WO2021052451A1

WO2021052451A1 - Method and system for determining estimated time of arrival

Info

Publication number: WO2021052451A1
Application number: PCT/CN2020/116081
Authority: WO
Inventors: 傅昆; 王征
Original assignee: 北京嘀嘀无限科技发展有限公司
Priority date: 2019-09-18
Filing date: 2020-09-18
Publication date: 2021-03-25
Also published as: CN111860903A

Abstract

The embodiments of the present application provide a method for determining an estimated time of arrival. Said method can comprise the following operations: acquiring a service request, the service request at least comprising a start point and an end point; determining an estimated travel route for the service request on the basis of the start point and the end point; acquiring an estimated positioning point sequence on the basis of the estimated travel route; and determining an estimated time of arrival of the service request on the basis of the estimated positioning point sequence.

Description

Method and system for determining estimated arrival time

Priority statement

This application claims the priority of the Chinese patent application 201910879115.5 filed on September 18, 2019, which is incorporated herein by reference in its entirety.

Technical field

This application relates to the field of transportation technology, and in particular to a method and system for determining an estimated time of arrival.

Background technique

With the development of network technology and communication technology, Online to Offline (O2O) services have become more and more popular. Take online taxi services as an example. Online taxi services bring a lot of convenience to people's daily lives. For online taxi-hailing services, Estimated Time of Arrival (ETA) is a very important technical indicator, which is used to estimate the time to reach a specified destination and can describe the time and cost of the user’s travel . However, due to frequent updates of road network data, ETA estimation is difficult. Therefore, it is necessary to propose a method and system for determining the estimated arrival time, so as to effectively estimate the arrival time of the service request and improve the user experience.

Summary of the invention

One of the embodiments of the present application provides a system. The system may include at least one storage medium and at least one processor. The storage medium may include instructions for determining the estimated time of arrival. The at least one processor may communicate with the at least one storage medium. When executing the instruction, the at least one processor is configured to perform the following operations: obtain a service request, the service request including at least a starting point and an end point; based on the starting point and the end point, determining the pre-determined value of the service request Estimate the driving path; obtain an estimated positioning point sequence based on the estimated driving path; determine the estimated arrival time of the service request based on the estimated positioning point sequence.

In some embodiments, in order to determine the estimated travel path, the processor is configured to perform the following operations: determine road network data related to the service request based on the start point and the end point; The starting point, the ending point, and the road network data are used to determine the estimated driving path using a path planning algorithm.

In some embodiments, the estimated travel path includes multiple road segments and traffic conditions of multiple road segments.

In some embodiments, in order to obtain an estimated positioning point sequence based on the estimated driving path, the processor is configured to perform the following operations: processing the estimated driving path using an positioning point sequence estimation model to obtain the Estimate the sequence of anchor points.

In some embodiments, the positioning point sequence estimation model includes a neural network model.

In some embodiments, the positioning point sequence estimation model includes a generative countermeasure network, and the generative countermeasure network includes a generator and a discriminator.

In some embodiments, in order to obtain the positioning point sequence estimation model, the processor is configured to perform the following operations: obtain a plurality of historical orders, the plurality of historical orders corresponding to a plurality of historical driving paths and a plurality of historical positioning Point sequence; based on the multiple historical orders, the generative confrontation network is determined through at least one iteration, wherein each of the at least one iteration includes: using the generator in the current iteration to determine the difference with the multiple Multiple sample positioning point sequences corresponding to a historical driving path; fixing the generator and optimizing the discriminator in the current iteration based on the multiple sample positioning point sequences and the multiple historical positioning point sequences; fixing the optimized The discriminator optimizes the generator based on at least the parameters of the optimized discriminator.

In some embodiments, in order to optimize the discriminator, the processor is configured to perform the following operations: determine the classification results of the plurality of sample positioning point sequences and the plurality of historical positioning point sequences; at least based on the According to the classification result, the value of the first loss function of the discriminator is determined; and the discriminator is optimized based on the value of the first loss function.

In some embodiments, in order to optimize the generator, the processor is configured to perform the following operations: at least based on the parameters of the optimized discriminator, the plurality of sample positioning point sequences, and the plurality of historical positioning Point sequence, determine the value of the second loss function of the generator; optimize the generator based on the value of the second loss function.

In some embodiments, in order to determine the estimated arrival time of the service request based on the estimated positioning point sequence, the processor is configured to perform the following operations: processing the estimated positioning using an estimated time of arrival model Point sequence to determine the estimated time of arrival of the service request.

One of the embodiments of the present application provides a method for determining the estimated time of arrival. The method may include the following operations. Obtain a service request, the service request including at least a starting point and an ending point; based on the starting point and the ending point, determining an estimated driving path of the service request; obtaining an estimated positioning point sequence based on the driving path; Estimate the positioning point sequence to determine the estimated time of arrival of the service request.

In some embodiments, the determining the estimated travel path may include the following operations: determining road network data related to the service request based on the starting point and the ending point; based on the starting point, the ending point, and The road network data uses a path planning algorithm to determine the estimated driving path.

In some embodiments, the obtaining an estimated positioning point sequence based on the estimated driving path may include the following operations: processing the estimated driving path using an positioning point sequence estimation model to obtain the estimated positioning point sequence.

In some embodiments, the obtaining the positioning point sequence estimation model may include the following operations: obtaining a plurality of historical orders, the plurality of historical orders corresponding to a plurality of historical driving paths and a plurality of historical positioning point sequences; Multiple historical orders, the generative confrontation network is determined through at least one iteration, wherein each of the at least one iteration includes: using a generator in the current iteration to determine the corresponding to the multiple historical driving paths Multiple sample positioning point sequences; fix the generator and optimize the discriminator in the current iteration based on the multiple sample positioning point sequences and the multiple historical positioning point sequences; fix the optimized discriminator and at least based on all The parameters of the optimized discriminator are optimized, and the generator is optimized.

In some embodiments, the optimizing the discriminator may include the following operations: determining the classification results of the plurality of sample positioning point sequences and the plurality of historical positioning point sequences; determining the The value of the first loss function of the discriminator; based on the value of the first loss function, the discriminator is optimized.

In some embodiments, the optimization of the generator may include the following operations: determining the sequence based on at least the parameters of the optimized discriminator, the plurality of sample positioning point sequences, and the plurality of historical positioning point sequences The value of the second loss function of the generator; based on the value of the second loss function, the generator is optimized.

In some embodiments, the determining the estimated time of arrival of the service request based on the estimated positioning point sequence may include the following operations: processing the estimated positioning point sequence using an estimated time of arrival model to determine the The estimated time of arrival of the service request.

One of the embodiments of the present application provides a computer-readable storage medium that stores computer instructions. After the computer reads the computer instructions in the storage medium, the computer executes the method for determining the estimated time of arrival as described below: Get Service request, the service request includes at least a starting point and an ending point; based on the starting point and the ending point, the estimated driving path of the service request is determined; based on the driving path, an estimated positioning point sequence is obtained; based on the prediction Estimate the positioning point sequence and determine the estimated time of arrival of the service request.

Description of the drawings

This application will be further described in the form of exemplary embodiments, and these exemplary embodiments will be described in detail with the accompanying drawings. These embodiments are not restrictive. In these embodiments, the same number represents the same structure, in which:

Fig. 1 is a schematic diagram of an exemplary O2O service system according to some embodiments of the present application;

Fig. 2 is a schematic diagram of exemplary hardware components and/or software components of an exemplary computing device according to some embodiments of the present application;

Fig. 3 is a schematic diagram of exemplary hardware components and/or software components of an exemplary mobile device according to some embodiments of the present application;

Fig. 4 is a block diagram of an exemplary processing device according to some embodiments of the present application;

Fig. 5 is a flowchart of an exemplary process for determining an estimated arrival time according to some embodiments of the present application;

Fig. 6 is a flowchart of an exemplary process for determining a positioning point sequence estimation model according to some embodiments of the present application;

Fig. 7 is a flowchart of an exemplary iteration of training a generative confrontation network according to some embodiments of the present application;

Fig. 8 is a block diagram of an exemplary terminal according to some embodiments of the present application;

FIG. 9 is a flowchart of an exemplary process for determining an estimated time of arrival according to some embodiments of the present application;

Fig. 10 is a schematic diagram of interaction between a processing device and a terminal according to some embodiments of the present application.

detailed description

In order to more clearly describe the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings that need to be used in the description of the embodiments. Obviously, the drawings in the following description are only some examples or embodiments of the application. For those of ordinary skill in the art, without creative work, the application can be applied to the application according to these drawings. Other similar scenarios. Unless it is obvious from the language environment or otherwise stated, the same reference numerals in the figures represent the same structure or operation.

It should be understood that the “system”, “device”, “unit” and/or “module” used herein is a method for distinguishing different components, elements, parts, parts, or assemblies of different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

As shown in the present application and claims, unless the context clearly suggests exceptional circumstances, the words "a", "an", "an" and/or "the" do not specifically refer to the singular, but may also include the plural. Generally speaking, the terms "include" and "include" only suggest that the clearly identified steps and elements are included, and these steps and elements do not constitute an exclusive list, and the method or device may also include other steps or elements.

A flowchart is used in this application to illustrate the operations performed by the system according to the embodiment of the application. It should be understood that the preceding or following operations are not necessarily performed exactly in order. Instead, the individual steps can be processed in reverse order or at the same time. At the same time, you can also add other operations to these processes, or remove a step or several operations from these processes.

The embodiments of the present application can be applied to different transportation systems, which include, but are not limited to, one or a combination of land, ocean, aviation, and aerospace. For example, taxis, private cars, ride-hailing cars, buses, agent driving, trains, high-speed trains, ships, airplanes, hot air balloons, unmanned vehicles, collection/delivery express delivery, etc. which apply management and/or distribution transportation systems . The application scenarios of the different embodiments of the present application include, but are not limited to, one or a combination of web pages, browser plug-ins, clients, customized systems, internal enterprise analysis systems, artificial intelligence robots, and the like. It should be understood that the application scenarios of the system and method of the present application are only some examples or embodiments of the present application. For those of ordinary skill in the art, they can also be based on these drawings without creative work. Apply this application to other similar scenarios. For example, other similar systems for guiding users to park.

The "passenger", "passenger terminal", "user terminal", "customer", "demand", "service demander", "consumer", "consumer", "user demander", etc. described in this application are Interchangeable refers to the party that needs or subscribes to the service. It can be an individual or a tool. Similarly, the “driver”, “driver’s end”, “provider”, “provider”, “service provider”, “service provider”, “service provider”, etc. described in this application are also interchangeable and refer to Individuals, tools, or other entities that provide services or assist in providing services. In addition, the "user" described in this application may be a party that needs or subscribes to services, or a party that provides services or assists in providing services.

Fig. 1 is a schematic diagram of an exemplary O2O service system according to some embodiments of the present application. In some embodiments, the O2O service system 100 can be applied to multiple application scenarios. For example, the O2O service system 100 may be an online service platform that can provide transportation services. Transportation services may include taxi services, express services, private car services, minibus services, car pool services, public transportation services, driving services, courier services, Take-out service, pick-up service, etc. For another example, the O2O service system 100 may also be an online service platform that provides other types of services, such as housekeeping services, travel (for example, travel) services, online and offline shopping services, education services, and so on.

In some embodiments, the O2O service system 100 can determine the estimated time of arrival of the trip. For example, for a taxi service, the O2O service system 100 may determine the estimated time for the driver to arrive at the passenger boarding point. For another example, for a taxi service, the O2O service system 100 can determine the estimated time for the driver to arrive at the destination from the departure point after picking up the passenger. For another example, for navigation services, the O2O service system 100 can determine the estimated time to arrive at the destination from the departure point set by the user. For another example, for an online meal delivery service, the O2O service system 100 can determine the estimated time from the merchant to the meal pick-up point set by the user.

As shown in FIG. 1, the O2O service system 100 may include a processing device 110, a terminal 120, a storage device 130, a network 140, and an information source 150.

The processing device 110 may process data and/or information obtained from the terminal 120, the storage device 130, and/or the information source 150. In some embodiments, the processing device 110 may obtain location/trajectory information of multiple terminals 120 and/or characteristic information of participants (for example, drivers and passengers) related to the journey. The processing device 110 may process the information and/or data obtained above to perform one or more functions described in this application. For example, the processing device 120 may obtain the service request from the terminal 120, and determine the estimated travel path of the service request based on the data obtained from the information source 150. Further, the processing device 120 may determine the estimated positioning point sequence corresponding to the estimated driving path and determine the estimated arrival time of the service request based on the estimated positioning point sequence. In some embodiments, the processing device 110 may be an independent server or a server group. The server group may be centralized or distributed (for example, the processing device 110 may be a distributed system). In some embodiments, the processing device 110 may be local or remote. For example, the processing device 110 may access information and/or data stored in the terminal 120, the storage device 130, and/or the information source 150 through the network 140. In some embodiments, the processing device 110 may be directly connected to the terminal 120, the storage device 130, and/or the information source 150 to access the information and/or data stored therein. In some embodiments, the processing device 110 may be executed on a cloud platform. For example, the cloud platform may include one or any combination of private cloud, public cloud, hybrid cloud, community cloud, decentralized cloud, internal cloud, etc. In some embodiments, the processing device 110 may be integrated in the terminal 120. In some embodiments, the processing device 110 may be implemented by the computing device 200 shown in FIG. 2.

In some embodiments, the processing device 110 may include one or more sub-processing devices (for example, a single-core processor or a multi-core processor). For example only, the processing device 110 may include a central processing unit (CPU), an application specific integrated circuit (ASIC), an application specific instruction processor (ASIP), a graphics processing unit (GPU), a physical processor (PPU), a digital signal processor ( DSP), Field Programmable Gate Array (FPGA), Editable Logic Circuit (PLD), Controller, Microcontroller Unit, Reduced Instruction Set Computer (RISC), Microprocessor, etc. or any combination thereof.

The terminal 120 may be a device with data acquisition, storage and/or transmission functions. The terminal 120 may include a service provider terminal, a service requester terminal, a vehicle-mounted terminal, and the like. Service providers can be individuals, tools, or other entities that provide services. Service requesters can be individuals, tools, or other entities that need to get or are receiving services. For example, for a taxi-hailing service, the service provider may be a driver or a third-party platform, and the service requester may be a passenger or other individuals or devices (for example, IoT devices) that receive similar services. In some embodiments, the terminal 120 may be used to collect various types of data, including but not limited to service-related data. The data collected by the terminal 120 may be real-time data or various historical data. In some embodiments, the terminal 120 may collect data through its own sensors, acquire data from external sensors, or read data from its own memory, or read data from the storage device 130 through the network 140. In some embodiments, the sensors of the terminal 120 may include positioning devices, sound sensors, image sensors, temperature and humidity sensors, position sensors, pressure sensors, distance sensors, speed sensors, acceleration sensors, gravity sensors, displacement sensors, torque sensors, and gyroscopes.仪, etc. or any combination thereof.

In some embodiments, the terminal 120 may include a mobile device 120-1, a vehicle built-in device 120-2, a notebook computer 120-3, a desktop computer 120-4, etc., or any combination thereof. In some embodiments, the mobile device 120-1 may include a smart home device, a wearable device, a smart mobile device, a virtual reality device, an augmented reality device, etc., or any combination thereof. Smart home devices may include smart lighting devices, smart electrical control devices, smart monitoring devices, smart TVs, smart cameras, walkie-talkies, etc., or any combination thereof. Wearable devices may include smart bracelets, smart footwear, smart glasses, smart helmets, smart watches, smart clothes, smart backpacks, smart accessories, etc., or any combination thereof. Smart mobile devices may include smart phones, personal digital assistants (PDAs), game devices, navigation devices, POS machines, etc., or any combination thereof. The virtual reality/augmented reality device may include a virtual reality helmet, virtual reality glasses, virtual reality goggles, augmented reality helmets, augmented reality glasses, augmented reality goggles, etc., or any combination thereof. In some embodiments, the in-vehicle device 120-2 may include an in-vehicle computer, an in-vehicle data recorder, an in-vehicle human-computer interaction (HCI) system, a driving recorder, an in-vehicle TV, and the like.

In some embodiments, the terminal 120 may be a device with a positioning function, and its positioning function may be realized by a variety of positioning technologies, for example, the global positioning system (GPS), the global satellite navigation system (GLONASS), and the Beidou navigation system (COMPASS) , Galileo positioning system, quasi-zenith satellite system (QZSS), wireless fidelity (Wi-Fi) positioning technology, etc. In some embodiments, the terminal 120 may transmit the collected data/information to the processing device 110 via the network 140 for subsequent steps. The terminal 120 may also store the collected data/information in its own memory, or transmit it to the storage device 130 via the network 140 for storage. The terminal 120 may also receive and/or display information generated by the processing device 110 (for example, a notification related to the estimated time of arrival). In some embodiments, the O2O system 100 may include multiple terminals connected to each other to collect various types of data, and one or more of the terminals may preprocess the data.

The storage device 130 may store data and/or instructions. In some embodiments, the storage device 130 may store data/information acquired by the terminal 120 and/or the processing device 110. For example, the storage device 130 may store historical transportation service data (for example, historical service order data, historical service participant data, historical vehicle-related data, historical travel data, historical order evaluation data, etc.). In some embodiments, the storage device 130 may store data and/or instructions used by the processing device 110 to execute or use to complete the exemplary methods described in this application. In some embodiments, the storage device 130 may be a part of the processing device 110 or the terminal 120.

In some embodiments, the storage device 130 may include mass memory, removable memory, volatile read-write memory, read-only memory (ROM), etc., or any combination thereof. Exemplary mass storage devices may include magnetic disks, optical disks, solid state disks, and the like. Exemplary removable storage may include flash drives, floppy disks, optical disks, memory cards, compact disks, magnetic tapes, and the like. An exemplary volatile read-only memory may include random access memory (RAM). Exemplary RAM may include dynamic RAM (DRAM), double rate synchronous dynamic RAM (DDR SDRAM), static RAM (SRAM), thyristor RAM (T-RAM), zero capacitance RAM (Z-RAM), and the like. Exemplary ROMs may include mask ROM (MROM), programmable ROM (PROM), erasable programmable ROM (EPROM), electronically erasable programmable ROM (EEPROM), compact disk ROM (CD-ROM), and digital General-purpose disk ROM, etc. In some embodiments, the storage device 130 may be implemented on a cloud platform. For example only, the cloud platform may include private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, internal cloud, multi-layer cloud, etc., or any combination thereof. In some embodiments, specific types of historical data can be uniformly stored on a cloud platform, so that multiple processing devices 110 or terminals 120 can access or update, and ensure the real-time and cross-platform use of the data.

In some embodiments, the storage device 130 may be connected to the network 140 to communicate with one or more components in the O2O service system 100 (for example, the processing device 110, the terminal 120, and the information source 150). One or more components in the O2O service system 100 can access data or instructions stored in the storage device 130 through the network 140. In some embodiments, the storage device 130 may directly connect or communicate with one or more components in the O2O service system 100 (for example, the processing device 110, the terminal 120, and the information source 150).

The network 140 may facilitate the exchange of information and/or data. In some embodiments, one or more components in the O2O service system 100 (for example, the processing device 110, the terminal 120, the storage device 130, and the information source 150) can send to/from other components in the O2O service system 100 via the network 140 And/or receive information and/or data. For example, the processing device 110 may obtain data/information related to transportation services from the terminal 120 and/or the information source 150 through the network 140. For another example, the terminal 120 may obtain the estimated arrival time of the service request from the processing device 110 or the storage device 130 via the network 140. The estimated arrival time can be displayed on the interface of the terminal 120 through application software.

In some embodiments, the network 140 may be any form of wired or wireless network or any combination thereof. For example only, the network 140 may include a cable network, a wired network, an optical fiber network, a telecommunication network, an internal network, the Internet, a local area network (LAN), a wide area network (WAN), a wireless local area network (WLAN), a metropolitan area network (MAN), public switched telephone network (PSTN), Bluetooth ^(TM) network, ZigBee ^TM network, near field communication (NFC) network, global system for mobile communications (GSM) network, Code division Multiple Access (CDMA) networks, Time division Multiple Access (TDMA) network , General Packet Radio Service (GPRS) network, Enhanced Data Rate GSM Evolution (EDGE) Network, Wideband Code Division Multiple Access (WCDMA) Network, High Speed Downlink Packet Access (HSDPA) Network, Long Term Evolution (LTE) Network, User Datagram Protocol (UDP) network, Transmission Control Protocol/Internet Protocol (TCP/IP) network, Short Message Service (SMS) network, Wireless Application Protocol (WAP) network, Ultra Wide Band (UWB) network, mobile communication (1G, 2G) , 3G, 4G, 5G) networks, Wi-Fi, Li-Fi, Narrowband Internet of Things (NB-IoT), etc. or any combination thereof. In some embodiments, the O2O service system 100 may include one or more network access points. For example, the O2O service system 100 may include wired or wireless network access points, such as base stations and/or wireless access points 140-1, 140-2, ..., through which one or more components of the O2O service system 100 may be connected To the network 140 to exchange data and/or information.

The information source 150 may be used to provide reference information for the O2O service system 100. In some embodiments, the reference information may include weather information, traffic information, geographic information, laws and regulations information, news events, life information, life guide information, and the like. The information source 150 may be implemented by a single central server, multiple servers connected to each other (for example, connected through a communication link), or multiple personal devices. For example, a personal device can generate content (e.g., text, voice, image, video) and upload it to a cloud server. Correspondingly, the information source 150 may be implemented by multiple personal devices and cloud servers. In some embodiments, the storage device 130, the processing device 110, and/or the terminal 120 may also serve as information sources. For example, the real-time feedback speed and/or positioning information of the terminal 120 may be used as reference information for other devices to obtain.

Those of ordinary skill in the art should understand that when the components of the O2O service system 100 are executed, the components may be executed by electrical signals and/or electromagnetic signals. For example, when the terminal 120 processes a task, such as determining, identifying, or selecting an object, the terminal 120 may operate a logic circuit in its processor to process the task. When the terminal 120 sends a service request to the processing device 110, the processor of the terminal 120 may generate an electrical signal encoding the request. Then, the processor of the terminal 120 may send the electrical signal to the output port. If the terminal 120 communicates with the processing device 110 via a wired network, the output port may be physically connected to a cable, which further transmits electrical signals to the input port of the processing device 110. If the terminal 120 communicates with the processing device 110 through a wireless network, the output port of the terminal 120 may be one or more antennas, and the antennas may convert electrical signals into electromagnetic signals. In an electronic device, when the processor of the electronic device processes instructions, sends instructions, and/or performs actions, the instructions and/or actions are conducted via electrical signals. For example, when the processor retrieves or saves data from a storage medium (for example, the storage device 130), it can send an electrical signal to a read/write device of the storage medium, and the read/write device can read or write in the storage medium. Structured data. The structured data can be transmitted to the processor via the bus of the electronic device in the form of electrical signals. Here, the electrical signal may refer to one electrical signal, a series of electrical signals, and/or multiple discontinuous electrical signals.

Fig. 2 is a schematic diagram of exemplary hardware components and/or software components of an exemplary computing device according to some embodiments of the present application. In some embodiments, the processing device 110 and/or the terminal 120 may be implemented by the computing device 200. As shown in FIG. 2, the computing device 200 may include a processor 210, a memory 220, an input/output (I/O) 230, and a communication port 240.

The processor 210 may execute computer instructions (for example, program code) and may perform the functions of the processing device 110 according to the technology described in this application. Computer instructions can be used to perform specific functions described in this application, and computer instructions can include programs, objects, components, data structures, programs, modules, functions, and so on. In some embodiments, the processor 210 may include one or more hardware processors, such as a microcontroller, a microprocessor, a reduced instruction set computer (RISC), and an application specific integrated circuit. circuit (ASIC)), application-specific instruction-set processor (ASIP), central processing unit (CPU), graphics processing unit (GPU)) , Physical processing unit (physics processing unit (PPU)), digital signal processor (digital signal processor (DSP)), field programmable gate array (FPGA)), advanced RISC machine (advanced RISC machine( ARM)), programmable logic device (PLD), any circuit or processor capable of performing one or more functions, or a combination of several of them.

For illustration only, only one processor is described in the computing device 200. However, it should be noted that the computing device 200 may also include multiple processors. The operations and/or methods described in this application that are executed by one processor may also be executed jointly or separately by multiple processors. For example, if the processor of the computing device 200 described in this application performs operation A and operation B, it should be understood that operation A and operation B can also be shared by two or more different processors in the computing device 200. Or separately (for example, the first processor performs operation A and the second processor performs operation B, or the first processor and the second processor jointly perform operations A and B).

The memory 220 may store data/information acquired from the processing device 110, the terminal 120, the storage device 130, and/or any other components of the O2O service system 100. In some embodiments, the memory 220 may include mass memory, removable memory, volatile read-write memory, read-only memory (ROM), etc., or any combination thereof. Mass storage can include magnetic disks, optical disks, solid state drives, mobile storage, and so on. Removable storage may include flash drives, floppy disks, optical disks, memory cards, ZIP disks, tapes, and so on. Volatile read-write memory may include random access memory (RAM). RAM can include dynamic random access memory (DRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), static random access memory (SRAM), thyristor random access memory (t-ram), zero capacitance random access memory Take memory (Z-RAM) and so on. ROM can include mask read-only memory (MROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), optical disk read-only memory Storage (CD-ROM), digital versatile disc, etc. In some embodiments, the memory 220 may store one or more programs and/or instructions for executing the exemplary methods described in this application.

The input/output 230 can input and/or output signals, data, information, and the like. In some embodiments, the input/output 230 may implement the interaction between the user and the processing device 110. In some embodiments, the input/output 230 may include an input device and an output device. The input device may include a keyboard, a mouse, a touch screen, a microphone, etc., or any combination thereof. The output device may include a display device, a speaker, a printer, a projector, etc. or any combination thereof. The display device may include a liquid crystal display (LCD), a light emitting diode (LED) display, a flat panel display, a curved screen, a television device, a cathode ray tube (CRT), a touch screen, etc., or any combination thereof.

The communication port 240 may be connected to a network (for example, the network 140) to facilitate data communication. The communication port 240 may establish a connection between the processing device 110 and the terminal 120, the storage device 130, and/or the information source 150. The connection may be a wired connection, a wireless connection, any connection capable of data transmission and/or reception, etc., or any combination thereof. Wired connections can include cables, optical cables, telephone lines, etc., or any combination thereof. The wireless connection may include a Bluetooth ^™ link, a Wi-Fi ^™ link, a WiMAX ^™ link, a wireless local area network link, a ZigBee ^™ link, a mobile network link (for example, 3G, 4G, 5G, etc.), etc., or any combination thereof. In some embodiments, the communication port 240 may be and/or include a standardized communication port, such as RS232, RS485, and the like.

Fig. 3 is a schematic diagram of exemplary hardware components and/or software components of an exemplary mobile device according to some embodiments of the present application. In some embodiments, the terminal 120 may be implemented by the mobile device 300. As shown in FIG. 3, the mobile device 300 may include a communication platform 310, a display 320, a graphics processing unit (GPU) 330, a central processing unit (CPU) 340, an input/output 350, a memory 360, and a storage 390. In some embodiments, the mobile device 300 may also include any other suitable components, including but not limited to a system bus or a controller (not shown in the figure). In some embodiments, the mobile operating system 370 (for example, iOS ^™ , Android, Windows Phone ^™, etc.) and one or more application programs 380 may be loaded from the memory 390 into the memory 360 so as to be executed by the central processing unit 340. The application program 380 may include a browser or any other suitable mobile application program for receiving and presenting information related to the estimated time of arrival or other information from the processing device 110. The user interaction of the information flow may be implemented through the input/output 350 and provided to the processing device 110 and/or other components of the O2O service system 100 through the network 140.

In order to realize the various modules, units and functions described in this application, a computer hardware platform may be used as a hardware platform for one or more elements described in this application. A computer with user interface elements can be used to implement a personal computer (PC) or any other type of workstation or terminal device. If properly programmed, the computer can also act as a server.

Fig. 4 is a block diagram of an exemplary processing device according to some embodiments of the present application. As shown in FIG. 4, the processing device 110 may include an acquisition module 410, a determination module 420, a processing module 430, an estimation module 440, a training module 450, and a transmission module 460.

The obtaining module 410 can obtain the service request. For example, the obtaining module 410 may obtain a service request from the terminal 120. For another example, the obtaining module 410 may obtain a service request from the storage device 130 or other third-party devices. The service request may include a transportation service request, for example, a taxi service request, a navigation service request, a meal delivery service request, and so on. In some embodiments, the service request may be a real-time service request or an appointment service request. In some embodiments, the service request may include at least a starting point (for example, a passenger's boarding point) and an ending point (for example, a passenger's getting off point).

The determination module 420 may determine the estimated travel path of the service request based on the start point and the end point. In some embodiments, the determination module 420 may determine the road network data related to the service request based on the starting point and the end point, and determine the estimated driving path of the service request based on the road network data related to the service request. In some embodiments, the determination module 420 may obtain road network data from the storage device 130, a map service provider, and/or other third-party devices. After obtaining the road network data related to the service request, the determining module 420 may determine the estimated driving path of the service request based on the starting point, the end point, and the road network data related to the service request using a path planning algorithm.

The processing module 430 may obtain an estimated positioning point sequence based on the preset driving path. The estimated positioning point sequence may include a series of virtual positioning points (or can be understood as a virtual trajectory obtained by connecting these virtual positioning points) between the starting point and the end point. The processing module 430 may use the positioning point sequence estimation model to process the estimated driving path. Get the sequence of estimated anchor points. Specifically, the processing module 430 may input the estimated driving path into the trained positioning point sequence estimation model, and determine the estimated positioning point sequence based on the output of the positioning point sequence estimation model. In some embodiments, the positioning point sequence estimation model may include a neural network model. In some embodiments, the positioning point sequence estimation model may include a Generative Adversarial Network (GAN). The processing module 430 may use the trained generative countermeasure network to obtain an estimated positioning point sequence similar to the estimated driving path height. Specifically, the processing module 430 may input the estimated driving path and/or its related feature information into the generator, and the generator may generate the corresponding estimated anchor point sequence, and the discriminator considers that the authenticity probability of the estimated anchor point sequence satisfies Requirement, that is, the discriminator cannot determine the true or false of the estimated positioning point sequence.

The estimation module 440 may determine the estimated arrival time of the service request based on the estimated positioning point sequence. The processing device 110 may use the estimated time of arrival model to process the estimated positioning point sequence to determine the estimated time of arrival of the service request. Specifically, the processing device 110 may input the estimated positioning point sequence into the estimated time of arrival model, and determine the estimated time of arrival based on the output of the estimated time of arrival model. In some embodiments, the estimated time of arrival model may include a deep learning model. Exemplary deep learning models may include, but are not limited to, deep belief network model, VGG (Visual Geometry Group Network), OverFeat, RNN (Recurrent Neural Network), LSTM (Long Short Term Memory), GUR (Gated Recurrent Unit), R- CNN (Region based Convolutional Neural Network), SPP-Net (Spatial Pyramid Pooling Network), Fast R-CNN (Fast Region based Convolutional Neural Network, Fast R-CNN (Faster Region based on Convolutional Neural Network, R-FCN (Region based Fully Network)) Convolutional Network), DSOD (Deeply Supervised Object Detector), etc.

The training module 450 can be used to train the model. In some embodiments, the training module 450 may obtain multiple historical orders, and based on the multiple historical orders, determine the generative confrontation network through at least one iteration. The multiple historical orders may include service orders for a period of time in the past (for example, 6 hours, 12 hours, 1 day, 2 days, 7 days, 14 days, 1 month, 3 months, etc.). In one iteration, the training module 450 may use the generator in the current iteration to determine multiple sample positioning point sequences corresponding to multiple historical driving paths. Subsequently, the training module 450 can fix the generator and optimize the discriminator in the current iteration based on multiple sample positioning point sequences and multiple historical positioning point sequences. For example, the training module 450 may determine the classification results of multiple sample positioning point sequences and multiple historical positioning point sequences, and determine the value of the first loss function of the current discriminator based at least on the classification results. Further, the training module 450 may optimize the current discriminator based on the value of the first loss function. After optimizing the current discriminator, the training module 450 may fix the optimized discriminator and optimize the generator based at least on the parameters of the optimized discriminator. The training module 450 may determine the value of the second loss function of the generator based at least on the parameters of the optimized discriminator, multiple sample positioning point sequences, and multiple historical positioning point sequences. Specifically, the training module 450 may determine the current generator based on the classification result (ie, authenticity determination) of the multiple sample positioning point sequences by the optimized discriminator and the difference between the multiple sample positioning point sequences and the multiple historical positioning point sequences. The value of the second loss function. Further, the training module 450 may optimize the current generator based on the value of the second loss function. Specifically, the training module 450 may reversely adjust the parameters of the current generator for optimization according to the value of the second loss function, so that the sample positioning point sequence generated by the optimized generator is as close as possible to the real historical positioning point sequence. , That is, make the discriminator's judgment of the sample positioning point sequence as close to 1 as possible. In some embodiments, the training module 450 may update the parameters of the generator in multiple rounds. The number of cyclic updates can be the system default value, or it can be adjusted according to different situations.

In some embodiments, the training module 450 may obtain multiple historical orders, and use relevant data of the multiple historical orders to train the initial model to obtain an estimated arrival time model. Each of the multiple historical orders may include a historical starting point, a historical ending point, a historical driving route, a historical positioning point sequence, a historical departure time, a historical arrival time, and the like. Taking a specific historical order as an example, the training module 450 may use the historical positioning point sequence and the historical arrival time of the historical order as a sample pair. Correspondingly, the training module 450 may use multiple sample pairs corresponding to multiple historical orders to perform model training. For example, the training module 450 may take multiple historical positioning point sequences of multiple historical orders as input, and use the corresponding historical arrival time as a label to train the initial model. After obtaining multiple estimated arrival times of multiple historical orders output by the initial model, the training module 450 can determine multiple historical arrival times (that is, the actual arrival time of historical orders) and multiple estimated arrival times (that is, the initial model determines The estimated time of arrival), and then reversely adjust the model parameters of the initial model. Then continue to train the initial model with the adjusted parameters. After multiple parameter adjustments, when the difference between the multiple historical arrival times and the multiple estimated arrival times of multiple historical orders meets the requirements (for example, the difference is less than the preset value), the training is stopped, and accordingly, The model training is complete.

The transmission module 460 may be used to transmit the estimated time of arrival. The transmission module 460 may send the estimated time of arrival to the terminal 120 via the network 140.

In some embodiments, two or more modules in the processing device 110 may be combined into a single module, and any of the modules may be divided into two or more units. For example, the acquisition module 410 and the transmission module 460 may be combined into a single module for acquiring service requests and sending estimated arrival time. For another example, the training module 450 can be integrated into the processing module 430. Further, for example, the processing device 110 may include a storage module (not shown in FIG. 4), which may be configured to store various data involved in the execution of the processing device (for example, service requests, estimated driving paths, estimated positioning points). Sequence, estimated time of arrival).

It should be understood that the system and its modules shown in FIG. 2 can be implemented in various ways. For example, in some embodiments, the system and its modules may be implemented by hardware, software, or a combination of software and hardware. Among them, the hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated design hardware. Those skilled in the art can understand that the above-mentioned methods and systems can be implemented using computer-executable instructions and/or included in processor control codes, for example on a carrier medium such as a disk, CD or DVD-ROM, such as a read-only memory (firmware Such codes are provided on a programmable memory or a data carrier such as an optical or electronic signal carrier. The system and its modules of this application can not only be implemented by hardware circuits 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, etc. It may also be implemented by software executed by various types of processors, or may be implemented by a combination of the above-mentioned hardware circuit and software (for example, firmware).

Fig. 5 is a flowchart of an exemplary process for determining an estimated arrival time according to some embodiments of the present application. In some embodiments, the process 500 may be executed by a processing device (for example, the processing device 110 shown in FIG. 1). For example, the process 500 may be stored in a storage device (for example, the storage device 130 or a storage unit of a processing device) in the form of a program or instruction. When the processor 210 or the module shown in FIG. 4 executes the program or instruction, the process may be implemented. 500. In some embodiments, the process 500 may utilize one or more additional operations not described below, and/or not be completed by one or more operations discussed below. In addition, the order of operations shown in FIG. 5 is not restrictive.

In step 501, the processing device 110 (for example, the obtaining module 410) may obtain a service request.

In some embodiments, the processing device 110 may obtain a service request from the terminal 120. For example, a user (for example, a passenger) may initiate a service request through the terminal 120 and send the service request to the processing device 110 through the network 140. In some embodiments, the processing device 110 may obtain the service request from the storage device 130 or other third-party devices.

In some embodiments, the service request may include a transportation service request, for example, a taxi service request, a navigation service request, a meal delivery service request, and so on. In some embodiments, the service request may be a real-time service request or an appointment service request. In some embodiments, "real time" or "reservation" can be defined by a preset time threshold. For example, if the user wants to receive the service immediately or at a time within a preset time threshold from the current moment, the service request can be regarded as a real-time service request. If the user wants to receive the service at a time outside the preset time threshold from the current moment, the service request can be regarded as a reservation service request. The preset time threshold can be the system default value, or it can be adjusted under different circumstances. For example, the preset time threshold may be 5 minutes, 10 minutes, 20 minutes, and so on. For another example, different preset time thresholds can be set for different cities, different regions, and different time periods.

In some embodiments, the service request may include at least a starting point (for example, a passenger's boarding point) and an ending point (for example, a passenger's getting off point). In some embodiments, the service request may also include the number of the service request, the information of the passenger who initiated the service request, the estimated price of the service request, and time information related to the service request (e.g., service request initiation time, service start time ( That is, the time when the user wants to receive the service), etc.

In step 503, the processing device 110 (for example, the determining module 420) may determine the estimated driving path of the service request based on the starting point and the ending point. In this article, the estimated travel path can refer to a drivable path connecting the starting point and the end point.

In some embodiments, the processing device 110 may determine the road network data related to the service request based on the start point and the end point, and determine the estimated travel path of the service request based on the road network data related to the service request. In some embodiments, the processing device 110 may obtain road network data from the storage device 130, a map service provider, and/or other third-party devices. In some embodiments, the road network data may be road network data updated at preset time intervals (for example, every day, every week), or road network data updated in real time.

In this article, road network data may refer to data describing road conditions in a certain area, which may include multiple links, multiple nodes connecting multiple links, link information of multiple links, and the like. In some embodiments, an actual road may correspond to one or more road segments in the road network data. The node can correspond to the intersection between the actual road and the road or the starting point or end of the actual road. Link information can be used to describe the relevant information of the link, such as link name, link number, link location, link level (for example, highway, urban road, etc.), link speed limit level, link length, link width, link real-time traffic Speed, the degree of congestion of the road section, the number of traffic light sections (for example, the number of left turns on traffic light sections, the number of right turns on traffic light sections, the number of straight traffic such as traffic sections), the number of non-traffic light sections (for example, the number of left turns on non-traffic light sections, the number of non-traffic light sections) The number of right turns, the number of straight road sections other than red and green), etc.

In some embodiments, the road network data related to the service request may be road network data of a preset area including at least a starting point and an ending point. For example, the road network data related to the service request may be road network data in a circular area with the diameter of the connection line between the start point and the end point. For another example, the road network data can be divided by regions (for example, administrative regions). Assuming that both the start point and the end point are located in the region A, the road network data related to the service request can be the road network data of the region A. For another example, assuming that the starting point is located in area A and the end point is located in area B, the road network data related to the service request may include area A, area B, and road networks connecting one or more areas between area A and area B. data.

In some embodiments, after obtaining the road network data related to the service request, the processing device 110 may use a path planning algorithm to determine the estimated driving path of the service request based on the starting point, the end point, and the road network data related to the service request. Exemplary path planning algorithms may include, but are not limited to, breadth first algorithm, Dijkstra algorithm, A* algorithm, LPA* algorithm, D* path search algorithm, D*Lite algorithm, Rapidly exploring random tree (RRT), Random road signs, etc. or any combination thereof. Taking the Dijkstra algorithm as an example, the processing device 110 may start from the starting point and start calculating the length of the path to the end point along the road network. After traversing all the paths, the shortest path can be selected as the estimated driving path.

In some embodiments, the estimated travel path may include multiple road segments and traffic conditions of multiple road segments. As mentioned above, the traffic condition may include the speed limit level of the road section, the length of the road section, the width of the road section, the real-time traffic speed of the road section, the degree of congestion of the road section, the number of traffic light sections, the number of non-traffic light sections, and so on.

In step 505, the processing device 110 (for example, the processing module 430) may obtain an estimated positioning point sequence based on the preset driving path.

In some embodiments, the estimated anchor point sequence may include a series of virtual anchor points between the starting point and the end point (or can be understood as a virtual track obtained by connecting these virtual anchor points). For example, the sequence of estimated positioning points may be a series of virtual positioning points roughly along the preset driving path. In some embodiments, the processing device 110 may use the positioning point sequence estimation model to process the estimated driving path to obtain the estimated positioning point sequence. Specifically, the processing device 110 may input the estimated driving path into the trained positioning point sequence estimation model, and determine the estimated positioning point sequence based on the output of the positioning point sequence estimation model.

In some embodiments, the positioning point sequence estimation model may include a neural network model. In some embodiments, the positioning point sequence estimation model may include a Generative Adversarial Network (GAN). The generative confrontation network can include generators and discriminators. The generator may generate virtual data (for example, a virtual positioning point sequence) based on real data (for example, a real historical driving route and/or a real historical positioning point sequence corresponding to a real historical driving route). The discriminator can determine the authenticity of the virtual data generated by the generator (for example, the probability that the virtual data is close to the real data (which may be referred to as the "authenticity probability")). After the generative adversarial network training is completed, the generator can generate virtual data that is highly similar to the real data and the discriminator cannot distinguish between the two (that is, the discriminator considers the virtual data to be infinitely close to the real data).

In some embodiments, during the training process of the generative confrontation network, the generator and the discriminator can each improve their own generation ability and discrimination ability through game-based learning. For example, the generator keeps learning to make the generated virtual positioning point sequence as close as possible to the real historical positioning point sequence (or real historical driving path), and the discriminator continuously improves the discrimination ability to distinguish the virtual positioning point sequence generated by the generator as much as possible. The positioning point sequence and the real historical positioning point sequence (or the real historical driving path) are continuously optimized to improve the generation and discrimination capabilities. For the description of the training of the generative confrontation network, please refer to the Figure 6 part of this application, which will not be repeated here.

In some embodiments, the processing device 110 may use the trained generative countermeasure network to obtain an estimated positioning point sequence that is highly similar to the estimated driving path. Specifically, the processing device 110 may input the estimated driving path and/or its related feature information into the generator, and the generator may generate a corresponding estimated anchor point sequence, and the discriminator considers that the authenticity probability of the estimated anchor point sequence satisfies Requirement, that is, the discriminator cannot determine the true or false of the estimated positioning point sequence.

In some embodiments, different generative confrontation networks can be trained for different requirements. For example, areas can be classified according to traffic conditions, for example, high-traffic areas, medium-traffic areas, and low-traffic areas. Correspondingly, different generative confrontation networks can be trained for different types of regions. For another example, different generative adversarial networks can be trained for different periods of the day (for example, morning peak hours, idle periods, and evening peak periods). Correspondingly, in some embodiments, the processing device 110 may select a corresponding generative confrontation network based on related information of the service request (for example, the area where the service request is located, the departure time of the service request).

In some embodiments, after obtaining the estimated anchor point sequence, the processing device 110 may also process the estimated anchor point sequence. For example, the processing device 110 can filter out drift points, deviation points, and the like. For another example, the processing device 110 may also perform interpolation processing on adjacent positioning points in the estimated positioning point sequence to increase the number of positioning, so that the processed estimated positioning point sequence is more accurate.

In step 507, the processing device 110 (for example, the estimation module 440) may determine the estimated arrival time of the service request based on the estimated positioning point sequence.

In some embodiments, the processing device 110 may use the estimated time of arrival model to process the estimated positioning point sequence to determine the estimated time of arrival of the service request. Specifically, the processing device 110 may input the estimated positioning point sequence into the estimated time of arrival model, and determine the estimated time of arrival based on the output of the estimated time of arrival model. In some embodiments, the estimated time of arrival model may include a deep learning model. Exemplary deep learning models may include, but are not limited to, deep belief network model, VGG (Visual Geometry Group Network), OverFeat, RNN (Recurrent Neural Network), LSTM (Long Short Term Memory), GUR (Gated Recurrent Unit), R- CNN (Region based Convolutional Neural Network), SPP-Net (Spatial Pyramid Pooling Network), Fast R-CNN (Fast Region based Convolutional Neural Network, Fast R-CNN (Faster Region based on Convolutional Neural Network, R-FCN (Region based Fully Network) Convolutional Network), DSOD (Deeply Supervised Object Detector), etc.

In some embodiments, the processing device 110 (for example, the training module 450) may obtain multiple historical orders, and use relevant data of the multiple historical orders to train the initial model to obtain the estimated arrival time model. In some embodiments, the terminal 120 may transmit data related to historical orders to a storage device (for example, the storage device 130) via the network 140. Correspondingly, the processing device 110 may obtain relevant data of historical orders from the storage device.

In some embodiments, the multiple historical orders may include service orders for a period of time in the past (for example, 6 hours, 12 hours, 1 day, 2 days, 7 days, 14 days, 1 month, 3 months, etc.). In some embodiments, the plurality of historical orders may include a certain number (eg, 10, 50, 100, 500, 1000, etc.) service orders that have been completed recently. In some embodiments, the multiple historical orders may be service orders for a certain area. For example, multiple historical orders may be historical orders with historical starting points or historical ending points in the same area. For another example, multiple historical orders may be historical orders with historical driving routes in the same area. For another example, multiple historical orders may be historical orders in which part of the historical driving route is in the same area. In some embodiments, the same area may include a certain city, a certain area, a certain street, a certain preset area, and so on.

In some embodiments, each of the multiple historical orders may include a historical starting point, a historical ending point, a historical driving route, a sequence of historical positioning points, a historical departure time, a historical arrival time, and the like. Taking a specific historical order as an example, the processing device 110 may use the historical positioning point sequence and the historical arrival time of the historical order as a sample pair. Correspondingly, the processing device 110 may use multiple sample pairs corresponding to multiple historical orders to perform model training. For example, the processing device 110 may take multiple historical positioning point sequences of multiple historical orders as input, and use the corresponding historical arrival time as a label to train the initial model. After obtaining multiple estimated arrival times of multiple historical orders output by the initial model, the processing device 110 may determine multiple historical arrival times (that is, the actual arrival time of historical orders) and multiple estimated arrival times (that is, the initial model determines The estimated time of arrival), and then reversely adjust the model parameters of the initial model. Then continue to train the initial model with the adjusted parameters. After multiple parameter adjustments, when the difference between the multiple historical arrival times and the multiple estimated arrival times of multiple historical orders meets the requirements (for example, the difference is less than the preset value), the training is stopped, and accordingly, The model training is complete.

In some embodiments, after the estimated arrival time is determined, the processing device 110 (for example, the transmission module 460) may send the estimated arrival time to the terminal 120 via the network 140. After receiving the estimated time of arrival, the terminal 120 may display it. For example, the terminal 120 may display the estimated arrival time through the display unit 320 shown in FIG. 3.

The method for determining the estimated time of arrival disclosed in this application uses a trained generative adversarial network to process service requests, determines the estimated positioning point sequence of the service request, and determines the estimated time of arrival of the service request based on the estimated positioning point sequence Estimated. In the training process of the generative confrontation network, the historical orders used can include the historical driving paths and historical positioning point sequences corresponding to different versions of the road network data. Therefore, the estimated positioning points obtained by the trained generative confrontation network are used The sequence confidence is high, and the estimated time of arrival determined therefrom is also more accurate. In addition, since the training data used in the training of the generative confrontation network is the historical driving path and/or historical positioning point sequence of historical orders, correspondingly, when determining the estimated arrival time of the current service request, it is only based on the current road network. The data determines the estimated driving path, and then determines the estimated positioning point sequence based on the trained generative confrontation network. Therefore, there is no need to obtain various historical versions of road network data, which can reduce the amount of calculation and reduce system overhead.

It should be noted that the foregoing description of the process 500 is only for example and description, and does not limit the scope of application of the present application. For those skilled in the art, various modifications and changes can be made to the process 500 under the guidance of this application. However, these amendments and changes are still within the scope of this application.

Fig. 6 is a flowchart of an exemplary process for determining an positioning point sequence estimation model according to some embodiments of the present application. In some embodiments, the process 600 may be executed by a processing device (for example, the training module 450 shown in FIG. 4). For example, the process 600 may be stored in a storage device (for example, the storage device 130 or a storage unit of a processing device) in the form of a program or instruction. When the processor 210 or the module shown in FIG. 4 executes the program or instruction, the process may be implemented. 600. In some embodiments, the process 600 may utilize one or more additional operations not described below, and/or not be completed by one or more operations discussed below. In addition, the order of operations shown in FIG. 6 is not restrictive.

In step 601, the processing device 110 (for example, the training module 450) may obtain multiple historical orders. As described in conjunction with step 507, the processing device 110 may obtain data related to multiple historical orders from the storage device.

In some embodiments, multiple historical orders may correspond to multiple historical driving paths and multiple historical positioning point sequences (ie, real historical positioning point sequences). Taking a specific historical order as an example, during the execution of the historical order, the user terminal (for example, the terminal 120) can obtain the positioning point through a built-in sensor (for example, a positioning device). During the execution of the entire historical order, the sampling of positioning points can be real-time or interval. For example, the sampling interval may be 0.5 seconds. After the historical order is completed, the user terminal (for example, the terminal 120) can obtain a series of positioning points (referred to as the "historical positioning point sequence" corresponding to the historical order). Correspondingly, the path obtained by connecting these positioning points can be called a historical driving path.

In some embodiments, each of the multiple historical orders may also include a historical starting point, a historical ending point, a historical departure time, a historical arrival time, and the like.

In step 603, the processing device 110 (for example, the training module 450) may determine a generative confrontation network through at least one iteration based on multiple historical orders.

As an example, in one iteration, the processing device 110 may use the generator in this iteration to determine multiple sample positioning point sequences corresponding to multiple historical driving paths in multiple historical orders. Subsequently, the processing device 110 may fix the generator and optimize the discriminator in this iteration based on the multiple sample positioning point sequences and the multiple historical positioning point sequences. For example, the processing device 110 may assign a label to each historical anchor point sequence, for example, the label is 1, and it is recorded as true. At the same time, the processing device 110 may assign a label to each sample positioning point sequence, for example, the label is 0 and it is recorded as false. The processing device 110 may use multiple historical anchor point sequences and multiple sample anchor point sequences as the input of the discriminator in this iteration, and the discriminator may output classification results for multiple historical anchor point sequences and multiple sample anchor point sequences (That is, the authenticity determination). For example, for each anchor point sequence (ie, historical anchor point sequence or sample anchor point sequence), the discriminator can output a value between 0-1, which represents the authenticity probability of the anchor point sequence. The larger the value, the greater the probability of authenticity, indicating that the anchor sequence is closer to the real anchor sequence. Further, the processing device 110 can update the parameters of the discriminator in this iteration based on the difference between the output value of the discriminator in this iteration and the corresponding label, so that it can more accurately distinguish the input data (that is, multiple The authenticity of a sequence of historical anchor points and a sequence of multiple sample anchor points). In some embodiments, the processing device 110 may update the parameters of the discriminator in multiple rounds. The number of cyclic updates can be the system default value, or it can be adjusted according to different situations.

After completing the optimization of the discriminator in this iteration, the processing device 110 may fix the discriminator and optimize the generator based at least on the parameters of the optimized discriminator. At this time, the optimized discriminator can still distinguish between the sample anchor point sequence and the historical anchor point sequence to a certain extent (that is, it can still distinguish between true data and fake data). Correspondingly, the processing device 110 may optimize the generator to promote the sequence of sample positioning points generated by it to be closer to the real historical positioning point sequence. In some embodiments, the processing device 110 may update the parameters of the generator in multiple rounds. The number of cyclic updates can be the system default value, or it can be adjusted according to different situations.

For other descriptions of the training of the generative confrontation network, please refer to other parts of this application (for example, FIG. 7 and its description), which will not be repeated here.

It should be noted that the foregoing description of the process 600 is only for example and description, and does not limit the scope of application of the present application. For those skilled in the art, various modifications and changes can be made to the process 600 under the guidance of this application. However, these amendments and changes are still within the scope of this application.

Fig. 7 is a flowchart of an exemplary iteration of training a generative confrontation network according to some embodiments of the present application. In some embodiments, the process 700 may be executed by a processing device (for example, the training module 450 shown in FIG. 4). For example, the process 700 may be stored in a storage device (for example, the storage device 130 or the storage unit of the processing device) in the form of a program or instruction. When the processor 210 or the module shown in FIG. 4 executes the program or instruction, the process may be implemented. 700. In some embodiments, the process 700 may utilize one or more additional operations not described below, and/or not be completed by one or more operations discussed below. In addition, the order of operations shown in FIG. 7 is not restrictive.

In step 701, the processing device 110 (for example, the training module 450) may use the generator in the current iteration to determine multiple sample positioning point sequences corresponding to multiple historical driving paths.

In some embodiments, the current iteration may be one of at least one iteration (for example, the first iteration or an intermediate iteration). Correspondingly, the generator in the current iteration can be the initial generator or the optimized generator obtained after several parameter updates. In this application, the "generator in the current iteration" may also be referred to as the "current generator".

In some embodiments, the processing device 110 may obtain multiple noise samples based on multiple historical driving paths. In some embodiments, the processing device 110 may collect multiple noise samples from prior distributed noise (eg, Gaussian noise distribution). Further, the processing device 110 may sequentially input multiple noise samples into the current generator to obtain multiple sample positioning point sequences.

In step 703, the processing device 110 (for example, the training module 450) may fix the generator and optimize the discriminator in the current iteration based on multiple sample positioning point sequences and multiple historical positioning point sequences.

Similarly, the discriminator in the current iteration can be the initial discriminator or an optimized discriminator obtained after several parameter updates. In this application, the "discriminator in the current iteration" may also be referred to as the "current discriminator".

In some embodiments, the processing device 110 may determine the classification results of multiple sample positioning point sequences and multiple historical positioning point sequences, and determine the value of the first loss function of the current discriminator based at least on the classification results. Specifically, the processing device 110 may assign a label to each historical anchor point sequence, for example, the label is 1, and it is recorded as true. At the same time, the processing device 110 may assign a label to each sample positioning point sequence, for example, the label is 0 and it is recorded as false. The processing device 110 may use multiple historical anchor point sequences and multiple sample anchor point sequences as the input of the current discriminator, and the current discriminator may output classification results for multiple historical anchor point sequences and multiple sample anchor point sequences (that is, real Sex determination). For example, for each anchor point sequence (ie, historical anchor point sequence or sample anchor point sequence), the current discriminator can output a value between 0-1, which represents the authenticity probability of the anchor point sequence. The larger the value, the greater the probability of authenticity, indicating that the anchor sequence is closer to the real anchor sequence. Subsequently, the processing device 110 may determine the value of the first loss function of the current discriminator based on the difference between the output value of the current discriminator and the corresponding label. In some embodiments, the first loss function may include a mean square error loss function, an exponential loss function, a log-likelihood loss function, a cross entropy loss function, a least square loss function, and the like.

Further, the processing device 110 may optimize the current discriminator based on the value of the first loss function. In the generative confrontation network, the optimization goal of the discriminator is to make it as correct as possible to distinguish between real data (for example, a sequence of historical anchor points) and fake data (for example, a sequence of sample anchor points). In other words, it is necessary to make the current discriminator's judgment of the historical positioning point sequence as close to 1 as possible, and the judgment of the sample positioning point sequence as close to 0 as possible. Specifically, the processing device 110 may reversely adjust the parameters of the current discriminator to optimize according to the value of the first loss function, so that the optimized current discriminator's discrimination for the historical positioning point sequence is as close to 1 as possible for the sample positioning point The sequence discrimination is as close to 0 as possible. In some embodiments, the processing device 110 may update the parameters of the discriminator in multiple rounds. The number of cyclic updates can be the system default value, or it can be adjusted according to different situations.

In step 705, the processing device 110 (for example, the training module 450) may fix the optimized discriminator and optimize the generator based at least on the parameters of the optimized discriminator.

In some embodiments, the processing device 110 may determine the value of the second loss function of the generator based at least on the parameters of the optimized discriminator, multiple sample positioning point sequences, and multiple historical positioning point sequences. Specifically, the processing device 110 may determine the current generator based on the classification result (ie, authenticity determination) of the multiple sample positioning point sequences by the optimized discriminator and the difference between the multiple sample positioning point sequences and the multiple historical positioning point sequences The value of the second loss function. In some embodiments, the second loss function may include a mean square error loss function, an exponential loss function, a log-likelihood loss function, a cross entropy loss function, a least square loss function, and the like.

Further, the processing device 110 may optimize the current generator based on the value of the second loss function. In the generative confrontation network, the optimization goal of the generator is to make the generated sample positioning point sequence as close as possible to the real historical positioning point sequence. Therefore, the value of the second loss function needs to be minimized. Specifically, the processing device 110 may reversely adjust the parameters of the current generator for optimization according to the value of the second loss function, so that the sample positioning point sequence generated by the optimized generator is as close as possible to the real historical positioning point sequence. , That is, make the discriminator's judgment of the sample positioning point sequence as close to 1 as possible. In some embodiments, the processing device 110 may update the parameters of the generator in multiple rounds. The number of cyclic updates can be the system default value, or it can be adjusted according to different situations.

It should be noted that the foregoing description of the process 700 is only for example and description, and does not limit the scope of application of the present application. For those skilled in the art, various modifications and changes can be made to the process 700 under the guidance of this application. However, these amendments and changes are still within the scope of this application.

Fig. 8 is a block diagram of an exemplary terminal according to some embodiments of the present application. As shown in FIG. 8, the terminal 120 may include an interaction module 810, a transmission module 820, and a communication module 830.

The interaction module 810 can obtain a service request. In some embodiments, users (for example, passengers) can input service requests through different input methods. Exemplary input methods include, but are not limited to, text input (for example, handwriting input, typing input), selection input, voice input, scan mark input, etc., or any combination thereof. In some embodiments, the terminal 120 may display the information (for example, the start point and/or the end point) input by the user in any suitable content form (for example, text, image, video, audio, graphics, etc.). In some embodiments, the interaction module 810 may present the information input by the user based on time-related standards, service cost-related standards, distance-related standards, and the like. For example, the information input by the user may be presented through the nearest departure point, the best pick-up point, and the destination among one or more options.

The transmission module 830 may send a service request to the server. The transmission module 830 may send the service request to the server (for example, the processing device 110) through the network 140. In some embodiments, the processing device 110 may determine the estimated travel path of the service request based on the starting point and the ending point. Subsequently, the processing device 110 may obtain an estimated positioning point sequence based on the preset driving path. Further, the processing device 110 may determine the estimated arrival time of the service request based on the estimated positioning point sequence. In some embodiments, the foregoing operations may also be implemented by the terminal 120.

The communication module 830 may receive the estimated arrival time corresponding to the service request sent by the server. In some embodiments, it may be sent and/or via any suitable communication protocol (for example, Hypertext Transfer Protocol (HTTP), Address Resolution Protocol (ARP), Dynamic Host Configuration Protocol (DHCP), File Transfer Protocol (FTP), etc.) Or receive the estimated time of arrival. In some embodiments, after receiving the estimated time of arrival, the terminal 120 may display the estimated time of arrival in a variety of ways (for example, text, image, audio, video, etc.).

In some embodiments, two or more modules in the terminal 120 may be combined into a single module, and any of the modules may be divided into two or more units. For example, the transmission module 820 and the communication module 830 can be combined into a single module for sending service requests and receiving estimated arrival time. For another example, the terminal 120 may include a storage module (not shown in FIG. 8), which may be configured to store various data (for example, service request, estimated time of arrival) involved in the execution of the terminal.

It should be understood that the system and its modules shown in FIG. 8 can be implemented in various ways. For example, in some embodiments, the system and its modules may be implemented by hardware, software, or a combination of software and hardware. Among them, the hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated design hardware. Those skilled in the art can understand that the above-mentioned methods and systems can be implemented using computer-executable instructions and/or included in processor control codes, for example on a carrier medium such as a disk, CD or DVD-ROM, such as a read-only memory (firmware Such codes are provided on a programmable memory or a data carrier such as an optical or electronic signal carrier. The system and its modules of this application can not only be implemented by hardware circuits 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, etc. It may also be implemented by software executed by various types of processors, or may be implemented by a combination of the above-mentioned hardware circuit and software (for example, firmware).

Fig. 9 is a flowchart of an exemplary process for determining an estimated arrival time according to some embodiments of the present application. In some embodiments, the process 500 may be executed by a mobile device (for example, the terminal 120 shown in FIG. 1). For example, the process 900 may be stored in a storage device (for example, the storage device 130 or a storage unit of a mobile device) in the form of a program or instruction. When the processor 340 or the module shown in FIG. 8 executes the program or instruction, the process may be implemented. 900. In some embodiments, the process 900 may utilize one or more additional operations not described below, and/or not be completed by one or more operations discussed below. In addition, the order of operations shown in FIG. 9 is not restrictive.

In step 901, the terminal 120 (for example, the interaction module 810) may obtain a service request.

In some embodiments, users (for example, passengers) can input service requests through different input methods. Exemplary input methods include, but are not limited to, text input (for example, handwriting input, typing input), selection input, voice input, scan mark input, etc., or any combination thereof. In some embodiments, the terminal 120 may display the information (for example, the start point and/or the end point) input by the user in any suitable content form (for example, text, image, video, audio, graphics, etc.). In some embodiments, the terminal 120 may present information input by the user based on time-related standards, service cost-related standards, distance-related standards, and the like. For example, the information input by the user may be presented through the nearest departure point, the best pick-up point, and the destination among one or more options.

In some embodiments, the service request may include at least a start point and an end point. The user can input the start point and/or end point by indicating (for example, by clicking, dragging, etc.) on the map displayed on the terminal 120. In some embodiments, the terminal 120 may also obtain images, audio, or video of the surrounding environment, and determine the starting point and/or the related information of the ending point based on the image, audio, or video. For more description of the service request, see step 501, which will not be repeated here.

In step 903, the terminal 120 (for example, the transmission module 820) may send a service request to the server.

In some embodiments, the terminal 120 may send the service request to the server (for example, the processing device 110) through the network 140. In some embodiments, the processing device 110 may determine the estimated travel path of the service request based on the start point and the end point. Subsequently, the processing device 110 may obtain an estimated positioning point sequence based on the preset driving path. Further, the processing device 110 may determine the estimated arrival time of the service request based on the estimated positioning point sequence. For more description, see Figures 5-7 and their descriptions, which will not be repeated here. In some embodiments, the foregoing operations may also be implemented by the terminal 120.

In step 905, the terminal 120 (for example, the communication module 830) may receive the estimated time of arrival corresponding to the service request sent by the server.

In some embodiments, it may be sent and/or via any suitable communication protocol (for example, Hypertext Transfer Protocol (HTTP), Address Resolution Protocol (ARP), Dynamic Host Configuration Protocol (DHCP), File Transfer Protocol (FTP), etc.) Or receive the estimated time of arrival. In some embodiments, after receiving the estimated time of arrival, the terminal 120 may display the estimated time of arrival in a variety of ways (for example, text, image, audio, video, etc.).

It should be noted that the foregoing description of the process 900 is only for example and description, and does not limit the scope of application of the present application. For those skilled in the art, various modifications and changes can be made to the process 900 under the guidance of this application. However, these amendments and changes are still within the scope of this application.

Fig. 10 is a schematic diagram of interaction between a processing device and a terminal according to some embodiments of the present application. As shown in FIG. 10, after obtaining the service request, the terminal 120 (for example, the transmission module 820) may send the service request to the processing device 110 (for example, the obtaining module 410). After receiving the service request, the processing device 110 may determine the estimated time of arrival of the service request based on methods in other locations of this application. After that, the processing device 110 (for example, the transmission module 460) may send the estimated arrival time to the terminal 120 (for example, the communication module 830). After receiving the estimated time of arrival, the terminal 120 may display the estimated time of arrival in various forms.

The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only an example, and does not constitute a limitation to the application. Although it is not explicitly stated here, those skilled in the art may make various modifications, improvements and amendments to this application. Such modifications, improvements, and corrections are suggested in this application, so such modifications, improvements, and corrections still belong to the spirit and scope of the exemplary embodiments of this application.

At the same time, this application uses specific words to describe the embodiments of this application. For example, "one embodiment", "an embodiment", and/or "some embodiments" mean a certain feature, structure, or characteristic related to at least one embodiment of the present application. Therefore, it should be emphasized and noted that “one embodiment” or “one embodiment” or “an alternative embodiment” mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. . In addition, some features, structures, or characteristics in one or more embodiments of the present application can be appropriately combined.

In addition, those skilled in the art can understand that various aspects of this application can be explained and described through a number of patentable categories or situations, including any new and useful process, machine, product, or combination of substances, or a combination of them. Any new and useful improvements. Correspondingly, various aspects of the present application can be completely executed by hardware, can be completely executed by software (including firmware, resident software, microcode, etc.), or can be executed by a combination of hardware and software. The above hardware or software can be called "data block", "module", "engine", "unit", "component" or "system". In addition, various aspects of this application may be embodied as a computer product located in one or more computer-readable media, and the product includes computer-readable program codes.

The computer storage medium may contain a propagated data signal containing a computer program code, for example on a baseband or as part of a carrier wave. The propagated signal may have multiple manifestations, including electromagnetic forms, optical forms, etc., or suitable combinations. The computer storage medium may be any computer readable medium other than the computer readable storage medium, and the medium may be connected to an instruction execution system, device, or device to realize communication, propagation, or transmission of the program for use. The program code located on the computer storage medium can be transmitted through any suitable medium, including radio, cable, fiber optic cable, RF, or similar medium, or any combination of the above medium.

The computer program codes required for the operation of each part of this application can be written in any one or more programming languages, including object-oriented programming languages such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python Etc., conventional programming languages such as C language, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, dynamic programming languages such as Python, Ruby and Groovy, or other programming languages. The program code can be run entirely on the user's computer, or run as an independent software package on the user's computer, or partly run on the user's computer and partly run on a remote computer, or run entirely on the remote computer or server. In the latter case, the remote computer can be connected to the user's computer through any network form, such as a local area network (LAN) or a wide area network (WAN), or connected to an external computer (for example, via the Internet), or in a cloud computing environment, or as a service Use software as a service (SaaS).

In addition, unless explicitly stated in the claims, the order of processing elements and sequences, the use of numbers and letters, or the use of other names in this application are not used to limit the order of the procedures and methods of this application. Although the foregoing disclosure uses various examples to discuss some embodiments of the invention that are currently considered useful, it should be understood that such details are only for illustrative purposes, and the appended claims are not limited to the disclosed embodiments. On the contrary, the rights are The requirements are intended to cover all modifications and equivalent combinations that conform to the essence and scope of the embodiments of the present application. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

For the same reason, it should be noted that, in order to simplify the expressions disclosed in this application and thus help the understanding of one or more embodiments of the invention, in the foregoing description of the embodiments of this application, multiple features are sometimes combined into one embodiment. In the drawings or its description. However, this method of disclosure does not mean that the subject of the application requires more features than those mentioned in the claims. In fact, the features of the embodiment are less than all the features of the single embodiment disclosed above.

In some embodiments, numbers describing the number of ingredients and attributes are used. It should be understood that such numbers used in the description of the embodiments use the modifier "about", "approximately" or "substantially" in some examples. Retouch. Unless otherwise stated, "approximately", "approximately" or "substantially" indicates that the number is allowed to vary by ±20%. Correspondingly, in some embodiments, the numerical parameters used in the description and claims are approximate values, and the approximate values can be changed according to the required characteristics of individual embodiments. In some embodiments, the numerical parameter should consider the prescribed effective digits and adopt the method of general digit retention. Although the numerical ranges and parameters used to confirm the breadth of the ranges in some embodiments of the present application are approximate values, in specific embodiments, the setting of such numerical values is as accurate as possible within the feasible range.

For each patent, patent application, patent application publication and other materials cited in this application, such as articles, books, specifications, publications, documents, etc., the entire contents are hereby incorporated into this application as a reference. The application history documents that are inconsistent or conflicting with the content of this application are excluded, and documents that restrict the broadest scope of the claims of this application (currently or later attached to this application) are also excluded. It should be noted that if there is any inconsistency or conflict between the description, definition, and/or term usage in the attached materials of this application and the content described in this application, the description, definition and/or term usage of this application shall prevail .

Finally, it should be understood that the embodiments described in this application are only used to illustrate the principles of the embodiments of this application. Other variations may also fall within the scope of this application. Therefore, as an example and not a limitation, the alternative configuration of the embodiment of the present application can be regarded as consistent with the teaching of the present application. Accordingly, the embodiments of the present application are not limited to the embodiments explicitly introduced and described in the present application.

Claims

A system including:

At least one storage medium, the storage medium including an instruction for determining an estimated time of arrival;

At least one processor, the at least one processor is in communication with the at least one storage medium, wherein, when the instruction is executed, the at least one processor is configured to:

Obtaining a service request, the service request including at least a starting point and an ending point;

Determining the estimated driving path of the service request based on the starting point and the ending point;

Obtaining an estimated positioning point sequence based on the estimated driving path;

Based on the estimated positioning point sequence, the estimated time of arrival of the service request is determined.
The system according to claim 1, wherein, in order to determine the estimated travel path, the processor is configured to:

Determine road network data related to the service request based on the start point and the end point;

Based on the starting point, the ending point, and the road network data, the estimated driving path is determined by using a path planning algorithm.
The system according to claim 1, wherein the estimated travel path includes multiple road segments and traffic conditions of multiple road segments.
The system according to claim 1, wherein, to obtain an estimated positioning point sequence based on the estimated driving path, the processor is configured to:

The estimated driving path is processed by using the positioning point sequence estimation model to obtain the estimated positioning point sequence.
The system according to claim 4, wherein the positioning point sequence estimation model includes a neural network model.
The system according to claim 4, wherein the positioning point sequence estimation model includes a generative countermeasure network, and the generative countermeasure network includes a generator and a discriminator.
The system according to claim 6, wherein, in order to obtain the positioning point sequence estimation model, the processor is configured to:

Acquiring multiple historical orders, the multiple historical orders corresponding to multiple historical driving paths and multiple historical positioning point sequences;

Based on the multiple historical orders, the generative confrontation network is determined through at least one iteration, wherein each of the at least one iteration includes:

Using the generator in the current iteration to determine multiple sample positioning point sequences corresponding to the multiple historical driving paths;

Fixing the generator and optimizing the discriminator in the current iteration based on the multiple sample positioning point sequences and the multiple historical positioning point sequences;

Fix the optimized discriminator and optimize the generator based on at least the parameters of the optimized discriminator.
The system according to claim 7, wherein, in order to optimize the discriminator, the processor is further configured to:

Determining the classification results of the multiple sample positioning point sequences and the multiple historical positioning point sequences;

Determine the value of the first loss function of the discriminator based at least on the classification result;

Based on the value of the first loss function, the discriminator is optimized.
The system according to claim 7, wherein, in order to optimize the generator, the processor is further configured to:

Determining the value of the second loss function of the generator based at least on the parameters of the optimized discriminator, the multiple sample positioning point sequences, and the multiple historical positioning point sequences;

Based on the value of the second loss function, the generator is optimized.
The system according to claim 1, wherein, to determine the estimated time of arrival of the service request based on the estimated positioning point sequence, the processor is configured to:

The estimated time of arrival model is used to process the estimated positioning point sequence to determine the estimated time of arrival of the service request.
A method for determining estimated time of arrival, wherein the method includes:

Obtaining a service request, the service request including at least a starting point and an ending point;

Determining the estimated driving path of the service request based on the starting point and the ending point;

Obtaining an estimated positioning point sequence based on the driving path;

Based on the estimated positioning point sequence, the estimated time of arrival of the service request is determined.
The method according to claim 11, wherein said determining said estimated driving path comprises:

Determine road network data related to the service request based on the start point and the end point;

Based on the starting point, the ending point, and the road network data, the estimated driving path is determined by using a path planning algorithm.
The method according to claim 11, wherein the estimated travel path includes multiple road sections and traffic conditions of multiple road sections.
The method according to claim 11, wherein the obtaining an estimated positioning point sequence based on the estimated driving path comprises:

The estimated driving path is processed by using the positioning point sequence estimation model to obtain the estimated positioning point sequence.
The method according to claim 14, wherein the positioning point sequence estimation model comprises a neural network model.
The method according to claim 14, wherein the positioning point sequence estimation model includes a generative confrontation network, and the generative confrontation network includes a generator and a discriminator.
The method according to claim 16, wherein said obtaining said positioning point sequence estimation model comprises:

Acquiring multiple historical orders, the multiple historical orders corresponding to multiple historical driving paths and multiple historical positioning point sequences;

Based on the multiple historical orders, the generative confrontation network is determined through at least one iteration, wherein each of the at least one iteration includes:

Using the generator in the current iteration to determine multiple sample positioning point sequences corresponding to the multiple historical driving paths;

Fixing the generator and optimizing the discriminator in the current iteration based on the multiple sample positioning point sequences and the multiple historical positioning point sequences;

Fix the optimized discriminator and optimize the generator based on at least the parameters of the optimized discriminator.
The method according to claim 17, wherein said optimizing said discriminator comprises:

Determining the value of the first loss function of the discriminator based at least on the plurality of sample positioning point sequences and the plurality of historical positioning point sequences;

Based on the value of the first loss function, the discriminator is optimized.
The method according to claim 17, wherein said optimizing said generator comprises:

Determining the value of the second loss function of the generator based at least on the parameters of the optimized discriminator, the multiple sample positioning point sequences, and the multiple historical positioning point sequences;

Based on the value of the second loss function, the generator is optimized.
The method according to claim 11, wherein the determining the estimated time of arrival of the service request based on the estimated positioning point sequence comprises:

The estimated time of arrival model is used to process the estimated positioning point sequence to determine the estimated time of arrival of the service request.
A computer-readable storage medium that stores computer instructions. After the computer reads the computer instructions in the storage medium, the computer executes the following method for determining the estimated time of arrival;

Obtaining a service request, the service request including at least a starting point and an ending point;

Determining the estimated driving path of the service request based on the starting point and the ending point;

Obtaining an estimated positioning point sequence based on the driving path;

Based on the estimated positioning point sequence, the estimated time of arrival of the service request is determined.