CN111860906A

CN111860906A - Method and system for determining estimated arrival time

Info

Publication number: CN111860906A
Application number: CN202010333432.XA
Authority: CN
Inventors: 傅昆; 王征
Original assignee: Beijing Didi Infinity Technology and Development Co Ltd
Current assignee: Beijing Didi Infinity Technology and Development Co Ltd
Priority date: 2020-04-24
Filing date: 2020-04-24
Publication date: 2020-10-30
Anticipated expiration: 2040-04-24

Abstract

The embodiment of the application discloses a method for determining estimated arrival time, which comprises the following steps: acquiring relevant data of a current order, wherein the relevant data of the current order at least comprises the following data: a departure time; obtaining a first feature vector of a first time period corresponding to the departure time based on the departure time of the current order; obtaining second feature vectors of a plurality of second time periods, wherein the second time periods are related to the first time periods; obtaining a target feature vector corresponding to the current order based on the first feature vector of the first time period and the second feature vectors of the plurality of second time periods; and obtaining the estimated arrival time of the current order at least based on the target characteristic vector.

Description

Method and system for determining estimated arrival time

Technical Field

The present application relates to the field of traffic technologies, and in particular, to a method and a system for determining a predicted arrival time.

Background

With the development of the network appointment car market, a car taxi taking platform brings convenience to the life of people, and Estimated Time of Arrival (ETA) is a very important technical index, is used for estimating the Time of arriving at a specified destination, and can describe the Time and cost spent by a user in traveling. When ETA is calculated, time is an important calculation characteristic, and due to the fact that data in adjacent time sections have similarity, the accuracy of the result of independent calculation is low, and ETA cannot be accurately estimated. Therefore, there is a need for a method and a system for determining an estimated arrival time to effectively estimate the arrival time of an order and improve the user experience.

Disclosure of Invention

One of the embodiments of the present application provides a method for determining an estimated arrival time, where the method includes: acquiring relevant data of a current order, wherein the relevant data of the current order at least comprises the following data: a departure time; obtaining a first feature vector of a first time period corresponding to the departure time based on the departure time of the current order; obtaining second feature vectors of a plurality of second time periods, wherein the second time periods are related to the first time periods; obtaining a target feature vector corresponding to the current order based on the first feature vector of the first time period and the second feature vectors of the plurality of second time periods; and obtaining the estimated arrival time of the current order at least based on the target characteristic vector.

In some embodiments, the obtaining, based on the departure time of the current order, a first feature vector of a first time period corresponding to the departure time includes: processing the preset time period according to a preset time period dividing method to obtain a plurality of candidate time periods; obtaining relevant data for each candidate time period, the relevant data at least comprising: the starting time of the candidate time period, the ending time of the candidate time period and the candidate feature vector corresponding to the candidate time period; determining a first time period corresponding to the current order from a plurality of candidate time periods based on the starting time and/or the ending time of the candidate time periods; and designating the candidate feature vector corresponding to the candidate time segment of the first time segment as the first feature vector of the first time segment.

In some embodiments, the obtaining the second feature vectors of the plurality of second time periods comprises: determining a plurality of second time periods from the plurality of candidate time periods based on the number of dimensions of the first feature vector and a preset number of dimensions; and appointing a candidate feature vector corresponding to the candidate time period as the second feature vector of the second time period. One of the embodiments of the present application provides an apparatus for determining an estimated time of arrival, including a processor, wherein the processor is configured to execute a method for determining an estimated time of arrival.

In some embodiments, the determining a plurality of second time periods from the plurality of candidate time periods comprises: determining a ratio of the dimension number of the first feature vector to the preset dimension number; selecting a plurality of third time periods including the first time period from the plurality of candidate time periods based on the ratio; designating the other time periods of the plurality of third time periods except the first time period as the plurality of second time periods.

In some embodiments, the obtaining the estimated arrival time of the current order based on at least the target feature vector of the preset dimensional quantity includes: obtaining the order characteristics of the current order; and processing the target characteristic vector and the order characteristics according to an arrival time prediction algorithm to obtain the estimated arrival time of the current order.

In some embodiments, the time of arrival prediction algorithm comprises a prediction model for predicting time of arrival; the pre-estimation model is a machine learning model and is obtained based on the following operations: obtaining a training set, wherein the training set comprises a plurality of sample pairs; and training an initial model by using the training set to obtain the pre-estimated model.

In some embodiments, the obtaining a training set comprises: acquiring related data of a historical order;

generating a sample pair based on the related data of the historical order and the arrival time of the historical order; wherein the related data of the historical order at least comprises: historical order features and feature vectors corresponding to the historical orders.

One of the embodiments of the present application provides a system for determining an estimated time of arrival, the system including: an obtaining module, configured to obtain relevant data of a current order, where the relevant data of the current order at least includes: a departure time; the first processing module is used for obtaining relevant data of a first time period corresponding to the departure time based on the departure time of the current order; the first processing module is further configured to obtain related data of a plurality of second time periods, where the second time periods are related to the first time period; the first processing module is further configured to obtain a time feature vector of a preset dimension quantity corresponding to the current order based on the relevant data of the first time period and the relevant data of the plurality of second time periods; and the second processing module is used for obtaining the estimated arrival time of the current order at least based on the time characteristic vector of the preset dimension quantity.

In some embodiments, the first processing module is configured to process the time feature vector according to a preset time period division method to obtain related data of a plurality of time periods, where the related data of each time period at least includes: time period data, a starting time of a time period, and an ending time of the time period, wherein each time period data comprises parameters of a plurality of dimensions; and determining a first time period corresponding to the current order based on the starting time of each time period and/or the ending time of each time period.

In some embodiments, the first processing module is further configured to process the time period data according to a preset dimension change method to obtain time period data with changed dimensions, where the time period data with changed dimensions includes parameters of multiple dimensions with changed dimensions.

In some embodiments, the first processing module is further configured to, when the ending time of the first time period is determined as the starting time of a second time period, determine the number of the second time periods according to the number of dimensions of the time periods and the number of dimensions of the preset time feature; and when the starting time of the first time period is determined as the ending time of one time period, determining the number of second time periods according to the dimension number of the time periods and the dimension number of the preset time characteristics.

In some embodiments, the second processing module is configured to process the relevant data of the current order according to a preset estimated arrival time method, and obtain an estimated arrival time of the current order; wherein the relevant data of the current order at least further comprises current order characteristics.

In some embodiments, the second processing module is further configured to process relevant data of the current order by using a preset estimated arrival time model; the estimated time of arrival model is obtained by the following method: obtaining a training set, wherein the training set comprises a plurality of sample pairs; and training the initial model by using the training set to obtain a pre-estimated time of arrival model.

In some embodiments, the second processing module is further configured to obtain data related to a historical order;

generating a sample pair based on the related data of the historical order and the arrival time of the historical order;

wherein the related data of the historical order at least comprises: historical order features and time feature vectors corresponding to the historical orders.

One of the embodiments of the present application provides an apparatus for determining an estimated time of arrival, including a processor configured to perform a method for determining an estimated time of arrival.

One embodiment of the present application provides a computer-readable storage medium, where the storage medium stores computer instructions, and after the computer reads the computer instructions in the storage medium, the computer executes a method for determining an estimated arrival time.

Drawings

The present application will be further explained by way of exemplary embodiments, which will be described in detail by way of the accompanying drawings. These embodiments are not intended to be limiting, and in these embodiments like numerals are used to indicate like structures, wherein:

FIG. 1 is a schematic diagram illustrating an application scenario of a system 100 for determining an estimated time of arrival according to some embodiments of the present application;

FIG. 2 is a block diagram of a system 200 for determining an estimated time of arrival according to some embodiments of the present application;

FIG. 3 is an exemplary flow chart of a method 300 of determining an estimated time of arrival according to some embodiments of the present application.

Detailed Description

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings used in the description of the embodiments will be briefly introduced below. It is obvious that the drawings in the following description are only examples or embodiments of the application, from which the application can also be applied to other similar scenarios without inventive effort for a person skilled in the art. Unless otherwise apparent from the context, or otherwise indicated, like reference numbers in the figures refer to the same structure or operation.

It should be understood that "system", "device", "unit" and/or "module" as used herein is a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, other words may be substituted by other expressions if they accomplish the same purpose.

As used in this application and the appended claims, the terms "a," "an," "the," and/or "the" are not intended to be inclusive in the singular, but rather are intended to be inclusive in the plural unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that steps and elements are included which are explicitly identified, that the steps and elements do not form an exclusive list, and that a method or apparatus may include other steps or elements.

Flow charts are used herein to illustrate operations performed by systems according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in the exact order in which they are performed. Rather, the various steps may be processed in reverse order or simultaneously. Also, other operations may be added to the flows, or one or more operations may be removed from the flows.

Embodiments of the present application may be applied to different transportation systems including, but not limited to, one or a combination of terrestrial, marine, aeronautical, aerospace, and the like. For example, taxis, special cars, tailplanes, buses, designated drives, trains, railcars, high-speed rails, ships, airplanes, hot air balloons, unmanned vehicles, receiving/sending couriers, and the like, employ managed and/or distributed transportation systems. The application scenarios of the different embodiments of the present application include, but are not limited to, one or a combination of several of a web page, a browser plug-in, a client, a customization system, an intra-enterprise analysis system, an artificial intelligence robot, and the like. It should be understood that the application scenarios of the system and method of the present application are merely examples or embodiments of the present application, and those skilled in the art can also apply the present application to other similar scenarios without inventive effort based on these figures. For example, other similar guided user parking systems.

The terms "passenger", "passenger end", "user terminal", "customer", "demander", "service demander", "consumer", "user demander" and the like are used interchangeably and refer to a party that needs or orders a service, either a person or a tool. Similarly, "driver," "provider," "service provider," "server," and the like, as described herein, are interchangeable and refer to an individual, tool, or other entity that provides a service or assists in providing a service. In addition, a "user" as described herein may be a party that needs or subscribes to a service, or a party that provides or assists in providing a service.

Fig. 1 is a schematic diagram illustrating an application scenario of a system 100 for determining a predicted arrival time according to some embodiments of the present application.

As shown in fig. 1, determining an estimated time of arrival system 100 may determine an estimated time of arrival for a journey. For example, the determine estimated time of arrival system 100 may determine an estimated time of arrival of the driver of the pickup at the passenger boarding point, and for example, the determine estimated time of arrival system 100 may determine an estimated time of arrival of the passenger from the departure point to the destination. The system 100 may be used to determine an estimated time of arrival for a service platform on the internet or other network. For example, the system 100 for determining estimated time of arrival may be an online service platform that provides services for transportation. In some embodiments, the system 100 for determining estimated time of arrival may be applied to taxi appointment services, such as taxi calls, express calls, special calls, mini-bus calls, car pool, bus service, driver employment and pickup services, and the like. In some embodiments, determining an estimated time of arrival system 100 may also be applied to designated drives, couriers, takeoffs, and the like. In other embodiments, the system 100 for determining estimated time of arrival may be applied to the fields of housekeeping services, travel (e.g., tourism) services, education (e.g., offline education) services, and the like. As shown in fig. 1, system 100 for determining an estimated time of arrival may include a processing device 110, one or more terminals 120, a storage device 130, a network 140, and an information source 150.

In some embodiments, processing device 110 may process data and/or information obtained from terminal 120, storage device 130, and/or information source 150. For example, the processing device 110 may obtain location/trajectory information for the plurality of terminals 120 and/or characteristic information of parties (e.g., drivers and passengers) associated with the trip. Processing device 110 may process the information and/or data obtained as described above to perform one or more functions described herein. In some embodiments, the processing device 110 may be a stand-alone server or a group of servers. The set of servers may be centralized or distributed (e.g., 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 material stored in the terminal 120, the storage device 130, and/or the information source 150 via 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 information and/or material stored therein. In some embodiments, the processing device 110 may execute on a cloud platform. For example, the cloud platform may include one or any combination of a private cloud, a public cloud, a hybrid cloud, a community cloud, a decentralized cloud, an internal cloud, and the like. In other embodiments, the processing device 110 may be one of the terminals 120 at the same time.

In some embodiments, processing device 110 may include one or more sub-processing devices (e.g., a single-core processor or a multi-core processor). By way of example only, 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 Processing Unit (PPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), a programmable logic circuit (PLD), a controller, a micro-controller unit, a Reduced Instruction Set Computer (RISC), a microprocessor, or the like, or any combination thereof.

In some embodiments, the terminal 120 may be a device with data acquisition, storage, and/or transmission capabilities, and may include any user or terminal that does not directly participate in a service, a service provider terminal, a service requester terminal, and/or a vehicle mounted terminal. The service provider may be an individual, tool, or other entity that provides the service. The service requester may be an individual, tool or other entity that needs to obtain or is receiving a service. For example, for a car-order-on-the-net service, the service provider may be a driver, a third-party platform, and the service requester may be a passenger or other person or device (e.g., an internet-of-things device) that receives similar services. In some embodiments, the terminal 120 may be used to collect various types of data, including but not limited to data related to services. The collected data may be real-time or various types of historical data such as past usage history of the user, etc. The data may be collected by the terminal 120 through its own sensor, may also collect data acquired by an external sensor, may also read data stored in its own memory, and may also read data stored in the storage device 150 through the network 140. In some embodiments, the sensor may include a pointing device, a sound sensor, an image sensor, a temperature and humidity sensor, a position sensor, a pressure sensor, a distance sensor, a velocity sensor, an acceleration sensor, a gravity sensor, a displacement sensor, a moment sensor, a gyroscope, or the like, or any combination thereof, or the like. In some embodiments, the terminal 120 may include one or a combination of desktop computer 120-1, laptop computer 120-2, in-vehicle device 120-3, mobile device 120-4, and/or the like. In some embodiments, mobile device 120-4 may include a smart home device, a wearable device, a smart mobile device, an augmented reality device, and the like, or a combination thereof. In some embodiments, the wearable device may include a smart bracelet, smart footwear, smart glasses, smart helmet, smart watch, smart clothing, smart backpack, smart accessory, or the like, or any combination thereof. In some embodiments, the smart mobile device may include a smartphone, a Personal Digital Assistant (PDA), a gaming device, a navigation device, a POS machine, or the like, or a combination thereof. In some embodiments, the in-vehicle device 120-3 may include an on-board computer, an automotive data recorder, an on-board human-computer interaction (HCI) system, a tachograph, an on-board television, and so forth. In some embodiments, the terminal 120 may be a device having a positioning technology for locating the position of the terminal 120. 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 notifications generated by the processing device 110 related to the estimated time of arrival. In some embodiments, multiple terminals may be connected to each other, and various types of data may be collected together and preprocessed by one or more terminals.

Storage device 130 may store data and/or instructions. In some embodiments, storage device 130 may store data/information obtained by terminal 120. The storage device 130 may also store historical transportation service data for historical events, such as order data for historical service orders for some events, service participant data, vehicle-related data, and the like, and trip data, and the like. In some embodiments, storage device 130 may store data and/or instructions for execution by, or used by, processing device 110 to perform the exemplary methods described in this application. In some embodiments, the storage device 130 may store various types of real-time or historical data of the user terminal, for example, historical records of the user related to historical services, such as historical ratings, and the like. In some embodiments, the storage device 130 may be part of the processing device 110 or the terminal 120. In some embodiments, storage 130 may include mass storage, removable storage, volatile read-write memory, read-only memory (ROM), and the like, or any combination thereof. Exemplary mass storage devices may include magnetic disks, optical disks, solid state disks, and the like. Exemplary removable memory may include flash drives, floppy disks, optical disks, memory cards, compact disks, magnetic tape, and the like. Exemplary volatile read-only memory can include Random Access Memory (RAM). Exemplary RAM may include Dynamic RAM (DRAM), double-data-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), Electrically Erasable Programmable ROM (EEPROM), compact disk ROM (CD-ROM), digital versatile disk ROM, and the like. In some embodiments, storage device 130 may be implemented on a cloud platform. By way of example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-tiered cloud, and the like, or any combination thereof. In some embodiments, some historical data may be stored uniformly on one cloud platform of the platform for access or update by multiple processing devices 110 or terminals 120 to ensure real-time and cross-platform usage of the data.

In some embodiments, storage device 130 may be connected to network 140 to communicate with one or more components (e.g., processing device 110, terminal 120, information source 150) in estimated time of arrival system 100. One or more components in estimated time of arrival system 100 may access data or instructions stored in storage 130 over network 140. In some embodiments, storage device 130 may be directly connected or in communication with one or more components (e.g., processing device 110, terminal 120, information source 150) in estimated time of arrival system 100. In some embodiments, the storage device 130 may be part of the processing device 110.

Network 140 may facilitate the exchange of information and/or data. In some embodiments, one or more components in system 100 (e.g., processing device 110, terminal 120, storage device 130, and information source 150) may send and/or receive information and/or data to/from other components in system 100 via network 140. For example, the processing device 110 may obtain data/information related to a transportation service from the terminal 120 and/or the information source 150 via the network 140. As another example, the terminal 120 may obtain the estimated time of arrival from the processing device 110 or the storage device 130 via the network 140. The estimated time of arrival may be displayed by the application software on the interface of the terminal 120. In some embodiments, the network 140 may be any form or combination of wired or wireless network. By way of example only, network 140 may include a cable network, a wireline network, a fiber optic network, a telecommunications network, an intranet, the Internet, a Local Area Network (LAN), a Wide Area Network (WAN), a Wireless Local Area Network (WLAN), a Metropolitan Area Network (MAN), a Wide Area Network (WAN), a Public Switched Telephone Network (PSTN), a Bluetooth network, a ZigBee network, a Near Field Communication (NFC) network, a Global System for Mobile communications (GSM) network, a Code Division Multiple Access (CDMA) network, a Time Division Multiple Access (TDMA) network, a General Packet Radio Service (GPRS) network, an enhanced data rates for GSM evolution (EDGE) network, a Wideband Code Division Multiple Access (WCDMA) network, a High Speed Downlink Packet Access (HSDPA) network, a Long Term Evolution (LTE) network, a User Datagram Protocol (UDP) network, a Transmission control protocol/Internet protocol (TCP/IP) network, a Short Message Service (SMS), A Wireless Application Protocol (WAP) network, an ultra-wideband (UWB) network, a mobile communication (1G, 2G, 3G, 4G, 5G) network, Wi-Fi, Li-Fi, narrowband Internet of things (NB-IoT), and the like, or any combination thereof. In some embodiments, the estimated time of arrival system 100 may include one or more network access points. For example, estimated time of arrival 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 estimated time of arrival system 100 may connect to network 140 to exchange data and/or information.

Information source 150 may be used to provide a source of information for system 100 to determine the estimated time of arrival. In some embodiments, the information source 150 may be used to provide information related to transportation services, such as weather conditions, traffic information, geographic information, legal information, news events, life information, life guide information, and the like, to the system 100 for determining the estimated time of arrival. In some embodiments, the information source 150 may also be other third party platforms that may provide credit records, such as credit records, for the service requester and/or the service provider. The information source 150 may be implemented in a single central server, multiple servers connected by communication links, or multiple personal devices. When the information source 150 is implemented in multiple personal devices, the personal devices may generate content (e.g., referred to as "user-generated content"), for example, by uploading text, voice, images, and video to a cloud server. The information source may be generated by a plurality of personal devices and a cloud server. The storage device 130, the processing device 110 and the terminal 120 may also be sources of information. For example, the speed and positioning information fed back by the terminal 120 in real time may be used as an information source to provide traffic condition information for other devices to obtain.

FIG. 2 is a block diagram of a system 200 for determining an estimated time of arrival according to some embodiments of the present application.

As shown in fig. 2, system 200 may include: an obtaining module 210, a first processing module 220, and a second processing module 230.

The obtaining module 210 may be configured to obtain relevant data of a current order, where the relevant data of the current order at least includes a departure time.

The first processing module 220 may be configured to obtain, based on a departure time of a current order, a first feature vector of a first time period corresponding to the departure time, and a second feature vector of a plurality of second time periods, where the second time periods are related to the first time periods. In some embodiments, the first processing module 220 may divide the preset time period according to a preset time period dividing method, obtain a plurality of candidate time periods and related data, and determine the first time period corresponding to the current order based on the start time and/or the end time of the plurality of candidate time periods and the corresponding candidate feature vector. In some embodiments, the first processing module 220 may further determine a plurality of second time periods based on the number of dimensions of the time periods and the number of dimensions of the preset time feature. For example, the first processing module 220 may determine the ending time of the first time period as the starting time of one second time period, or determine the starting time of the first time period as the ending time of one second time period, and then determine a plurality of second time periods according to the dimension number of the time periods and the dimension number of the preset time characteristics.

The first processing module 220 may be further configured to obtain a target feature vector of a preset dimension quantity corresponding to the current order based on the first feature vector in the first time period and the second feature vectors in the multiple second time periods.

The second processing module 230 is configured to obtain an estimated arrival time of the current order based on at least the target feature vector with the preset dimensional quantity. In some embodiments, the second processing module 230 may process the data related to the current order using a preset estimated time of arrival model. In some embodiments, the second processing module 230 may also be configured to obtain data related to historical orders and generate sample pairs for training the estimated time of arrival model.

It should be understood that the system and its modules shown in FIG. 2 may be implemented in a variety of ways. For example, in some embodiments, the system and its modules may be implemented in hardware, software, or a combination of software and hardware. Wherein the hardware portion may be implemented using dedicated logic; the software portions may be stored in a memory for execution by a suitable instruction execution system, such as a microprocessor or specially designed hardware. Those skilled in the art will appreciate that the methods and systems described above may be implemented using computer executable instructions and/or embodied in processor control code, such code being provided, for example, on a carrier medium such as a diskette, CD-or DVD-ROM, a programmable memory such as read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its modules of the present application may be implemented not only by hardware circuits such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but also by software executed by various types of processors, for example, or by a combination of the above hardware circuits and software (e.g., firmware).

It should be noted that the above description is merely for convenience and should not be taken as limiting the scope of the present application. It will be understood by those skilled in the art that, having the benefit of the teachings of this system, various modifications and changes in form and detail may be made to the field of application for which the method and system described above may be practiced without departing from this teachings.

FIG. 3 is an exemplary flow chart of a method 300 of determining an estimated time of arrival according to some embodiments of the present application. The method 300 may be implemented on the processing device 110 of fig. 1. As shown in FIG. 3, a method 300 of determining a predicted arrival event may include:

step 301, obtaining relevant data of the current order. Specifically, the step 301 may be performed by the obtaining module 210.

In some embodiments, when the service requester initiates the car use service request through a service platform (e.g., a network car appointment service platform, a shared car service platform, etc.), the obtaining module 210 may obtain the relevant data of the current order from a background database of the service platform. The service requester may be a passenger who needs to take a car, or may be a user who places an order for other delivery objects (e.g., goods, etc.). For convenience of description, the term "service requester" is used in some places to mean "passenger" or "user".

The current order refers to a request that a service requester needs to travel by using a vehicle currently, the relevant data of the current order at least includes a departure time, the departure time of the order may be a time for a passenger to arrive at a boarding point to confirm departure, and the departure time of the order may be a specific time point, for example, the departure time is 12: 30.

In some embodiments, the relevant data of the current order may further include one or any combination of order number, starting point of the order (e.g., the passenger getting on), travel destination, expected mileage of the order, order starting time (the time the passenger starts the order), traffic condition in the order travel, weather condition in the order travel, passenger information (e.g., basic identity information of the passenger) for starting the order, and the like.

Step 303, based on the departure time of the current order, obtaining a first feature vector of a first time period corresponding to the departure time. In particular, this step 303 may be performed by the first processing module 220.

In some embodiments, the processing device 110 (e.g., the first processing module 220) may process the preset time period according to a preset time period division method to obtain a plurality of candidate time periods. For example, 24 hours a day is divided into one candidate time period every 5 minutes for a total of 288 candidate time periods, and the candidate time periods are numbered in chronological order, for example, the candidate time period with the time period 00:00 to 00:05 has the number t of 0, the candidate time period with the time period 00:05 to 00:10 has the number t of 1, and the candidate time period with the time period 00:10 to 00:15 has the number t of 2 …. The first processing module 220 may obtain the relevant data of each candidate time period, where the relevant data of each candidate time period at least includes one or any combination of the start time of the candidate time period, the end time of the candidate time period, and the candidate feature vector corresponding to the candidate time period. In some embodiments, the data relating to the candidate time period may also include the date on which the time period was and the day of the week, etc. In some embodiments, the correlation data for all candidate time periods may form an embedded table, which corresponds to a matrix. In some embodiments, the matrix corresponding to the embedded table may be a vector set matrix composed of a plurality of feature vectors. In some embodiments, the number of dimensions of the matrix may be determined based on actual circumstances. Specifically, the relevant data of the candidate time period is compared with the embedding table in the embedding process, and the corresponding feature vector, that is, the candidate feature vector, can be queried in the embedding table. Namely, the relevant data of the candidate time period is subjected to vectorization processing.

In some embodiments, by setting the number of dimensions of the embedding table to be the same as the number of actually required dimensions of the feature vector, the relevant data of the candidate time period may obtain the feature vector of the actually required number of dimensions in the embedding process. In some embodiments, the number of dimensions of the feature vector is the number of components contained in the feature vector, for example, the vector a1 is equal to (1,0,0), and the number of dimensions of the vector a1 is equal to 3.

In some embodiments, the data associated with the candidate time period may change the number of dimensions during the embedding process to obtain a feature vector for the actual number of dimensions required. In some embodiments, changing the number of dimensions includes both a dimensionality reduction and a dimensionality increase process. Specifically, the feature vector with the actually required number of dimensions can be obtained by multiplying the candidate feature vector corresponding to the candidate time period by the vector matrix corresponding to the embedded table. For example, the eigenvector corresponding to the candidate time slot is a matrix (20-dimensional row vector) of 1x20, and the embedded table corresponds to a matrix (the number of dimensions of the matrix can be set according to practical situations) of 5-dimensional row number, 20-dimensional column number and 5, and the two are multiplied to obtain a matrix (5-dimensional row vector) of 1x5, thereby realizing that the eigenvector of 20 dimensions is reduced to 5 dimensions.

In some embodiments, the method of dimension reduction processing may include an attribute selection method, which may include filtering, packing, embedding, or a mapping method, which may include linear mapping methods (e.g., PCA, LDA, SVD, etc.), non-linear mapping methods (e.g., kernel methods, bidimensionalization, learning-by-prevalence, etc.), neural networks, clustering, etc. Because the dimension reduction processing is mainly adopted in the method, the dimension increasing processing is not required to be described too much.

In some embodiments, the first time period corresponding to the current order may be determined from a plurality of candidate time periods based on a start time and/or an end time of the plurality of candidate time periods. Specifically, at least one of the order initiation time, the order acceptance time, and the departure time included in the current order is compared with the relevant data of the candidate time period in the embedded table. For example, if the departure time is 00:13, the corresponding candidate time period is 00:10 to 00:15, and t is 2, where the candidate time period 00:10 to 00:15 is the first time period. In some embodiments, the candidate feature vector corresponding to the candidate time segment of the first time segment is the first feature vector. For ease of explanation, the following description is intended as an example only.

24 hours a day can be divided into 288 candidate time segments in 5 minutes, the number of dimensions of the candidate feature vector corresponding to each candidate time segment can be 5 dimensions, 10 dimensions, 15 dimensions, 20 dimensions, and the like, and generally, the number of dimensions of the first feature vector can be adjusted according to actual conditions. In some embodiments, there is similarity between time periods. For example, if the departure time of the current order is 00:17, the corresponding first time period is 00:15 to 00:20, and t is 3, and if the departure time of the current order is 00:13, the corresponding first time period is 00:10 to 00:15, and t is 2. If the similarity between adjacent time segments is not considered, the time segments 00: 16-00: 20, t-3, and the time segments 00: 10-00: 15, t-2 have two completely different first feature vectors. In practical cases, when the departure time is 00:13 and 00:17, there is similarity between two time periods (for example, traffic conditions or weather conditions are similar), so based on the similarity between adjacent time periods, a preset dimension number may be set to perform dimension reduction on candidate feature vectors corresponding to 288 candidate time segments in the embedding process, for example, the dimension number of the first feature vector is 20 dimensions, the preset dimension number is 5 dimensions, and after the dimension reduction of the first feature vector, the dimension number of the first feature vector is 5 dimensions. Specifically, the number of dimensions of the embedded table may be set to 5 dimensions, and then the 20-dimensional first eigenvector is multiplied by the 5-dimensional embedded table matrix, and the resultant vector is the 5-dimensional first eigenvector.

Step 305, obtaining a plurality of second feature vectors of a second time period, wherein the second time period is related to the first time period. In particular, this step 305 may be performed by the first processing module 220.

In some embodiments, the plurality of second time periods may be determined from a plurality of candidate time periods based on the number of dimensions of the first feature vector and a preset number of dimensions. Specifically, a plurality of third time periods including the first time period may be selected from the plurality of candidate time periods based on a ratio of the number of dimensions of the first feature vector to a preset number of dimensions, and then, the other time periods except the first time period in the plurality of third time periods may be used as the second time period. In some embodiments, the second time period is related to the first time period, e.g., adjacent in time sequence. In some embodiments, the plurality of third time periods are sequentially adjacent, wherein one of the third time periods is the first time period and the rest of the third time periods are the second time periods. In some embodiments, the first time period is the first time period of the plurality of third time periods, and may also be the last time period. In some embodiments, the first time period may be anywhere in the plurality of third time periods. For ease of explanation, the following description is intended as an example only.

The dimension number of the feature vector corresponding to the first time period 00: 10-00: 15, t ═ 2 and the preset dimension number are 20 dimensions and 5 dimensions respectively, and the ratio of the dimension number to the preset dimension number is 4, because the final output of the embedding process is still 20-dimensional feature vector, the 5-dimensional feature vectors after dimension reduction of 4 third time periods need to be extracted from a plurality of candidate time periods according to the first time period to form 20-dimensional feature vectors. The 4 third time periods are adjacent in sequence, one of the third time periods is a first time period, and the other three third time periods are second time periods, for example, the departure time of a driver is 00:13, the first time period is 00:10 to 00:15, t is 2, when calculating, 00:00 to 00:05, t is 0, 00:05 to 00:10, t is 1, 00:11 to 00:15, t is 2, 00:15 to 00:20, t is 3 or 00:10 to 00:15, t is 2, 00:15 to 00:20, t is 3, 00:20 to 00:25, t is 4, 00:25 to 00:30, t is 5, and 5-dimensional feature vectors corresponding to the four candidate time periods form a 20-dimensional feature vector. Wherein, 00:11 to 00:15, t 2 is a first time period, 00:00 to 00:05, t 0, 00:05 to 00:10, t 1, 00:15 to 00:20, t 3 or 00:15 to 00:20, t 3, 00:20 to 00:25, t 4, 00:25 to 00:30, and t 5 is a second time period. In some embodiments, the candidate feature vector corresponding to the candidate time segment of the second time segment is the second feature vector.

In some embodiments, when the first time period is used as a first time period in the plurality of third time periods, and the ending time of the first time period is determined as the starting time of one second time period, the second time period may be determined according to the number of dimensions of the first time period and the preset number of dimensions.

Specifically, a plurality of third time periods including the first time period may be selected from the plurality of candidate time periods based on a ratio of the number of dimensions of the first feature vector to a preset number of dimensions, and then, the other time periods except the first time period among the plurality of third time periods may be used as the second time period. Wherein the first time period is a first time period of a plurality of third time periods. After obtaining the relevant data of the first time period corresponding to the departure time in step 303, the end time of the first time period may be determined as the start time of the first second time period based on the end time of the first time period, and then the end time of the first second time period may be determined based on the length of the time period; after the start time and the end time of the first second time period are determined, the end time of the first second time period is determined as the start time of the second time period, and then the start time and the end time of the plurality of second time periods are sequentially acquired according to the method, so that the plurality of second time periods are determined. For example, the number of dimensions of the first feature vector is 20 dimensions, the number of preset dimensions is 5 dimensions, and thus, the number of third time periods is 4, wherein the number of first time periods is 1, and the number of second time periods related to the first time periods is 3. Assuming that the departure time is 00:28, the corresponding first time period is 00:25 to 00:30, and t is 5, the ending time of the first time period is 00: 30. And determining the end time of the first time period as the start time of the first second time period, wherein the start time of the first second time period is 00:30, and the end time of the first second time period is 00:35 based on the length of the time period being 5min, so that the first second time period is determined to be 00: 30-00: 35, and t is 6. And determining the ending time of the first second time period as the starting time of the second time period, wherein the starting time of the second time period is 00:35, and sequentially determining the second time period to be 00: 35-00: 40, t is 7, and the third second time period to be 00: 40-00: 45(t is 8) according to the method.

In some embodiments, when the first time period is the last time period of the plurality of third time periods and the starting time of the first time period is determined as the ending time of one second time period, the second time period may be determined according to the number of dimensions of the first time period and the number of dimensions of the preset time characteristic.

Specifically, a plurality of third time periods including the first time period may be selected from the plurality of candidate time periods based on a ratio of the number of dimensions of the first feature vector to a preset number of dimensions, and then, the other time periods except the first time period among the plurality of third time periods may be used as the second time period. Wherein the first time period is the last time period of the plurality of third time periods. After obtaining the relevant data of the first time period corresponding to the departure time in step 303, the start time of the first time period may be determined as the end time of the first second time period based on the start time of the first time period, and then the start time of the first second time period may be determined based on the length of the time period; after the start time and the end time of the first second time period are determined, the start time of the first second time period is determined as the end time of the second time period, and then the start time and the end time of the plurality of second time periods are sequentially acquired according to the method, so that the plurality of second time periods are determined. For example, the number of dimensions of the first feature vector is 20 dimensions, and the number of preset dimensions is 5 dimensions, so that the number of third time periods is 4, wherein the number of first time periods is 1, and the number of second time periods related to the first time periods is 3. Assuming that the departure time is 00:28, the corresponding first time period is 00:25 to 00:30, and t is 5, the start time of the first time period is 00: 25. And determining the starting time of the first time period as the ending time of the first second time period, wherein the ending time of the first second time period is 00:25, and the starting time of the first second time period is 00:20 based on the length of the time period being 5min, so that the first second time period is determined to be 00: 20-00: 25, and t is 4. And determining the starting time of the first second time period as the ending time of the second time period, wherein the ending time of the second time period is 00:20, and sequentially determining the second time period to be 00: 15-00: 20, t is 3, the third second time period to be 00: 10-00: 15, and t is 2 according to the method.

In some embodiments, when the first time period is located in the middle of the plurality of third time periods, the start time of the first time period may be used as the end time of one second time period, and the end time of the first time period may be used as the start time of another second time period, then the start time and the end time of the two second time periods are respectively determined according to the lengths of the time periods, and finally the other second time periods are determined according to the determined second time periods. Specific examples can be found in the foregoing.

Step 307, obtaining a target feature vector corresponding to the current order based on the first feature vector of the first time period and the second feature vectors of the plurality of second time periods. In particular, this step 307 may be performed by the first processing module 220.

In some embodiments, based on the related data of the first time period and the related data of the plurality of second time periods, the time feature vector of the first time period and the time feature vectors of the plurality of second time periods may be merged, that is, the first feature vector of the first time period and the second feature vectors of the plurality of second time periods are extracted at the same time to jointly form a target feature vector of a preset number of dimensions corresponding to the current order. For example, the number of dimensions of the first time period is 20 dimensions, the preset number of dimensions is 5 dimensions, and based on the first time period and the plurality of second time periods obtained in

steps

303 and 305, if the departure time is 00:28, 5-dimensional feature vectors of 00:25 to 00:30(t is 5), 00:30 to 00:35(t is 6), 00:35 to 00:40(t is 7), 00:40 to 00:45(t is 8) or 5-dimensional feature vectors of 00:25 to 00:30(t is 5), 00:20 to 00:25(t is 4), 00:15 to 00:20(t is 3), and 00:10 to 00:15(t is 2) are extracted at the same time to jointly form a 20-dimensional target feature vector corresponding to the current order.

Step 309, obtaining the estimated arrival time of the current order at least based on the target feature vectors with the preset dimension quantity. In particular, this step 309 may be performed by the second processing module 230.

In some embodiments, the processing device 110 (e.g., the second processing module 230) may process the data related to the current order according to a time of arrival prediction method to obtain an estimated time of arrival of the current order. In some embodiments, the relevant data of the current order further includes at least a target feature vector of a preset dimensional quantity and a current order feature.

The current order characteristics may include: the location characteristics can comprise a starting location characteristic and a destination characteristic of the order, the distance characteristics can comprise an order expected driving distance characteristic, the time characteristics can comprise an order departure time characteristic, and the road condition characteristics can comprise a traffic condition characteristic and a weather condition characteristic in an order driving route.

In some embodiments, the time of arrival prediction algorithm may be performed by a prediction model for predicting time of arrival. In particular, the processing device 110 (e.g., the second processing module 230) may process the relevant data of the current order using the predictive model. In some embodiments, the predictive model is a machine learning model. The estimated time of arrival model is obtained by the following method: obtaining a training set, wherein the training set comprises a plurality of sample pairs; and training the initial model by using the training set to obtain a pre-estimated model.

The estimated time of arrival model may be an Embedding (Embedding) based machine learning model.

In some embodiments, the predictive model may be trained by:

1) and acquiring a training set, and preprocessing sample data in the training set to enable the sample data to meet the training requirement. Preprocessing may include format conversion, normalization, identification, and the like.

2) Dividing the sample data into a training set, a verification set and a test set. The data may be randomly divided by a ratio of 80% in the training set, 15% in the validation set, and 5% in the test set.

3) And inputting the sample data in the training set into a to-be-trained estimated arrival time model for training, and acquiring a trained model.

4) Inputting the sample data in the verification set into the model trained in the step 3) for calculation to obtain an output value.

5) Comparing the output value of the sample data in the step 4) with the identifier of the corresponding sample data, and if the comparison result is ideal, turning to the step 6) to test. And if the comparison result is considered to need to be improved, adjusting the parameters of the estimated arrival time model according to the result, and executing the step 3) again based on the model after the parameters are adjusted.

6) And inputting the sample data in the test set into the trained model for calculation to obtain an output value.

7) Comparing the output value of the sample data in the step 6) with the identifier of the corresponding sample data, and judging whether the training result meets the requirement. If the training result does not meet the requirement, sample data is prepared again or the training set, the verification set and the test set are divided again for continuous training.

The training method of the estimated arrival time model described above may be variously changed, for example, the training set, the verification set, and the test set may be divided according to other methods or proportions, some of the steps may be omitted, and other steps may be added.

The training process for the estimated time of arrival model may be performed on the processing device 110, or may be performed on another device, and the trained estimated time of arrival model may be applied to the processing device 110. The training process may be performed multiple times or iteratively.

In some embodiments, the processing device 110 may obtain a training set, including: acquiring related data of a historical order; and generating a sample pair based on the related data of the historical order and the arrival time of the historical order. Wherein the related data of the historical order at least comprises: historical order features and target feature vectors corresponding to the historical orders.

In some embodiments, the historical orders may include orders that were placed by a service requester (e.g., a passenger) and completed by a service provider (e.g., a driver) on a service platform (e.g., a network appointment platform). The data related to the historical order may include one or more historical order related information and/or characteristics, for example, the data related to the historical order may include any combination of one or more of a historical order number, a starting location of the historical order, a travel destination of the historical order, a historical order travel distance, a departure time of the historical order, an arrival time of the historical order, an estimated arrival time of the historical order, passenger information (e.g., basic identity information of a passenger) initiating the historical order, traffic conditions in the historical order travel, weather conditions in the historical order travel, and the like.

In some embodiments, once an order is completed, the order may be treated as a historical order. The terminal 120 (e.g., a service requester terminal, or a service provider terminal) may transmit the associated historical order data to the storage device 130 of the system 100 via the network 140. The processing device 110 may obtain data related to the historical order from the storage device 130 of the system 100.

It should be noted that the above description related to the flow 300 is only for illustration and explanation, and does not limit the applicable scope of the present application. Various modifications and changes to flow 300 will be apparent to those skilled in the art in light of this disclosure. However, such modifications and variations are intended to be within the scope of the present application.

The beneficial effects that may be brought by the embodiments of the present application include, but are not limited to: based on the similarity between adjacent time periods, the time characteristics are subjected to dimension reduction processing, so that the accuracy of the network car booking platform in estimating the arrival time of the travel order can be improved, and the user experience is improved. It is to be noted that different embodiments may produce different advantages, and in different embodiments, any one or combination of the above advantages may be produced, or any other advantages may be obtained.

Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be considered merely illustrative and not restrictive of the broad application. Various modifications, improvements and adaptations to the present application may occur to those skilled in the art, although not explicitly described herein. Such modifications, improvements and adaptations are proposed in the present application and thus fall within the spirit and scope of the exemplary embodiments of the present application.

Also, this application uses specific language to describe embodiments of the application. Reference throughout this specification to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic described in connection with at least one embodiment of the present application is included in at least one embodiment of the present application. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, some features, structures, or characteristics of one or more embodiments of the present application may be combined as appropriate.

Moreover, those skilled in the art will appreciate that aspects of the present application may be illustrated and described in terms of several patentable species or situations, including any new and useful combination of processes, machines, manufacture, or materials, or any new and useful improvement thereon. Accordingly, various aspects of the present application may be embodied entirely in hardware, entirely in software (including firmware, resident software, micro-code, etc.) or in a combination of hardware and software. The above hardware or software may be referred to as "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the present application may be represented as a computer product, including computer readable program code, embodied in one or more computer readable media.

The computer storage medium may comprise a propagated data signal with the computer program code embodied therewith, for example, on baseband or as part of a carrier wave. The propagated signal may take any of a variety of forms, including electromagnetic, optical, etc., or any suitable combination. A computer storage medium may be any computer-readable medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code located on a computer storage medium may be propagated over any suitable medium, including radio, cable, fiber optic cable, RF, or the like, or any combination of the preceding.

Computer program code required for the operation of various portions of the present application may be written in any one or more programming languages, including an object oriented programming language such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C + +, C #, VB.NET, Python, and the like, a conventional programming language such as C, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, a dynamic programming language such as Python, Ruby, and Groovy, or other programming languages, and the like. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any network format, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet), or in a cloud computing environment, or as a service, such as a software as a service (SaaS).

Additionally, the order in which elements and sequences of the processes described herein are processed, the use of alphanumeric characters, or the use of other designations, is not intended to limit the order of the processes and methods described herein, unless explicitly claimed. While various presently contemplated embodiments of the invention have been discussed in the foregoing disclosure by way of example, it is to be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments herein. For example, although the system components described above may be implemented by hardware devices, they may also be implemented by software-only solutions, such as installing the described system on an existing server or mobile device.

Similarly, it should be noted that in the preceding description of embodiments of the application, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of one or more of the embodiments. This method of disclosure, however, is not intended to require more features than are expressly recited in the claims. Indeed, the embodiments may be characterized as having less than all of the features of a single embodiment disclosed above.

Numerals describing the number of components, attributes, etc. are used in some embodiments, it being understood that such numerals used in the description of the embodiments are modified in some instances by the use of the modifier "about", "approximately" or "substantially". Unless otherwise indicated, "about", "approximately" or "substantially" indicates that the number allows a variation of ± 20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximations that may vary depending upon the desired properties of the individual embodiments. In some embodiments, the numerical parameter should take into account the specified significant digits and employ a general digit preserving approach. Notwithstanding that the numerical ranges and parameters setting forth the broad scope of the range are approximations, in the specific examples, such numerical values are set forth as precisely as possible within the scope of the application.

The entire contents of each patent, patent application publication, and other material cited in this application, such as articles, books, specifications, publications, documents, and the like, are hereby incorporated by reference into this application. Except where the application is filed in a manner inconsistent or contrary to the present disclosure, and except where the claim is filed in its broadest scope (whether present or later appended to the application) as well. It is noted that the descriptions, definitions and/or use of terms in this application shall control if they are inconsistent or contrary to the statements and/or uses of the present application in the material attached to this application.

Finally, it should be understood that the embodiments described herein are merely illustrative of the principles of the embodiments of the present application. Other variations are also possible within the scope of the present application. Thus, by way of example, and not limitation, alternative configurations of the embodiments of the present application can be viewed as being consistent with the teachings of the present application. Accordingly, the embodiments of the present application are not limited to only those embodiments explicitly described and depicted herein.

Claims

1. A method of determining an estimated time of arrival, the method comprising:

acquiring relevant data of a current order, wherein the relevant data of the current order at least comprises the following data: a departure time;

obtaining a first feature vector of a first time period corresponding to the departure time based on the departure time of the current order;

obtaining second feature vectors of a plurality of second time periods, wherein the second time periods are related to the first time periods;

obtaining a target feature vector corresponding to the current order based on the first feature vector of the first time period and the second feature vectors of the plurality of second time periods;

and obtaining the estimated arrival time of the current order at least based on the target characteristic vector.

2. The method according to claim 1, wherein the obtaining a first feature vector of a first time period corresponding to the departure time based on the departure time of the current order comprises:

Processing the preset time period according to a preset time period dividing method to obtain a plurality of candidate time periods;

obtaining relevant data for each candidate time period, the relevant data at least comprising: the starting time of the candidate time period, the ending time of the candidate time period and the candidate feature vector corresponding to the candidate time period;

determining a first time period corresponding to the current order from a plurality of candidate time periods based on the starting time and/or the ending time of the candidate time periods;

and designating the candidate feature vector corresponding to the candidate time segment of the first time segment as the first feature vector of the first time segment.

3. The method of claim 2, wherein obtaining the second feature vectors for the plurality of second time segments comprises:

determining a plurality of second time periods from the plurality of candidate time periods based on the number of dimensions of the first feature vector and a preset number of dimensions;

and appointing a candidate feature vector corresponding to the candidate time period as the second feature vector of the second time period.

4. The method of claim 3, wherein determining a plurality of second time periods from the plurality of candidate time periods comprises:

Determining a ratio of the dimension number of the first feature vector to the preset dimension number;

selecting a plurality of third time periods including the first time period from the plurality of candidate time periods based on the ratio;

designating the other time periods of the plurality of third time periods except the first time period as the plurality of second time periods.

5. The method of claim 1, wherein obtaining the estimated arrival time of the current order based on at least the target feature vector of the preset dimensional quantity comprises:

obtaining the order characteristics of the current order;

and processing the target characteristic vector and the order characteristics according to an arrival time prediction algorithm to obtain the estimated arrival time of the current order.

6. The method of claim 5, wherein the time of arrival prediction algorithm comprises a prediction model for predicting time of arrival; the pre-estimation model is a machine learning model and is obtained based on the following operations:

obtaining a training set, wherein the training set comprises a plurality of sample pairs;

and training an initial model by using the training set to obtain the pre-estimated model.

7. The method of claim 6, wherein the obtaining the training set comprises:

acquiring related data of a historical order;

wherein the related data of the historical order at least comprises:

historical order features and feature vectors corresponding to the historical orders.

8. A system for determining an estimated time of arrival, the system comprising:

an obtaining module, configured to obtain relevant data of a current order, where the relevant data of the current order at least includes: a departure time;

the first processing module is used for obtaining relevant data of a first time period corresponding to the departure time based on the departure time of the current order;

the first processing module is further configured to obtain related data of a plurality of second time periods, where the second time periods are related to the first time period;

the first processing module is further configured to obtain a time feature vector of a preset dimension quantity corresponding to the current order based on the relevant data of the first time period and the relevant data of the plurality of second time periods;

And the second processing module is used for obtaining the estimated arrival time of the current order at least based on the time characteristic vector of the preset dimension quantity.

9. An apparatus for determining an estimated time of arrival comprising a processor, wherein the processor is configured to perform the method of determining an estimated time of arrival of any of claims 1-7.

10. A computer readable storage medium storing computer instructions which, when read by a computer, cause the computer to carry out a method of determining an estimated time of arrival according to any one of claims 1 to 7.