的计算机环境，或与提供按需服务所需要的信息相关的类似功能的系统。因此，另一种能够传递软件元素的介质也可以被用作局部设备之间的物理连接，例如光波、电波、电磁波等，通过电缆、光缆或者空气实现传播。用来载波的物理介质如电缆、无线连接或光缆等类似设备，也可以被认为是承载软件的介质。在这里的用法除非限制了有形的“储存”介质，其他表示计算机或机器“可读介质”的术语都表示在处理器执行任何指令的过程中参与的介质。
因此，一个计算机可读的介质可能有多种形式，包括但不限于，有形的存储介质，载波介质或物理传输介质。稳定的储存介质包括：光盘或磁盘，以及其他计算机或类似设备中使用的，能够实现图中所描述的系统组件的存储系统。不稳定的存储介质包括动态内存，例如计算机平台的主内存。有形的传输介质包括同轴电缆、铜电缆以及光纤，包括计算机系统内部形成总线的线路。载波传输介质可以传递电信号、电磁信号，声波信号 或光波信号，这些信号可以由无线电频率或红外数据通信的方法所产生的。通常的计算机可读介质包括硬盘、软盘、磁带、任何其他磁性介质；CD-ROM、DVD、DVD-ROM、任何其他光学介质；穿孔卡、任何其他包含小孔模式的物理存储介质；RAM、PROM、EPROM、FLASH-EPROM，任何其他存储器片或磁带；传输数据或指令的载波、电缆或传输载波的连接装置、任何其他可以利用计算机读取的程序代码和/或数据。这些计算机可读介质的形式中，会有很多种出现在处理器在执行指令、传递一个或更多结果的过程之中。
本领域技术人员能够理解，本申请所披露的内容可以出现多种变型和改进。例如，以上所描述的不同系统组件都是通过硬件设备所实现的，但是也可能只通过软件的解决方案得以实现。例如：在现有的服务器上安装系统。此外，这里所披露的位置信息的提供可能是通过一个固件、固件/软件的组合、固件/硬件的组合或硬件/固件/软件的组合得以实现。
以上内容描述了本申请和/或一些其他的示例。根据上述内容，本申请还可以作出不同的变形。本申请披露的主题能够以不同的形式和例子所实现，并且本申请可以被应用于大量的应用程序中。后文权利要求中所要求保护的所有应用、修饰以及改变都属于本申请的范围。

Claims (20)

  1. 一种为按需服务提供信息的方法，包括以下步骤：
    接收来自一个乘客端设备的一个乘客的服务请求信息，所述服务请求信息包括所述乘客的始发地位置；
    获取与所述乘客相关的历史服务请求信息；
    至少部分基于所述乘客的始发地位置与所述历史服务请求信息，确定出行路径相关信息。
  2. 根据权利要求1所述的方法，所述服务请求信息包括一个时间信息。
  3. 根据权利要求1所述的方法，所述出行路径相关信息包括至少一种下列信息：
    一个目的地；一个由所述乘客的当前位置到达所述目的地的路径；上述路径的距离。
  4. 根据权利要求3所述的方法，所述目的地是基于一种分类模型所确定的。
  5. 根据权利要求4所述的方法，所述分类模型是基于至少一个地点类型的。
  6. 根据权利要求1所述的方法，进一步包括：
    将所述出行路径相关信息发送给所述乘客端设备。
  7. 根据权利要求6所述的方法，进一步包括：
    接收来自所述乘客端设备的乘客对所述出行路径相关信息的处理。
  8. 根据权利要求1所述的方法，所述历史服务请求信息包括至少一种下列信息：
    一个历史始发地；一个历史目的地；一个由所述乘客的历史始发地到达所述历史目的地的历史路径；上述历史路径的距离。
  9. 根据权利要求1所述的方法，进一步包括确定一个服务费用。
  10. 根据权利要求9所述的方法，其中确定所述服务费用包括：
    获取来自一个司机在多个时间点的多个位置信息；
    至少部分基于所述多个位置信息，计算所述服务费用。
  11. 一种为按需服务提供信息的系统，包括：
    一种计算机可读的存储媒介，被配置为存储可执行模块，包括：
    一个服务请求方接口模块，被配置为接收来自一个乘客端设备的一个乘客的服务请求信息，所述服务请求信息包括所述乘客的始发地位置；
    一个处理模块，被配置为：1)获取与所述乘客相关的历史服务请求信息；2)至少部分基于所述乘客的始发地位置与所述历史服务请求信息，确定出行路径相关信息；
    一个处理器，所述处理器能够执行所述计算机可读的存储媒介存储的可执行模块。
  12. 根据权利要求11所述的系统，所述服务请求信息包括一个时间信息。
  13. 根据权利要求11所述的系统，所述出行路径相关信息包括至少一种下列信息：
    一个目的地；一个由所述乘客的当前位置到达所述目的地的路径；上述路径的距离。
  14. 根据权利要求13所述的系统，所述目的地是基于一种分类模型所确定的。
  15. 根据权利要求14所述的系统，所述分类模型是基于至少一个地点类型的。
  16. 根据权利要求11所述的系统，服务请求方接口模块进一步被配置为：
    将所述出行路径相关信息发送给所述乘客端设备。
  17. 根据权利要求16所述的系统，服务请求方接口模块进一步被配置为：
    接收来自所述乘客端设备的乘客对所述出行路径相关信息的处理。
  18. 根据权利要求11所述的系统，所述历史服务请求信息包括至少一种下列信息：
    一个历史始发地；一个历史目的地；一个由所述乘客的历史始发 地到达所述历史目的地的历史路径；上述历史路径的距离。
  19. 根据权利要求11所述的系统，处理模块进一步被配置为确定一个服务费用。
  20. 根据权利要求19所述的系统，其中确定所述服务费用包括：
    由一个服务提供方接口模块获取来自一个司机在多个时间点的多个位置信息；
    至少部分基于所述多个位置信息，计算所述服务费用。
PCT/CN2016/072357 2015-01-27 2016-01-27 一种为按需服务提供信息的方法及系统 WO2016119704A1 (zh)

Priority Applications (16)

Application Number Priority Date Filing Date Title
AU2016212530A AU2016212530A1 (en) 2015-01-27 2016-01-27 Methods and systems for providing information for an on-demand service
EP16742766.5A EP3252704B1 (en) 2015-01-27 2016-01-27 Information providing method and system for on-demand service
CA2975002A CA2975002C (en) 2015-01-27 2016-01-27 Methods and systems for providing information for an on-demand service
BR112017016064-1A BR112017016064B1 (pt) 2015-02-10 2016-01-27 Métodos e sistemas para fornecer informação para um serviço por demanda
MYPI2017001096A MY193639A (en) 2015-01-27 2016-01-27 Methods and systems for providing information for an on-demand service
KR1020177023933A KR20180006875A (ko) 2015-01-27 2016-01-27 주문형 서비스를 위한 정보를 제공하는 방법들 및 시스템들
JP2017539550A JP6637054B2 (ja) 2015-01-27 2016-01-27 オン・デマンドサービスの情報を提供する方法及びシステム
SG11201706149XA SG11201706149XA (en) 2015-01-27 2016-01-27 Methods And Systems For Providing Information For An On-Demand Service
GB1712010.6A GB2550309A (en) 2015-01-27 2016-01-27 Information providing method and system for on-demand service
US15/546,657 US10458806B2 (en) 2015-01-27 2016-01-27 Methods and systems for providing information for an on-demand service
PH12017501345A PH12017501345A1 (en) 2015-01-27 2017-07-27 Methods and systems for providing information for an on-demand service
HK18104998.4A HK1245955A1 (zh) 2015-01-27 2018-04-18 按需服務信息提供方法和系統
US16/569,632 US11156470B2 (en) 2015-01-27 2019-09-12 Methods and systems for providing information for an on-demand service
AU2019236639A AU2019236639A1 (en) 2015-01-27 2019-09-24 Methods and systems for providing information for an on-demand service
AU2019101806A AU2019101806A4 (en) 2015-01-27 2019-09-24 Methods and systems for providing information for an on-demand service
US17/448,717 US11892312B2 (en) 2015-01-27 2021-09-24 Methods and systems for providing information for an on-demand service

Applications Claiming Priority (22)

Application Number Priority Date Filing Date Title
CN201510039939.3A CN104599217B (zh) 2015-01-27 2015-01-27 用于确定乘客的当前目的地的方法及设备
CN201510039939.3 2015-01-27
CN201510048217.4 2015-01-29
CN201510048217.4A CN104574255A (zh) 2015-01-29 2015-01-29 向用户提供出行路径的方法及设备
CN201510070073.2A CN104599161A (zh) 2015-02-10 2015-02-10 基于客户端的gps坐标点对订单进行计价的方法和设备
CN201510070073.2 2015-02-10
CN201510105381.4A CN104658255B (zh) 2015-03-10 2015-03-10 基于gps数据来检测车辆静止状态的方法及装置
CN201510105381.4 2015-03-10
CN201510151590.2 2015-04-01
CN201510151590.2A CN104837114B (zh) 2015-04-01 2015-04-01 用于确定用户的定位信息异常的方法和设备
CN201510239402.1 2015-05-12
CN201510239402.1A CN104899252B (zh) 2015-05-12 2015-05-12 一种信息推送的方法及装置
CN201510284601.4 2015-05-28
CN201510284601.4A CN104869638B (zh) 2015-05-28 2015-05-28 Gps坐标作弊的检测方法及装置
CN201510464596.5A CN105138590A (zh) 2015-07-31 2015-07-31 轨迹预测方法和装置
CN201510464596.5 2015-07-31
CN201510591079.4A CN105303817B (zh) 2015-09-16 2015-09-16 一种出行方式的规划方法及装置
CN201510591079.4 2015-09-16
CN201510991394.6A CN106919993A (zh) 2015-12-25 2015-12-25 一种基于历史数据的高准确性默认目的地预测方法及装置
CN201511000093.9 2015-12-25
CN201510991394.6 2015-12-25
CN201511000093.9A CN106919996A (zh) 2015-12-25 2015-12-25 一种目的地预测方法及装置

Related Child Applications (2)

Application Number Title Priority Date Filing Date
US15/546,657 A-371-Of-International US10458806B2 (en) 2015-01-27 2016-01-27 Methods and systems for providing information for an on-demand service
US16/569,632 Continuation US11156470B2 (en) 2015-01-27 2019-09-12 Methods and systems for providing information for an on-demand service

Publications (1)

Publication Number Publication Date
WO2016119704A1 true WO2016119704A1 (zh) 2016-08-04

Family

ID=56542436

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/072357 WO2016119704A1 (zh) 2015-01-27 2016-01-27 一种为按需服务提供信息的方法及系统

Country Status (12)

Country Link
US (3) US10458806B2 (zh)
EP (1) EP3252704B1 (zh)
JP (2) JP6637054B2 (zh)
KR (1) KR20180006875A (zh)
AU (3) AU2016212530A1 (zh)
CA (1) CA2975002C (zh)
GB (1) GB2550309A (zh)
HK (1) HK1245955A1 (zh)
MY (1) MY193639A (zh)
PH (1) PH12017501345A1 (zh)
SG (1) SG11201706149XA (zh)
WO (1) WO2016119704A1 (zh)

Cited By (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106897919A (zh) * 2017-02-28 2017-06-27 百度在线网络技术（北京）有限公司 用车类型预测模型建立、信息提供方法及装置
CN107332770A (zh) * 2017-08-18 2017-11-07 郑州云海信息技术有限公司 一种必经点路由路径选择方法
CN107528790A (zh) * 2017-07-28 2017-12-29 东北大学 一种改变节点处理顺序缓解公交网络拥塞的方法
US20180012153A1 (en) * 2015-01-29 2018-01-11 Beijing Didi Infinity Technology And Development C O., Ltd. Order allocation system and method
CN108289122A (zh) * 2017-01-09 2018-07-17 福特全球技术公司 用于分析运动配置文件的方法
WO2019015600A1 (en) * 2017-07-20 2019-01-24 Beijing Didi Infinity Technology And Development Co., Ltd. SYSTEMS AND METHODS FOR RECOMMENDING A DESTINATION
EP3455840A4 (en) * 2017-06-13 2019-07-31 Beijing Didi Infinity Technology And Development Co., Ltd. SYSTEMS AND METHODS FOR ESTIMATED ARRIVAL TIME DETERMINATION
KR20190094230A (ko) * 2016-12-14 2019-08-12 알리바바 그룹 홀딩 리미티드 잘못된 주소 정보를 식별하기 위한 방법 및 장치
CN110119955A (zh) * 2018-02-06 2019-08-13 北京嘀嘀无限科技发展有限公司 订单成交率预估方法及装置
US10458806B2 (en) 2015-01-27 2019-10-29 Beijing Didi Infinity Technology And Development Co., Ltd. Methods and systems for providing information for an on-demand service
JP2020504344A (ja) * 2017-04-27 2020-02-06 ベイジン ディディ インフィニティ テクノロジー アンド ディベロップメント カンパニー リミティッド 推定された到着時間を決定するためのシステムおよび方法
EP3642821A4 (en) * 2017-07-21 2020-04-29 Beijing Didi Infinity Technology and Development Co., Ltd. SYSTEMS AND METHODS FOR DETERMINING A NEW ROUTE ON A MAP
CN111125272A (zh) * 2018-10-31 2020-05-08 百度在线网络技术（北京）有限公司 一种区域特征获取方法、装置、计算机设备及介质
CN111831897A (zh) * 2019-09-09 2020-10-27 北京嘀嘀无限科技发展有限公司 一种出行目的地推荐方法、装置、电子设备及存储介质
US11120091B2 (en) * 2018-06-14 2021-09-14 Beijing Didi Infinity Technology And Development Co., Ltd. Systems and methods for on-demand services
CN113938521A (zh) * 2021-06-30 2022-01-14 深圳市巴滴科技有限公司 基于乘客需求信息的出行方案推荐方法及装置
TWI763863B (zh) * 2017-06-06 2022-05-11 大陸商北京嘀嘀無限科技發展有限公司 區域劃分系統和方法
CN114754783A (zh) * 2021-11-10 2022-07-15 广州汽车集团股份有限公司 一种用户出行信息的推荐方法、系统及汽车

Families Citing this family (52)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10120381B2 (en) * 2015-03-13 2018-11-06 Nissan North America, Inc. Identifying significant locations based on vehicle probe data
US20170153636A1 (en) * 2015-11-27 2017-06-01 Bragi GmbH Vehicle with wearable integration or communication
US10099636B2 (en) 2015-11-27 2018-10-16 Bragi GmbH System and method for determining a user role and user settings associated with a vehicle
US9944295B2 (en) 2015-11-27 2018-04-17 Bragi GmbH Vehicle with wearable for identifying role of one or more users and adjustment of user settings
US10104460B2 (en) 2015-11-27 2018-10-16 Bragi GmbH Vehicle with interaction between entertainment systems and wearable devices
US10635994B2 (en) 2015-12-11 2020-04-28 Lyft, Inc. System for navigating driver to passenger for ride authorized by another user of transportation service
US10242574B2 (en) 2016-03-21 2019-03-26 Uber Technologies, Inc. Network computer system to address service providers to contacts
US20180017400A1 (en) * 2016-07-15 2018-01-18 Microsoft Technology Licensing, Llc Point of interest identification based on polyline route and progress along route
US20180032874A1 (en) * 2016-07-29 2018-02-01 Ca, Inc. Document analysis system that uses process mining techniques to classify conversations
US10991063B2 (en) * 2016-08-29 2021-04-27 Conduent Business Services, Llc System and method for optimization of on-demand microtransit
US10417727B2 (en) 2016-09-26 2019-09-17 Uber Technologies, Inc. Network system to determine accelerators for selection of a service
US10477504B2 (en) 2016-09-26 2019-11-12 Uber Technologies, Inc. Network service over limited network connectivity
US10425490B2 (en) 2016-09-26 2019-09-24 Uber Technologies, Inc. Service information and configuration user interface
CN108022140A (zh) * 2016-11-02 2018-05-11 北京嘀嘀无限科技发展有限公司 一种用车订单推荐方法、装置及服务器
US11087287B2 (en) 2017-04-28 2021-08-10 Uber Technologies, Inc. System and method for generating event invitations to specified recipients
US10700864B2 (en) * 2017-07-12 2020-06-30 International Business Machines Corporation Anonymous encrypted data
JP2020529649A (ja) * 2017-08-04 2020-10-08 ベイジン ディディ インフィニティ テクノロジー アンド ディベロップメント カンパニー リミティッド ピックアップロケーションをネーミングするための方法およびシステム
US10721327B2 (en) 2017-08-11 2020-07-21 Uber Technologies, Inc. Dynamic scheduling system for planned service requests
CN110741401B (zh) * 2017-11-07 2024-02-13 北京嘀嘀无限科技发展有限公司 用于预约拼车服务的系统和方法
US10760914B2 (en) 2017-12-21 2020-09-01 Verizon Patent And Licensing, Inc. Comparative metrics for route planning scenarios
US11348061B2 (en) * 2017-12-21 2022-05-31 Verizon Connect Development Limited Logistics management platform for modifying schedules in real-time
WO2019154398A1 (en) * 2018-02-06 2019-08-15 Beijing Didi Infinity Technology And Development Co., Ltd. Systems and methods for recommending transportation services
WO2019171132A1 (en) * 2018-03-06 2019-09-12 Pratik Sharma Geographic coordinates locator service
CN108647771A (zh) * 2018-05-07 2018-10-12 福建师范大学 一种混合云环境下科学工作流数据的布局方法
WO2020000277A1 (en) * 2018-06-28 2020-01-02 Beijing Didi Infinity Technology And Development Co., Ltd. Systems and methods for predicting destination in online to offline service
JP2020052926A (ja) * 2018-09-28 2020-04-02 マツダ株式会社 自動車運行管理システム
US10518750B1 (en) * 2018-10-11 2019-12-31 Denso International America, Inc. Anti-theft system by location prediction based on heuristics and learning
US11868929B2 (en) * 2018-10-18 2024-01-09 Lyft, Inc. Optimizing engagement of transportation providers
EP3644014A1 (en) * 2018-10-23 2020-04-29 Offshore Navigation Limited An apparatus for determining an optimal route of a maritime ship
EP3877235A4 (en) 2018-11-09 2023-07-19 Iocurrents, Inc. MACHINE LEARNING-BASED PREDICTION, PLANNING AND OPTIMIZATION OF TRAVEL TIME, TRAVEL COSTS AND/OR POLLUTANT EMISSION DURING NAVIGATION
CN111179000B (zh) * 2018-11-09 2023-08-11 北京嘀嘀无限科技发展有限公司 一种订单管理方法及装置、服务器及计算机可读存储介质
US10949483B2 (en) * 2018-11-12 2021-03-16 Ford Global Technologies, Llc Location tagging for ubiquitous access
CN109740939A (zh) * 2019-01-04 2019-05-10 杭州卓凯科技有限公司 网约货运汽车订单分配系统及方法
JP2020112917A (ja) * 2019-01-09 2020-07-27 日本電信電話株式会社 目的地予測装置、方法、及びプログラム
CN111442778A (zh) * 2019-01-16 2020-07-24 百度在线网络技术（北京）有限公司 出行方案推荐方法、装置、设备及计算机可读存储介质
US11012809B2 (en) * 2019-02-08 2021-05-18 Uber Technologies, Inc. Proximity alert system
CN113508606B (zh) 2019-02-13 2023-03-28 格步计程车控股私人有限公司 根据噪声多模态数据自动确定针对兴趣点的最优运输服务位置
US11085781B2 (en) * 2019-02-25 2021-08-10 Mitsubishi Electric Research Laboratories, Inc. System and method for scheduling multiple modes of transport with incomplete information
CN110033017A (zh) * 2019-02-27 2019-07-19 中国人民解放军空军工程大学 一种多雷达航迹分步关联模糊聚类算法
US11060879B2 (en) * 2019-03-01 2021-07-13 Here Global B.V. Method, system, and computer program product for generating synthetic demand data of vehicle rides
JP7291522B2 (ja) * 2019-04-10 2023-06-15 スズキ株式会社 乗車予約利用者支援装置及び乗車予約利用者支援方法
CN110119884B (zh) * 2019-04-17 2022-09-13 五邑大学 一种基于近邻传播聚类的高速铁路客流时段划分方法
US20220274617A1 (en) * 2019-07-10 2022-09-01 Lg Electronics Inc. Vehicle control method and intelligent computing device for controlling vehicle
US20210192402A1 (en) * 2019-12-20 2021-06-24 Beijing Didi Infinity Technology And Development Co., Ltd. Abnormal trip monitor
CN111984877B (zh) * 2020-07-09 2023-11-07 北京北大千方科技有限公司 机场陆侧旅客出行链构建方法、系统、存储介质及终端
DE102020120730A1 (de) 2020-08-06 2022-02-10 Valeo Schalter Und Sensoren Gmbh Fischschwarmfahrt
CN112287048A (zh) * 2020-09-28 2021-01-29 珠海大横琴科技发展有限公司 一种地图服务处理方法和装置
CN116806345A (zh) * 2021-03-02 2023-09-26 格步计程车控股私人有限公司 用于预测目的地位置的系统和方法
CN113225260B (zh) * 2021-04-25 2022-11-18 湖南大学 一种基于机器学习的混合聚类机会路由实现方法
US20230085699A1 (en) * 2021-09-21 2023-03-23 International Business Machines Corporation Order compliance tracking of electronic components
DE102022123212A1 (de) 2022-09-12 2024-03-14 Bayerische Motoren Werke Aktiengesellschaft Vorrichtung und Verfahren zur prädiktiven Ermittlung von Zwischenzielen einer Route
CN116523426B (zh) * 2023-07-05 2023-09-08 成都花娃网络科技有限公司 基于订单地址智能配送系统及方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2009125880A1 (en) * 2008-04-10 2009-10-15 Sk Marketing & Company Co., Ltd System and method for call service, call server, user terminal and storage medium
CN104442825A (zh) * 2014-11-28 2015-03-25 上海交通大学 一种电动汽车剩余行驶里程的预测方法和系统
CN104571036A (zh) * 2014-12-29 2015-04-29 小米科技有限责任公司 智能家居开启方法及装置
CN104599217A (zh) * 2015-01-27 2015-05-06 北京嘀嘀无限科技发展有限公司 用于确定乘客的当前目的地的方法及设备
CN105138590A (zh) * 2015-07-31 2015-12-09 北京嘀嘀无限科技发展有限公司 轨迹预测方法和装置

Family Cites Families (99)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5948040A (en) * 1994-06-24 1999-09-07 Delorme Publishing Co. Travel reservation information and planning system
JPH10283519A (ja) 1997-04-03 1998-10-23 Yazaki Corp Ｇｐｓ位置データ記録方法、ｇｐｓ位置データ記録装置及び運行管理装置
CN1101123C (zh) 1999-09-22 2003-02-05 刘仪 模拟蜂窝多基站定位方法和系统
US10684350B2 (en) * 2000-06-02 2020-06-16 Tracbeam Llc Services and applications for a communications network
JP3541802B2 (ja) 2000-11-22 2004-07-14 日本電気株式会社 携帯電話機および携帯電話機の動作制御システム
JP4433604B2 (ja) * 2000-12-19 2010-03-17 株式会社デンソー ナビゲーションシステム及びナビゲーション装置
JP3937916B2 (ja) * 2001-05-24 2007-06-27 二葉計器株式会社 タクシーの配車サービス方法及びそのシステム、並びに見積処理プログラムを記録した記録媒体
CN1330937C (zh) 2001-08-06 2007-08-08 松下电器产业株式会社 信息提供方法
JP3816068B2 (ja) 2001-08-06 2006-08-30 松下電器産業株式会社 情報提供方法および情報提供装置
JP3683198B2 (ja) * 2001-09-20 2005-08-17 Ｎｅｃソフト株式会社 営業車配車システムおよび営業車配車サーバー
AU2003275550A1 (en) 2002-10-10 2004-05-04 Matsushita Electric Industrial Co., Ltd. Information acquisition method, information providing method, and information acquisition device
CN100429953C (zh) 2002-10-10 2008-10-29 松下电器产业株式会社 信息取得方法、信息提供方法及信息取得装置
US20040117246A1 (en) 2002-11-07 2004-06-17 Applebaum Ted H. Navigation and promotion distribution system
JP4254375B2 (ja) * 2003-06-26 2009-04-15 カシオ計算機株式会社 目的地案内システムおよびプログラム
JP2005157724A (ja) * 2003-11-26 2005-06-16 Matsushita Electric Ind Co Ltd 車両管理システム
US8024112B2 (en) 2005-09-29 2011-09-20 Microsoft Corporation Methods for predicting destinations from partial trajectories employing open-and closed-world modeling methods
US7885443B2 (en) * 2005-11-14 2011-02-08 Hologic, Inc. Facilitating temporal comparison of medical images
US20070150174A1 (en) 2005-12-08 2007-06-28 Seymour Shafer B Predictive navigation
CN1808517A (zh) 2006-02-17 2006-07-26 周朝勇 实时监测主动式车辆报警装置和方法
JP4179339B2 (ja) 2006-05-29 2008-11-12 セイコーエプソン株式会社 測位装置、測位装置の制御方法及びプログラム
JP2008003906A (ja) * 2006-06-23 2008-01-10 Nec Corp 配車管理システム及び配車管理システムにおける配車管理方法
US8095279B2 (en) * 2007-08-31 2012-01-10 Caterpillar Inc. Systems and methods for improving haul route management
CN101382936A (zh) 2007-12-25 2009-03-11 苏州中茵泰格科技有限公司 一种主动式互动导航的方法和系统
CN101470012B (zh) 2007-12-29 2011-03-30 厦门雅迅网络股份有限公司 一种基于无线网络和gps位置信息实时统计汽车行驶里程的方法
CN101231718A (zh) 2008-02-15 2008-07-30 上海申通轨道交通研究咨询有限公司 轨道交通换乘的票务清分方法
CN101546314A (zh) 2008-03-24 2009-09-30 东森得易购股份有限公司 一种主动提供场所信息的方法与系统
US8706406B2 (en) * 2008-06-27 2014-04-22 Yahoo! Inc. System and method for determination and display of personalized distance
KR20100005922A (ko) 2008-07-08 2010-01-18 주식회사 로티스 콜택시 서비스 방법
JP5271637B2 (ja) * 2008-08-28 2013-08-21 アイシン・エィ・ダブリュ株式会社 走行経路評価システム及び走行経路評価プログラム
US8478642B2 (en) 2008-10-20 2013-07-02 Carnegie Mellon University System, method and device for predicting navigational decision-making behavior
JP5545076B2 (ja) 2009-07-22 2014-07-09 ソニー株式会社 画像表示装置及び光学装置
CN102080964A (zh) 2009-12-01 2011-06-01 汤贻芸 自动确定导航目标地址的智能导航方法和系统
US8805707B2 (en) * 2009-12-31 2014-08-12 Hartford Fire Insurance Company Systems and methods for providing a safety score associated with a user location
CN102129078B (zh) 2010-01-20 2013-05-22 厦门雅迅网络股份有限公司 上传车辆定位数据的方法
US8392116B2 (en) 2010-03-24 2013-03-05 Sap Ag Navigation device and method for predicting the destination of a trip
US8782045B1 (en) 2010-04-15 2014-07-15 Google Inc. Evaluating techniques for clustering geographic entities
US9183560B2 (en) * 2010-05-28 2015-11-10 Daniel H. Abelow Reality alternate
US20120041675A1 (en) 2010-08-10 2012-02-16 Steven Juliver Method and System for Coordinating Transportation Service
US8504062B2 (en) * 2010-11-01 2013-08-06 Wavemarket, Inc. System and method for aggregating and associating mobile device location data
KR101264284B1 (ko) * 2010-11-12 2013-05-22 재단법인대구경북과학기술원 택시 목적지 알림 서비스 방법
JP5389853B2 (ja) * 2011-04-08 2014-01-15 株式会社Ｎｔｔドコモ 地域情報配信サーバ、移動端末、地域情報配信システム、地域情報配信方法及び地域情報表示方法
JP2012244368A (ja) 2011-05-19 2012-12-10 Sony Corp 無線通信装置、情報処理装置、通信システムおよび位置決定方法
KR20130002086A (ko) 2011-06-28 2013-01-07 주식회사 선택인터내셔날 오차 보정을 통한 추측항법 시스템 및 그 방법
CN102402566A (zh) 2011-08-09 2012-04-04 江苏欣网视讯科技有限公司 基于中文网页自动分类技术的Web用户行为分析方法
US8538686B2 (en) * 2011-09-09 2013-09-17 Microsoft Corporation Transport-dependent prediction of destinations
CN102413231A (zh) 2011-10-10 2012-04-11 宇龙计算机通信科技(深圳)有限公司 移动终端和日程提醒方法
WO2013072729A1 (en) 2011-11-14 2013-05-23 Way Better Ltd System and method for ride sharing
CN102496130A (zh) 2011-11-15 2012-06-13 王家庆 一种高效运营出租车的实时移动商务系统
CN102629297B (zh) 2012-03-06 2016-01-06 北京建筑工程学院 一种基于行程识别的出行者活动规律分析方法
US9200918B2 (en) 2012-03-09 2015-12-01 Apple Inc. Intelligent destination recommendations based on historical data
US20160086391A1 (en) * 2012-03-14 2016-03-24 Autoconnect Holdings Llc Fleetwide vehicle telematics systems and methods
US20130246219A1 (en) * 2012-03-14 2013-09-19 Google Inc. Ranking and optimizing trips
JP5615312B2 (ja) 2012-03-26 2014-10-29 株式会社デンソーアイティーラボラトリ 渋滞予測方法及び渋滞予測装置
JP5901392B2 (ja) * 2012-03-30 2016-04-06 株式会社ゼンリンデータコム 情報処理システム、及び情報処理方法
CN102645220A (zh) 2012-05-21 2012-08-22 诚迈科技（南京）有限公司 智能出行方式实时规划推荐方法
KR101296737B1 (ko) * 2012-05-23 2013-08-20 이문호 배차 서비스 방법 및 배차 서비스 시스템
US9635557B2 (en) 2012-06-14 2017-04-25 Intel Corporation Reliability for location services
US9638537B2 (en) * 2012-06-21 2017-05-02 Cellepathy Inc. Interface selection in navigation guidance systems
WO2013192591A2 (en) 2012-06-22 2013-12-27 Google Inc. Ranking nearby destinations based on visit likelihoods and predicting future visits to places from location history
US8855901B2 (en) 2012-06-25 2014-10-07 Google Inc. Providing route recommendations
CN102749637A (zh) 2012-07-02 2012-10-24 西安大唐电信有限公司 一种车载gps精确定位的实现方法
US20140032274A1 (en) 2012-07-30 2014-01-30 Tikr, Inc. Apparatus, system, and method for managing dynamic pricing for online sales
CN103632532B (zh) 2012-08-22 2015-09-30 北京掌城科技有限公司 一种出租车的打车诱导方法
JP2014075727A (ja) * 2012-10-05 2014-04-24 Zenrin Datacom Co Ltd タクシー料金表示システム、サーバ装置及びタクシー料金表示支援プログラム。
CN103852771B (zh) 2012-12-05 2017-07-11 厦门雅迅网络股份有限公司 一种定位漂移的处理方法
CN102982680B (zh) 2012-12-10 2015-05-13 丰田汽车研发中心（中国）有限公司北京分公司 一种获取交通信息的方法及装置
EP2750087A1 (en) 2012-12-28 2014-07-02 Exapaq Sas Methods and systems for determining estimated package delivery/pick-up times
CN104937375B (zh) 2013-01-21 2017-05-10 三菱电机株式会社 目的地预测装置
CN103942229B (zh) 2013-01-22 2017-05-03 日电（中国）有限公司 目的地预测设备和方法
WO2014145059A2 (en) * 2013-03-15 2014-09-18 Bell Tyler Apparatus, systems, and methods for analyzing movements of target entities
US20140278105A1 (en) 2013-03-16 2014-09-18 Nimbler World, Inc. Computing apparatus and method for providing transportation information
CN103208181A (zh) 2013-04-09 2013-07-17 南京理工大学 可视化出租车点对点自主召车系统及其方法
US20140310277A1 (en) * 2013-04-15 2014-10-16 Flextronics Ap, Llc Suspending user profile modification based on user context
CN103323018B (zh) 2013-06-21 2016-01-27 广州市香港科大霍英东研究院 基于时段的热点路径的特征识别与快速搜索方法
US20150006279A1 (en) * 2013-06-27 2015-01-01 Google Inc. Systems and methods of generating a valid location cluster based on a location of a commercial entity
CN103310287B (zh) 2013-07-02 2016-07-06 北京航空航天大学 基于svm预测乘客出行概率的轨道交通客流预测方法
CN104427466A (zh) 2013-08-28 2015-03-18 高德软件有限公司 终端设备定位方法及终端设备
CN103514739B (zh) 2013-09-18 2015-07-08 福建工程学院 一种出租车叫车拼车方法及其系统
CN103747523B (zh) 2014-01-14 2017-09-22 上海河广信息科技有限公司 一种基于无线网络的用户位置预测系统和方法
CN103841517B (zh) 2014-03-03 2018-12-04 七星天（北京）咨询有限责任公司 一种叫车信息服务的系统和方法
US20160025408A1 (en) 2014-07-28 2016-01-28 Zhengrong Xu Air separation method and apparatus
SG10202000037SA (en) 2014-08-04 2020-03-30 Uber Technologies Inc Determining and providing predetermined location data points to service providers
EP3189479A1 (en) * 2014-09-02 2017-07-12 Telecom Italia S.p.A. Method and system for providing a dynamic ride sharing service
CN104391855A (zh) 2014-10-10 2015-03-04 百度在线网络技术（北京）有限公司 信息展示方法和装置
NZ733863A (en) * 2015-01-20 2019-04-26 Beijing Didi Infinity Technology & Dev Co Ltd Systems and methods for providing information for an on-demand service
GB2550309A (en) 2015-01-27 2017-11-15 Beijing Didi Infinity Tech And Dev Co Ltd Information providing method and system for on-demand service
CN104899252B (zh) 2015-05-12 2019-03-12 北京嘀嘀无限科技发展有限公司 一种信息推送的方法及装置
CN104599168A (zh) 2015-02-02 2015-05-06 北京嘀嘀无限科技发展有限公司 叫车订单的分配方法和装置
GB2550523A (en) 2015-02-02 2017-11-22 Beijing Didi Infinity Tech And Dev Co Ltd Methods and systems for order processing
WO2016127917A1 (zh) * 2015-02-10 2016-08-18 北京嘀嘀无限科技发展有限公司 一种订单推送方法及系统
WO2016127918A1 (zh) * 2015-02-13 2016-08-18 北京嘀嘀无限科技发展有限公司 一种运力调度方法及系统
CN104616086A (zh) 2015-02-28 2015-05-13 北京嘀嘀无限科技发展有限公司 用于动态设置订单的缓冲时间的方法和设备
US9989374B2 (en) * 2015-12-31 2018-06-05 Gt Gettaxi Limited System for generating travel route to be serviced by primary transportation service and secondary transportation service
US20230045975A1 (en) * 2018-01-23 2023-02-16 Circlesx Llc Financial Swap Index Method and System on Transportation Capacity Units and Trading Derivative Products Based Thereon
CN108022140A (zh) * 2016-11-02 2018-05-11 北京嘀嘀无限科技发展有限公司 一种用车订单推荐方法、装置及服务器
US20180137594A1 (en) * 2016-11-17 2018-05-17 Gt Gettaxi Limited System and method for reserving drivers for a transportation service and navigating drivers to service transportation requests
US10555354B2 (en) * 2016-12-06 2020-02-04 Beijing Didi Infinity Technology And Development Co., Ltd. Systems and methods for assisting two terminals to establish connections therebetween
KR102419728B1 (ko) * 2017-05-30 2022-07-13 현대자동차주식회사 상황 기반 동작 결정 시스템, 상황 기반으로 결정된 동작을 수행 가능한 차량 및 상황 기반 동작 결정 방법
EP3455840A4 (en) * 2017-06-13 2019-07-31 Beijing Didi Infinity Technology And Development Co., Ltd. SYSTEMS AND METHODS FOR ESTIMATED ARRIVAL TIME DETERMINATION

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2009125880A1 (en) * 2008-04-10 2009-10-15 Sk Marketing & Company Co., Ltd System and method for call service, call server, user terminal and storage medium
CN104442825A (zh) * 2014-11-28 2015-03-25 上海交通大学 一种电动汽车剩余行驶里程的预测方法和系统
CN104571036A (zh) * 2014-12-29 2015-04-29 小米科技有限责任公司 智能家居开启方法及装置
CN104599217A (zh) * 2015-01-27 2015-05-06 北京嘀嘀无限科技发展有限公司 用于确定乘客的当前目的地的方法及设备
CN105138590A (zh) * 2015-07-31 2015-12-09 北京嘀嘀无限科技发展有限公司 轨迹预测方法和装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3252704A4 *

Cited By (28)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11156470B2 (en) 2015-01-27 2021-10-26 Beijing Didi Infinity Technology And Development Co., Ltd. Methods and systems for providing information for an on-demand service
US11892312B2 (en) 2015-01-27 2024-02-06 Beijing Didi Infinity Technology And Development Co., Ltd. Methods and systems for providing information for an on-demand service
US10458806B2 (en) 2015-01-27 2019-10-29 Beijing Didi Infinity Technology And Development Co., Ltd. Methods and systems for providing information for an on-demand service
US20180012153A1 (en) * 2015-01-29 2018-01-11 Beijing Didi Infinity Technology And Development C O., Ltd. Order allocation system and method
US10977585B2 (en) * 2015-01-29 2021-04-13 Beijing Didi Infinity Technology And Development Co., Ltd. Order allocation system and method
CN111858937B (zh) * 2016-12-14 2024-04-30 创新先进技术有限公司 一种虚假地址信息识别的方法及装置
CN111858937A (zh) * 2016-12-14 2020-10-30 创新先进技术有限公司 一种虚假地址信息识别的方法及装置
KR20190094230A (ko) * 2016-12-14 2019-08-12 알리바바 그룹 홀딩 리미티드 잘못된 주소 정보를 식별하기 위한 방법 및 장치
KR102208892B1 (ko) 2016-12-14 2021-01-29 어드밴스드 뉴 테크놀로지스 씨오., 엘티디. 잘못된 주소 정보를 식별하기 위한 방법 및 장치
CN108289122A (zh) * 2017-01-09 2018-07-17 福特全球技术公司 用于分析运动配置文件的方法
CN106897919A (zh) * 2017-02-28 2017-06-27 百度在线网络技术（北京）有限公司 用车类型预测模型建立、信息提供方法及装置
JP2020504344A (ja) * 2017-04-27 2020-02-06 ベイジン ディディ インフィニティ テクノロジー アンド ディベロップメント カンパニー リミティッド 推定された到着時間を決定するためのシステムおよび方法
TWI763863B (zh) * 2017-06-06 2022-05-11 大陸商北京嘀嘀無限科技發展有限公司 區域劃分系統和方法
EP3455840A4 (en) * 2017-06-13 2019-07-31 Beijing Didi Infinity Technology And Development Co., Ltd. SYSTEMS AND METHODS FOR ESTIMATED ARRIVAL TIME DETERMINATION
CN110945501A (zh) * 2017-07-20 2020-03-31 北京嘀嘀无限科技发展有限公司 推荐目的地的系统和方法
WO2019015600A1 (en) * 2017-07-20 2019-01-24 Beijing Didi Infinity Technology And Development Co., Ltd. SYSTEMS AND METHODS FOR RECOMMENDING A DESTINATION
EP3642821A4 (en) * 2017-07-21 2020-04-29 Beijing Didi Infinity Technology and Development Co., Ltd. SYSTEMS AND METHODS FOR DETERMINING A NEW ROUTE ON A MAP
CN107528790B (zh) * 2017-07-28 2020-08-04 东北大学 一种缓解公交网络拥塞的方法
CN107528790A (zh) * 2017-07-28 2017-12-29 东北大学 一种改变节点处理顺序缓解公交网络拥塞的方法
CN107332770A (zh) * 2017-08-18 2017-11-07 郑州云海信息技术有限公司 一种必经点路由路径选择方法
CN110119955A (zh) * 2018-02-06 2019-08-13 北京嘀嘀无限科技发展有限公司 订单成交率预估方法及装置
CN110119955B (zh) * 2018-02-06 2022-11-11 北京嘀嘀无限科技发展有限公司 订单成交率预估方法及装置
US11120091B2 (en) * 2018-06-14 2021-09-14 Beijing Didi Infinity Technology And Development Co., Ltd. Systems and methods for on-demand services
CN111125272A (zh) * 2018-10-31 2020-05-08 百度在线网络技术（北京）有限公司 一种区域特征获取方法、装置、计算机设备及介质
CN111831897A (zh) * 2019-09-09 2020-10-27 北京嘀嘀无限科技发展有限公司 一种出行目的地推荐方法、装置、电子设备及存储介质
CN111831897B (zh) * 2019-09-09 2024-04-23 北京嘀嘀无限科技发展有限公司 一种出行目的地推荐方法、装置、电子设备及存储介质
CN113938521A (zh) * 2021-06-30 2022-01-14 深圳市巴滴科技有限公司 基于乘客需求信息的出行方案推荐方法及装置
CN114754783A (zh) * 2021-11-10 2022-07-15 广州汽车集团股份有限公司 一种用户出行信息的推荐方法、系统及汽车

Also Published As

Publication number Publication date
EP3252704A4 (en) 2018-08-01
EP3252704A1 (en) 2017-12-06
CA2975002C (en) 2020-09-29
US11892312B2 (en) 2024-02-06
US20220011131A1 (en) 2022-01-13
EP3252704B1 (en) 2022-04-06
US11156470B2 (en) 2021-10-26
JP6918087B2 (ja) 2021-08-11
CA2975002A1 (en) 2016-08-04
GB201712010D0 (en) 2017-09-06
JP2018503920A (ja) 2018-02-08
JP6637054B2 (ja) 2020-01-29
US20180017405A1 (en) 2018-01-18
AU2016212530A1 (en) 2017-08-17
BR112017016064A2 (zh) 2018-04-03
AU2019101806A4 (en) 2021-07-22
PH12017501345A1 (en) 2017-12-18
US10458806B2 (en) 2019-10-29
SG11201706149XA (en) 2017-08-30
HK1245955A1 (zh) 2018-08-31
MY193639A (en) 2022-10-21
US20200003576A1 (en) 2020-01-02
KR20180006875A (ko) 2018-01-19
JP2020057423A (ja) 2020-04-09
GB2550309A (en) 2017-11-15
AU2019236639A1 (en) 2019-10-17

Similar Documents

Publication Publication Date Title
WO2016119704A1 (zh) 一种为按需服务提供信息的方法及系统
WO2016127917A1 (zh) 一种订单推送方法及系统
Pereira et al. Using data from the web to predict public transport arrivals under special events scenarios
WO2016127918A1 (zh) 一种运力调度方法及系统
US11182871B2 (en) System and apparatus for ridesharing
WO2016138863A1 (zh) 一种订单配对系统及方法
US9488487B2 (en) Route detection in a trip-oriented message data communications system
WO2016124118A1 (zh) 一种订单处理方法与系统
WO2016119749A1 (zh) 一种订单分配系统及方法
JP2018503196A (ja) オン・デマンドサービスの情報を提供するシステム及び方法
EP4187204A1 (en) Method and system for generating a personalized routing graph for use with shared vehicle hubs
Nguyen Deriving trip's modes and trip's purposes from GPS-based travel surveys
US20230289667A1 (en) Contextual relevance for shared mobility
BR112017016064B1 (pt) Métodos e sistemas para fornecer informação para um serviço por demanda
Paoli Big Data Solutions: Models and Algorithms in Smart City Domains
NZ751377B2 (en) Methods and systems for providing information for an on-demand service
NZ751377A (en) Methods and systems for providing information for an on-demand service
BR112017018866B1 (pt) Sistemas e métodos para emparelhamento de ordens

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16742766

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2975002

Country of ref document: CA

Ref document number: 201712010

Country of ref document: GB

Kind code of ref document: A

Free format text: PCT FILING DATE = 20160127

REEP Request for entry into the european phase

Ref document number: 2016742766

Country of ref document: EP

WWE Wipo information: entry into national phase

Ref document number: 15546657

Country of ref document: US

ENP Entry into the national phase

Ref document number: 2017539550

Country of ref document: JP

Kind code of ref document: A

WWE Wipo information: entry into national phase

Ref document number: 12017501345

Country of ref document: PH

NENP Non-entry into the national phase

Ref country code: DE

WWE Wipo information: entry into national phase

Ref document number: 11201706149X

Country of ref document: SG

ENP Entry into the national phase

Ref document number: 2016212530

Country of ref document: AU

Date of ref document: 20160127

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 20177023933

Country of ref document: KR

Kind code of ref document: A

REG Reference to national code

Ref country code: BR

Ref legal event code: B01A

Ref document number: 112017016064

Country of ref document: BR

ENP Entry into the national phase

Ref document number: 112017016064

Country of ref document: BR

Kind code of ref document: A2

Effective date: 20170727