WO2021077300A1

WO2021077300A1 - Systems and methods for improving an online to offline platform

Info

Publication number: WO2021077300A1
Application number: PCT/CN2019/112585
Authority: WO
Inventors: Xiao Liu; Yunzhou ZHANG
Original assignee: Beijing Didi Infinity Technology And Development Co., Ltd.
Priority date: 2019-10-22
Filing date: 2019-10-22
Publication date: 2021-04-29

Abstract

A method includes obtaining a plurality of routes associated with a plurality of orders provided by the online to offline platform in a historical period (510). The method may also include clustering, based on one or more features associated with each of the plurality of routes, the plurality of routes into multiple groups, each of the multiple groups including one or more routes (520). The method may further include determining, based on the one or more operation indicators of the online to offline platform (530); and determining, based on the model for estimating one or more operation indicators of the online to offline platform, an operation indicator of the online to offline platform in a future period (540).

Description

SYSTEMS AND METHODS FOR IMPROVING AN ONLINE TO OFFLINE PLATFORM

TECHNICAL FIELD

The present disclosure generally relates to online to offline service platforms, and specifically, to systems and methods for estimating an operation indicator of an online to offline service platform.

BACKGROUND

Online to offline services, such as online ridesharing services and delivery services, have become increasingly popular due to their convenience. A huge amount of data can be generated and/or provided by an online to offline service platform (e.g., an online transport service platform) when providing online to offline services for users. For example, for the online transport service platform, a large number of historical routes or orders can be provided by the online transport service platform. The analysis of such historical data may be used to improve urban public transport network and optimize shared travel. However, since the data related to a particular route, or to a certain type of routes, is generally sparse, the analysis of the online to offline service platform relying on such data may lack accuracy. Therefore, it is desirable to provide systems and methods for data estimation associated with an online to offline platform more effectively and accurately to improve the online to offline platform.

SUMMARY

According to a first aspect of the present disclosure, a system for improving an online to offline platform is provided. The system may include at least one storage device storing executable instructions, and at least one processor in communication with the at least one storage device. When executing the executable instructions, the at least one processor may cause the system to perform one or more of the following operations. The system may obtain a plurality of routes associated with a plurality of orders provided by the online to offline platform in a historical period and cluster, based on one or more features associated with each of the plurality of routes, the plurality of routes into multiple groups, each of the multiple groups including one or more routes. The system may also determine, based on the one or more routes in at least a portion of the multiple groups, a model for estimating one or more operation indicators of the online to offline platform. The system may further determine, based on the model for estimating one or more operation indicators of the online to offline platform, an operation indicator of the online to offline platform in a future period.

In some embodiments, the one or more features of the each of the plurality of routes may include at least one of a starting location of, a destination, a travel distance, a travel duration, a departure time, an arrival time, a price, or a discount.

In some embodiments, to cluster the plurality of routes into the multiple groups, the system may cluster the plurality of routes into the multiple groups using a density-based clustering model.

In some embodiments, to cluster, based on one or more features associated with each of the plurality of routes, the plurality of routes into multiple groups, the system represent, based on the one or more features associated with each of the plurality of routes, each of the plurality of routes with a point in an N-dimensional coordinate system, N being an integer greater than or equal to 3. The system may also cluster, based on points representing the plurality of routes, the plurality of routes into the multiple groups.

In some embodiments, to represent each of the plurality of routes with a point in the N-dimensional coordinate system, the system may denote geographical coordinates of a starting location and geographical coordinates of a destination of each of the plurality of routes as coordinates of the point in the N-dimensional coordinate system.

In some embodiments, to cluster the plurality of routes into the multiple groups, the system may determine a distance between two points corresponding to any two of the plurality of routes in the N-dimensional system; and cluster, based on the distance between two points corresponding to any two of the plurality of routes in the N-dimensional system, the plurality of routes into the multiple groups, wherein whether the distance between two points corresponding to any two of the plurality of routes satisfies a criterion determines whether the two routes belong to a same group in the multiple groups.

In some embodiments, the operation indicator of the online to offline platform may include at least one of an order amount, a gross merchandise volume (GMV) , a gross margin, or a gain and loss rate.

In some embodiments, the model for estimating the one or more operation indicators of the online to offline platform may be configured to provide a relationship between the operation indicator and a price parameter, and to determine, based on the one or more routes in at least a portion of the multiple groups, a model for estimating one or more operation indicators of the online to offline platform, the system may determine statistically, based on the one or more routes in each group of the multiple groups, the relationship between the operation indicator and the price parameter using a fitting technique.

In some embodiments, to determine statistically, based on the one or more routes in each group of the multiple groups, the relationship between the operation indicator and the price parameter using a fitting technique, the system may determine statistically, based on the one or more routes in each group of the multiple groups, multiple reference values of the operation indicator, each of the reference values corresponding to each group of the multiple groups; and determine the relationship between the operation indicator and the price parameter using the fitting technique based on the multiple reference values of the operation indicator and the price parameter corresponding to each group of the multiple groups.

In some embodiments, the model for estimating the one or more operation indicators of the online to offline platform may include an objective function with a specific operation indicator as a dependent variable and a price parameter as an independent variable, and to estimate one or more operation indicators of the online to offline platform, the one or more operation indicators of the online to offline platform in a future period, the system may determine a maximum value or a minimum value of the objective function under one or more constraint conditions being satisfied; and designate the maximum value or the minimum value of the objective function as the a predicted value of the specific operation indicator in the future period, wherein the each of the one or more constraint conditions may be associated with an additional operation indicator.

In some embodiments, the specific operation indicator may include an order amount and the price parameter includes a discount, and the objective function may be determined by determining a first component providing a first relationship between a probability that an order is a carpooling order and the discount of the order; determining a second component providing a second relationship between the discount and a change of the probability changing with the discount; and determining the objective function based on the first component and the second component.

In some embodiments, to determine, based on the one or more routes in at least a portion of the multiple groups, a model for estimating one or more operation indicators of the online to offline platform, the system may determine two or more groups that satisfy a first condition from the multiple groups; cluster one or more routes that satisfy a second condition in each of the two or more groups into one or more additional groups; and determine, based on the one or more additional groups and the at least a portion of the multiple groups, the model.

According to a second aspect of the present disclosure, a method for improving an online to offline platform is provided. The method may be implemented on at least one computing device, each of which may include at least one processor and a storage device. The method may include obtaining a plurality of routes associated with a plurality of orders provided by the online to offline platform in a historical period. The method may also include clustering, based on one or more features associated with each of the plurality of routes, the plurality of routes into multiple groups, each of the multiple groups including one or more routes. The method may further include determining, based on the one or more routes in at least a portion of the multiple groups, a model for estimating one or more operation indicators of the online to offline platform; and determining, based on the model for estimating one or more operation indicators of the online to offline platform, an operation indicator of the online to offline platform in a future period.

According to a third aspect of the present disclosure, a non-transitory computer readable medium is provided. The non-transitory computer readable medium may include a set of instructions. When executed by at least one processor, the set of instructions may direct the at least one processor to effectuate a method. The method may include obtaining a plurality of routes associated with a plurality of orders provided by the online to offline platform in a historical period. The method may also include clustering, based on one or more features associated with each of the plurality of routes, the plurality of routes into multiple groups, each of the multiple groups including one or more routes. The method may further include determining, based on the one or more routes in at least a portion of the multiple groups, a model for estimating one or more operation indicators of the online to offline platform; and determining, based on the model for estimating one or more operation indicators of the online to offline platform, an operation indicator of the online to offline platform in a future period.

According to a fourth aspect of the present disclosure, a system for improving an online to offline platform is provided. The system may include an obtaining module configured to obtain a plurality of routes associated with a plurality of orders provided by the online to offline platform in a historical period; a clustering module configured to cluster, based on one or more features associated with each of the plurality of routes, the plurality of routes into multiple groups, each of the multiple groups including one or more routes; a determination module configured to determine, based on the one or more routes in at least a portion of the multiple groups, a model for estimating one or more operation indicators of the online to offline platform; and an estimation module configured to determining, based on the model for estimating one or more operation indicators of the online to offline platform, an operation indicator of the online to offline platform in a future period

Additional features will be set forth in part in the description which follows, and in part will become apparent to those skilled in the art upon examination of the following and the accompanying drawings or may be learned by production or operation of the examples. The features of the present disclosure may be realized and attained by practice or use of various aspects of the methodologies, instrumentalities and combinations set forth in the detailed examples discussed below.

BRIEF DESCRIPTION OF THE DRAWINGS

The present disclosure is further described in terms of exemplary embodiments. These exemplary embodiments are described in detail with reference to the drawings. These embodiments are non-limiting exemplary embodiments, in which like reference numerals represent similar structures throughout the several views of the drawings, and wherein:

FIG. 1 is a schematic diagram illustrating an exemplary online to offline service system according to some embodiments of the present disclosure;

FIG. 2 is a schematic diagram illustrating exemplary hardware and/or software components of a computing device according to some embodiments of the present disclosure;

FIG. 3 is a schematic diagram illustrating exemplary hardware and/or software components of a mobile device according to some embodiments of the present disclosure;

FIG. 4 is a block diagram illustrating an exemplary processing device according to some embodiments of the present disclosure;

FIG. 5 is a schematic flowchart illustrating an exemplary process for estimating an operation indicator according to some embodiments of the present disclosure; and

FIG. 6 is a schematic flowchart illustrating an exemplary process for clustering a plurality of routes using a density-based clustering model according to some embodiments of the present disclosure.

DETAILED DESCRIPTION

The following description is presented to enable any person skilled in the art to make and use the present disclosure and is provided in the context of a particular application and its requirements. Various modifications to the disclosed embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other embodiments and applications without departing from the spirit and scope of the present disclosure. Thus, the present disclosure is not limited to the embodiments shown but is to be accorded the widest scope consistent with the claims.

The terminology used herein is for the purpose of describing particular example embodiments only and is not intended to be limiting. As used herein, the singular forms “a, ” “an, ” and “the” may be intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprise, ” “comprises, ” and/or “comprising, ” “include, ” “includes, ” and/or “including” when used in this disclosure, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

Generally, the word “module, ” “unit, ” or “block, ” as used herein, refers to logic embodied in hardware or firmware, or to a collection of software instructions. A module, a unit, or a block described herein may be implemented as software and/or hardware and may be stored in any type of non-transitory computer-readable medium or other storage devices. In some embodiments, a software module/unit/block may be compiled and linked into an executable program. It will be appreciated that software modules can be callable from other modules/units/blocks or from themselves, and/or may be invoked in response to detected events or interrupts. Software modules/units/blocks configured for execution on computing devices may be provided on a computer-readable medium, such as a compact disc, a digital video disc, a flash drive, a magnetic disc, or any other tangible medium, or as a digital download (and can be originally stored in a compressed or installable format that needs installation, decompression, or decryption prior to execution) . Such software code may be stored, partially or fully, on a storage device of the executing computing device, for execution by the computing device. Software instructions may be embedded in firmware, such as an erasable programmable read-only memory (EPROM) . It will be further appreciated that hardware modules/units/blocks may be included in connected logic components, such as gates and flip-flops, and/or can be included of programmable units, such as programmable gate arrays or processors. The modules/units/blocks or computing device functionality described herein may be implemented as software modules/units/blocks, but may be represented in hardware or firmware. In general, the modules/units/blocks described herein refer to logical modules/units/blocks that may be combined with other modules/units/blocks or divided into sub-modules/sub-units/sub-blocks despite their physical organization or storage. The description may be applicable to a system, an engine, or a portion thereof.

It will be understood that the term “system, ” “engine, ” “unit, ” “module, ” and/or “block” used herein are one method to distinguish different components, elements, parts, section or assembly of different level in ascending order. However, the terms may be displaced by another expression if they achieve the same purpose.

It will be understood that when a unit, engine, module or block is referred to as being “on, ” “connected to, ” or “coupled to, ” another unit, engine, module, or block, it may be directly on, connected or coupled to, or communicate with the other unit, engine, module, or block, or an intervening unit, engine, module, or block may be present, unless the context clearly indicates otherwise. As used herein, the term “and/or” includes any and all combinations of one or more of the associated listed items.

These and other features, and characteristics of the present disclosure, as well as the methods of operation and functions of the related elements of structure and the combination of parts and economies of manufacture, may become more apparent upon consideration of the following description with reference to the accompanying drawings, all of which form a part of this disclosure. It is to be expressly understood, however, that the drawings are for the purpose of illustration and description only and are not intended to limit the scope of the present disclosure. It is understood that the drawings are not to scale.

The flowcharts used in the present disclosure illustrate operations that systems implement according to some embodiments in the present disclosure. It is to be expressly understood, the operations of the flowchart may be implemented not in order. Conversely, the operations may be implemented in inverted order, or simultaneously. Moreover, one or more other operations may be added to the flowcharts. One or more operations may be removed from the flowcharts.

Embodiments of the present disclosure may be applied to different transportation systems including but not limited to land transportation, sea transportation, air transportation, space transportation, or the like, or any combination thereof. A vehicle of the transportation systems may include a rickshaw, travel tool, taxi, chauffeured car, hitch, bus, rail transportation (e.g., a train, a bullet train, high-speed rail, and subway) , ship, airplane, spaceship, hot-air balloon, driverless vehicle, or the like, or any combination thereof. The transportation system may also include any transportation system that applies management and/or distribution, for example, a system for sending and/or receiving an express.

The application scenarios of different embodiments of the present disclosure may include but not limited to one or more webpages, browser plugins and/or extensions, client terminals, custom systems, intracompany analysis systems, artificial intelligence robots, or the like, or any combination thereof. It should be understood that application scenarios of the system and method disclosed herein are only some examples or embodiments. Those having ordinary skills in the art, without further creative efforts, may apply these drawings to other application scenarios. For example, other similar servers.

The term “passenger, ” “requester, ” “requestor, ” “service requester, ” “service requestor” and “customer” in the present disclosure are used interchangeably to refer to an individual, an entity or a tool that may request or order a service. Also, the term “driver, ” “provider, ” “service provider, ” and “supplier” in the present disclosure are used interchangeably to refer to an individual, an entity or a tool that may provide a service or facilitate the providing of the service. The term “user” in the present disclosure may refer to an individual, an entity or a tool that may request a service, order a service, provide a service, or facilitate the providing of the service. For example, the user may be a requester, a passenger, a driver, an operator, or the like, or any combination thereof. In the present disclosure, “requester” and “requester terminal” may be used interchangeably, and “provider” and “provider terminal” may be used interchangeably.

The term “request, ” “service, ” “service request, ” and “order” in the present disclosure are used interchangeably to refer to a request that may be initiated by a passenger, a requester, a service requester, a customer, a driver, a provider, a service provider, a supplier, or the like, or any combination thereof. The service request may be accepted by anyone of a passenger, a requester, a service requester, a customer, a driver, a provider, a service provider, or a supplier. The service request may be chargeable or free.

The present disclosure provides systems and methods for estimating an operation indicator of an online to offline (O2O) service platform. The system may obtain a plurality of routes associated with a plurality of orders provided by the online to offline platform in a historical period. The system may cluster, based on one or more features associated with each of the plurality of routes, the plurality of routes into multiple groups. Each of the multiple groups may include one or more routes. The system may determine, based on the one or more routes in at least a portion of the multiple groups, a model for estimating one or more operation indicators of the online to offline platform. The system may determine, based on the model for estimating one or more operation indicators of the online to offline platform, an operation indicator of the online to offline platform in a future period. Accordingly, the operation indicator of the online to offline platform in a future period may be estimated based on multiple groups of routes each of which includes multiple routes having similar features, which may enrich data volume and improve accuracy of the estimated operation indicator.

FIG. 1 is a schematic diagram illustrating an exemplary online to offline service system according to some embodiments of the present disclosure. For example, the online to offline service system 100 may be an online to offline platform or an online on-demand service platform such as a travel platform for providing transportation services. The online to offline service system 100 may include a server 110, a network 120, a requester terminal 130, a provider terminal 140, a vehicle 150, a storage device 160, and a navigation system 170.

The online to offline service system 100 may provide a plurality of services. Exemplary services may include a taxi-hailing service, a chauffeur service, an express car service, a carpool service, a bus service, a driver hire service, and a shuttle service. In some embodiments, the online to offline service may be any online service, such as booking a meal, shopping, or the like, or any combination thereof.

In some embodiments, the server 110 may be a single server or a server group. The server group may be centralized (e.g., a data center) or distributed (e.g., the server 110 may be a distributed system) . In some embodiments, the server 110 may be local or remote. For example, the server 110 may access information and/or data stored in the requester terminal 130, the provider terminal 140, and/or the storage device 160 via the network 120. As another example, the server 110 may be directly connected to the requester terminal 130, the provider terminal 140, and/or the storage device 160 to access stored information and/or data. In some embodiments, the server 110 may be implemented on a cloud platform. Merely by way of example, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an inter-cloud, a multi-cloud, or the like, or any combination thereof. In some embodiments, the server 110 may be implemented on a computing device 200 having one or more components illustrated in FIG. 2 in the present disclosure.

In some embodiments, the server 110 may include a processing device 112. The processing device 112 may process information and/or data related to service data to perform one or more functions described in the present disclosure. For example, the processing device 112 may obtain a plurality of routes associated with a plurality of orders provided by the online to offline platform 100 in a historical period. The processing device 112 may cluster the plurality of routes into multiple groups based on one or more features associated with each of the plurality of routes. The processing device 112 may determine a model for estimating one or more operation indicators of the online to offline platform based on the one or more routes in at least a portion of the multiple groups. The processing device 112 may determine an operation indicator of the online to offline platform in a future period based on the model for estimating one or more operation indicators of the online to offline platform. As another example, the processing device 112 may represent each of the plurality of travel routes with a point in an N-dimensional coordinate system based on the one or more features associated with each of the plurality of routes. The processing device 112 may determine a distance between two points corresponding to any two of the plurality of routes in the N-dimensional coordinate system. The processing device 112 may cluster the plurality of routes into the multiple groups based on the distance between two points corresponding to any two of the plurality of routes in the N-dimensional coordinate system.

In some embodiments, the processing device 112 may include one or more processing engines (e.g., single-core processing engine (s) or multi-core processor (s) ) . Merely by way of example, the processing device 112 may include a central processing unit (CPU) , an application-specific integrated circuit (ASIC) , an application-specific instruction-set processor (ASIP) , a graphics processing unit (GPU) , a physics processing unit (PPU) , a digital signal processor (DSP) , a field-programmable gate array (FPGA) , a programmable logic device (PLD) , a controller, a microcontroller unit, a reduced instruction-set computer (RISC) , a microprocessor, or the like, or any combination thereof. In some embodiments, the processing device 112 may be integrated in the requester terminal 130 or the provider terminal 140.

The network 120 may facilitate the exchange of information and/or data. In some embodiments, one or more components (e.g., the server 110, the requester terminal 130, the provider terminal 140, the vehicle 150, the storage device 160, and the navigation system 170) of the online to offline service system 100 may transmit information and/or data to other component (s) of the online to offline service system 100 via the network 120. For example, the server 110 may receive a service request from the requester terminal 130 via the network 120. In some embodiments, the network 120 may be any type of wired or wireless network, or combination thereof. Merely by way of example, the network 120 may include a cable network, a wireline network, an optical fiber network, a telecommunications network, an intranet, an Internet, a local area network (LAN) , a wide area network (WAN) , a wireless local area network (WLAN) , a metropolitan area network (MAN) , a public telephone switched network (PSTN) , a Bluetooth network, a ZigBee network, a near field communication (NFC) network, or the like, or any combination thereof. In some embodiments, the network 120 may include one or more network access points. For example, the network 120 may include wired or wireless network access points such as base stations and/or internet exchange points 120-1, 120-2, through which one or more components of the online to offline service system 100 may be connected to the network 120 to exchange data and/or information.

In some embodiments, a passenger may be an owner of the requester terminal 130. In some embodiments, the owner of the requester terminal 130 may be someone other than the passenger. For example, an owner A of the requester terminal 130 may use the requester terminal 130 to transmit a service request for a passenger B or receive a service confirmation and/or information or instructions from the server 110. In some embodiments, a service provider may be a user of the provider terminal 140. In some embodiments, the user of the provider terminal 140 may be someone other than the service provider. For example, a user C of the provider terminal 140 may use the provider terminal 140 to receive a service request for a service provider D, and/or information or instructions from the server 110. In some embodiments, "passenger" and "passenger terminal" may be used interchangeably, and "service provider" and "provider terminal" may be used interchangeably. In some embodiments, the provider terminal may be associated with one or more service providers (e.g., a night-shift service provider, or a day-shift service provider) .

In some embodiments, the requester terminal 130 may include a mobile device 130-1, a tablet computer 130-2, a laptop computer 130-3, a built-in device in a vehicle 130-4, a wearable device 130-5, or the like, or any combination thereof. In some embodiments, the mobile device 130-1 may include a smart home device, a smart mobile device, a virtual reality device, an augmented reality device, or the like, or any combination thereof. In some embodiments, the smart home device may include a smart lighting device, a control device of an intelligent electrical apparatus, a smart monitoring device, a smart television, a smart video camera, an interphone, or the like, or any combination thereof. In some embodiments, the smart mobile device may include a smartphone, a personal digital assistance (PDA) , a gaming device, a navigation device, a point of sale (POS) device, or the like, or any combination thereof. In some embodiments, the virtual reality device and/or the augmented reality device may include a virtual reality helmet, virtual reality glasses, a virtual reality patch, an augmented reality helmet, augmented reality glasses, an augmented reality patch, or the like, or any combination thereof. For example, the virtual reality device and/or the augmented reality device may include Google ^TM Glasses, an Oculus Rift, a HoloLens, a Gear VR, etc. In some embodiments, the built-in device in the vehicle 130-4 may include an onboard computer, an onboard television, etc. In some embodiments, the requester terminal 130 may be a device with positioning technology for locating the position of the passenger and/or the requester terminal 130. In some embodiments, the wearable device 130-5 may include a smart bracelet, a smart footgear, smart glasses, a smart helmet, a smart watch, smart clothing, a smart backpack, a smart accessory, or the like, or any combination thereof.

The provider terminal 140 may include a plurality of provider terminals 140-1, 140-2, …, 140-n. In some embodiments, the provider terminal 140 may be similar to, or the same device as the requester terminal 130. In some embodiments, the provider terminal 140 may be customized to be able to implement the online to offline service system 100. In some embodiments, the provider terminal 140 may be a device with positioning technology for locating the service provider, the provider terminal 140, and/or a vehicle 150 associated with the provider terminal 140. In some embodiments, the requester terminal 130 and/or the provider terminal 140 may communicate with another positioning device to determine the position of the passenger, the requester terminal 130, the service provider, and/or the provider terminal 140. In some embodiments, the requester terminal 130 and/or the provider terminal 140 may periodically transmit the positioning information to the server 110. In some embodiments, the provider terminal 140 may also periodically transmit the availability status to the server 110. The availability status may indicate whether a vehicle 150 associated with the provider terminal 140 is available to carry a passenger. For example, the requester terminal 130 and/or the provider terminal 140 may transmit the positioning information and the availability status to the server 110 every thirty minutes. As another example, the requester terminal 130 and/or the provider terminal 140 may transmit the positioning information and the availability status to the server 110 each time the user logs into the mobile application associated with the on-demand transportation service 100.

In some embodiments, the provider terminal 140 may correspond to one or more vehicles 150. The vehicles 150 may carry the passenger and travel to the destination. The vehicles 150 may include a plurality of vehicles 150-1, 150-2, …, 150-n. One vehicle may correspond to one type of services (e.g., a taxi-hailing service, a chauffeur service, an express car service, a carpool service, a bus service, a driver hire service, or a shuttle service) .

The storage device 160 may store data and/or instructions relating to the service request. In some embodiments, the storage device 160 may store data obtained from the requester terminal 130 and/or the provider terminal 140. In some embodiments, the storage device 160 may store data and/or instructions that the server 110 may execute or use to perform exemplary methods described in the present disclosure. In some embodiments, the storage device 160 may include a mass storage, removable storage, a volatile read-and-write memory, a read-only memory (ROM) , or the like, or any combination thereof. Exemplary mass storage may include a magnetic disk, an optical disk, solid-state drives, etc. Exemplary removable storage may include a flash drive, a floppy disk, an optical disk, a memory card, a zip disk, a magnetic tape, etc. Exemplary volatile read-and-write memory may include a random access memory (RAM) . Exemplary RAM may include a dynamic RAM (DRAM) , a double date rate synchronous dynamic RAM (DDR SDRAM) , a static RAM (SRAM) , a thyristor RAM (T-RAM) , and a zero-capacitor RAM (Z-RAM) , etc. Exemplary ROM may include a mask ROM (MROM) , a programmable ROM (PROM) , an erasable programmable ROM (EPROM) , an electrically-erasable programmable ROM (EEPROM) , a compact disk ROM (CD-ROM) , and a digital versatile disk ROM, etc. In some embodiments, the storage device 160 may be implemented on a cloud platform. Merely by way of example, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an inter-cloud, a multi-cloud, or the like, or any combination thereof.

In some embodiments, the storage device 160 may be connected to the network 120 to communicate with one or more components of the online to offline service system 100 (e.g., the server 110, the requester terminal 130, or the provider terminal 140) . One or more components of the online to offline service system 100 may access the data or instructions stored in the storage device 160 via the network 120. In some embodiments, the storage device 160 may be directly connected to or communicate with one or more components of the online to offline service system 100 (e.g., the server 110, the requester terminal 130, the provider terminal 140) . In some embodiments, the storage device 160 may be part of the server 110.

The navigation system 170 may determine information associated with an object, for example, one or more of the requester terminal 130, the provider terminal 140, the vehicle 150, etc. In some embodiments, the navigation system 170 may be a global positioning system (GPS) , a global navigation satellite system (GLONASS) , a compass navigation system (COMPASS) , a BeiDou navigation satellite system, a Galileo positioning system, a quasi-zenith satellite system (QZSS) , etc. The information may include a location, an elevation, a velocity, or an acceleration of the object, or a current time. The navigation system 170 may include one or more satellites, for example, a satellite 170-1, a satellite 170-2, and a satellite 170-3. The satellites 170-1 through 170-3 may determine the information mentioned above independently or jointly. The satellite navigation system 170 may transmit the information mentioned above to the network 120, the requester terminal 130, the provider terminal 140, or the vehicle 150 via wireless connections.

In some embodiments, one or more components of the online to offline service system 100 (e.g., the server 110, the requester terminal 130, the provider terminal 140) may have permissions to access the storage device 160. In some embodiments, one or more components of the online to offline service system 100 may read and/or modify information related to the passenger, service provider, and/or the public when one or more conditions are met. For example, the server 110 may read and/or modify one or more passengers’ information after a service is completed. As another example, the server 110 may read and/or modify one or more service providers’ information after a service is completed.

One of ordinary skill in the art would understand that when an element (or component) of the online to offline service system 100 performs, the element may perform through electrical signals and/or electromagnetic signals. For example, when a requester terminal 130 transmits out a service request to the server 110, a processor of the requester terminal 130 may generate an electrical signal encoding the request. The processor of the requester terminal 130 may then transmit the electrical signal to an output port. If the requester terminal 130 communicates with the server 110 via a wired network, the output port may be physically connected to a cable, which further may transmit the electrical signal to an input port of the server 110. If the requester terminal 130 communicates with the server 110 via a wireless network, the output port of the requester terminal 130 may be one or more antennas, which convert the electrical signal to electromagnetic signal. Similarly, a provider terminal 140 may receive an instruction and/or service request from the server 110 via electrical signal or electromagnet signals. Within an electronic device, such as the requester terminal 130, the provider terminal 140, and/or the server 110, when a processor thereof processes an instruction, transmits out an instruction, and/or performs an action, the instruction and/or action is conducted via electrical signals. For example, when the processor retrieves or saves data from a storage medium, it may transmit out electrical signals to a read/write device of the storage medium, which may read or write structured data in the storage medium. The structured data may be transmitted to the processor in the form of electrical signals via a bus of the electronic device. Here, an electrical signal may refer to one electrical signal, a series of electrical signals, and/or a plurality of discrete electrical signals.

FIG. 2 illustrates a schematic diagram illustrating exemplary hardware and/or software components of a computing device on which the server 110, the requester terminal 130 and/or the provider terminal 140 may be implemented according to some embodiments of the present disclosure. For example, the processing device 112 may be implemented on the computing device 200 and configured to perform functions of the processing device 112 disclosed in this disclosure.

The computing device 200 may be a special purpose computer in some embodiments. The computing device 200 may be used to implement the online to offline service system 100 for the present disclosure. The computing device 200 may implement any component that performs one or more functions disclosed in the present disclosure. In FIGs. 1-2, only one such computing device is shown purely for convenience purposes. One of ordinary skill in the art would understand that the computer functions relating to the operation indicator estimation as described herein may be implemented in a distributed fashion on a number of similar platforms, to distribute the processing load.

The computing device 200 may include a communication ports (COM ports) 250 connected to and from a network (e.g., the network 120) connected thereto to facilitate data communications. The computing device 200 may also include a processor 220, in the form of one or more processors, for executing program instructions. The exemplary computer platform may include an internal communication bus 210, a program storage and a data storage of different forms, for example, a disk 270, and a read only memory (ROM) 230, or a random access memory (RAM) 240, for various data files to be processed and/or transmitted by the computer. The exemplary computer platform may also include program instructions stored in the ROM 230, the RAM 240, and/or other types of non-transitory storage medium to be executed by the processor 220. The methods and/or processes of the present disclosure may be implemented as the program instructions. The computing device 200 also includes an I/O component 260, supporting input/output between the computing device 200 and other components. Moreover, the computing device 200 may receive programs and data via the communication network.

Merely for illustration, only one processor 220 is described in the computing device 200. However, it should be noted that the computing device 200 in the present disclosure may also include multiple processors, thus operations and/or method steps that are performed by one processor 220 as described in the present disclosure may also be jointly or separately performed by the multiple processors. For example, if in the present disclosure the processor 220 of the computing device 200 executes both operation A and operation B, it should be understood that operation A and operation B may also be performed by two different processors jointly or separately in the computing device 200 (e.g., the first processor executes operation A and the second processor executes operation B, or the first and second processors jointly execute operations A and B) .

FIG. 3 is a schematic diagram illustrating exemplary hardware and/or software components of an exemplary mobile device according to some embodiments of the present disclosure. As illustrated in FIG. 3, the mobile device 300 may include a camera 305, a communication platform 310, a display 320, a graphic processing unit (GPU) 330, a central processing unit (CPU) 340, an I/O 350, a memory 360, a mobile operating system (OS) 370, application (s) 380, and a storage 390. In some embodiments, any other suitable component, including but not limited to a system bus or a controller (not shown) , may also be included in the mobile device 300.

In some embodiments, the mobile operating system 370 (e.g., iOS ^TM, Android ^TM, Windows Phone ^TM, etc. ) and one or more applications 380 may be loaded into the memory 360 from the storage 390 in order to be executed by the CPU 340. The applications 380 may include a browser or any other suitable mobile apps for receiving and rendering information relating to image processing or other information from the online to offline service system 100. User interactions with the information stream may be achieved via the I/O 350 and provided to the storage device 160, the server 110 and/or other components of the online to offline service system 100. In some embodiments, the mobile device 300 may be an exemplary embodiment corresponding to the requester terminal 130 or the provider terminal 140.

To implement various modules, units, and their functionalities described in the present disclosure, computer hardware platforms may be used as the hardware platform (s) for one or more of the elements described herein. The hardware elements, operating systems and programming languages of such computers are conventional in nature, and it is presumed that those skilled in the art are adequately familiar therewith to adapt those technologies to operation indicator estimation as described herein. A computer with user interface elements may be used to implement a personal computer (PC) or other types of work station or terminal device, although a computer may also act as a server if appropriately programmed. It is believed that those skilled in the art are familiar with the structure, programming and general operation of such computer equipment and as a result, the drawings should be self-explanatory.

One of ordinary skill in the art would understand that when an element (or component) of the online to offline service system 100 performs, the element may perform through electrical signals and/or electromagnetic signals. For example, when a server 110 processes a task, such as estimating an operation indicator of the online to offline service system 100 in a future period, the server 110 may operate logic circuits in its processor to process such task. When the server 110 completes estimating an operation indicator of the online to offline service system 100 in a future period, the processor of the server 110 may generate electrical signals encoding the operation indicator. The processor of the server 110 may then send the electrical signals to at least one data exchange port of a target system associated with the server 110. The server 110 communicates with the target system via a wired network, the at least one data exchange port may be physically connected to a cable, which may further transmit the electrical signals to an input port (e.g., an information exchange port) of the requester terminal 130. If the server 110 communicates with the target system via a wireless network, the at least one data exchange port of the target system may be one or more antennas, which may convert the electrical signals to electromagnetic signals. Within an electronic device, such as the requester terminal 130, the provider terminal 140, and/or the server 110, when a processor thereof processes an instruction, sends out an instruction, and/or performs an action, the instruction and/or action is conducted via electrical signals. For example, when the processor retrieves or saves data from a storage medium (e.g., the storage device 160) , it may send out electrical signals to a read/write device of the storage medium, which may read or write structured data in the storage medium. The structured data may be transmitted to the processor in the form of electrical signals via a bus of the electronic device. Here, an electrical signal may be one electrical signal, a series of electrical signals, and/or a plurality of discrete electrical signals.

FIG. 4 is a block diagram illustrating an exemplary processing device according to some embodiments of the present disclosure. In some embodiments, the processing device 112 may be implemented on a computing device 200 (e.g., the processor 220) illustrated in FIG. 2 or a CPU 340 as illustrated in FIG. 3. As shown in FIG. 4, the processing device 112 may include an obtaining module 410, a clustering module 420, a determination module 430, and an estimation module 440. Each of the modules described above may be a hardware circuit that is designed to perform certain actions, e.g., according to a set of instructions stored in one or more storage media, and/or any combination of the hardware circuit and the one or more storage media.

The obtaining module 410 may be configured to obtain a plurality of routes associated with a plurality of orders provided by an online to offline platform in a historical period. The online to offline platform may provide online to offline services (e.g., a transport service) for users implemented as the online to offline service system 100 as described elsewhere in the present disclosure (e.g., FIG. 1 and the descriptions thereof) . An order provided by the online to offline platform may be a taxi-hailing order, an express car order, a carpooling order, a goods delivery order, or a short-term driver-renting order, etc. As used herein, the term “order” may include information associated with the order, also referred to as order information. The order information may include information associated with a service requestor (e.g., a passenger who requests for a service) , information associated with a service provider (e.g., a driver who provides the service for the passenger) , information of a route associated with the order (e.g., a starting location of the route, a destination of the route, a travel distance of the route, a travel duration of the route, an arrival time of the route, etc. ) , price information associated with the order (e.g., an order price, a cost of the order, etc. ) , discount information associated with the order, etc. In some embodiments, order information may also be referred to as route information. In some embodiments, the obtaining module 410 may obtain the plurality of orders in the historical period from any database or storage device (e.g., the storage device 160, the ROM 230, the RAM 240, etc. ) .

The clustering module 420 may be configured to cluster the plurality of routes into multiple groups based on one or more features associated with each of the plurality of routes. Each group of the multiple groups may include one or more routes. In some embodiments, the one or more features associated with a route may include a starting location, a destination, a travel distance, a travel duration, a travel time, a departure time, an order price, a cost, a discount, or the like, or any combination thereof. In some embodiments, the clustering module 420 may determine the one or more features associated with a route based on the order information. In some embodiments, routes in each of the multiple groups may have similar or identical features. As used herein, similar or identical features of two routes may refer to that a difference between features of the two routes may be less than a threshold or in a range.

In some embodiments, the clustering module 420 may cluster the plurality of routes into the multiple groups using a clustering algorithm, for example, a density-based clustering algorithm, a partition-based clustering algorithm, a hierarchical-based clustering algorithm, a grid-based clustering algorithm, a model-based algorithm, etc. The clustering module 420 may cluster the plurality of routes into the multiple groups based on a similarity degree between two routes among the plurality of routes. In some embodiments, the clustering module 420 may determine the similarity degree between two routes based on a distance, such as a Euclidean distance, a Manhattan distance, a Minkowski distance, etc. In some embodiments, the clustering module 420 may cluster the plurality of routes into the multiple groups based on the distance between two routes among the plurality of routes.

In some embodiments, the clustering module 420 may determine a similarity degree between two routes among the plurality of routes based on the one or more features of each of the two routes. In some embodiments, the clustering module 420 may use an M-dimensional feature vector to represent each of the plurality of routes based on the one or more features associated with each of the plurality of routes. The clustering module 420 may determine a similarity degree between two routes by determining a similarity degree between two feature vectors of the two routes. M may be an integer greater than or equal to 2. The M-dimensional feature vector of a route may include a plurality of elements. Each of the plurality of elements may represent a feature of the route.

In some embodiments, the clustering module 420 may represent each of the plurality of routes with a point in an N-dimensional coordinate system based on the one or more features associated with each of the plurality of routes. The clustering module 420 may determine a similarity degree between two routes by determining a distance between two points representing the two routes. N may be an integer greater than, or equal to 3. As used herein, coordinates of a point in an N-dimensional coordinate system may include N (N ≥ 3) factors. A factor may also be referred to as a coordinate of a point in the N-dimensional coordinate system. In some embodiments, a feature of a route may be represented by one or more factors. In some embodiments, the clustering module 420 may represent a specific route with a specific point in the N-dimensional coordinate system based on the geographical coordinates of the starting location and/or the destination of the specific route in the geographic coordinate system.

In some embodiments, the clustering module 420 may cluster the plurality of routes into the multiple groups in the N-dimensional coordinate system. In some embodiments, a distance between two points representing two routes may represent a level of similarity between the two routes. In some embodiments, a distance between two points representing two routes belonging to a same group in the N-dimensional coordinate system may be lower than a distance threshold. In some embodiments, the points representing two routes belonging to a same group may form an area in the N-dimensional space. In some embodiments, the points in an area may also form one cluster, i.e., group. The area may include a center point. A distance between each point in the area and the center point may be less than a distance between each point in the area and another center point in another area.

The determination module 430 may be configured to determine a model for estimating one or more operation indicators of the online to offline platform based on the one or more routes in at least a portion of the multiple groups. As used herein, an operation indicator of the online to offline platform may refer to a performance indicator that may be used to assess operation benefits of the online to offline platform. In some embodiments, the one or more operation indicators may include an order count, a gross merchandise volume (GMV) , a gross margin, a gain and loss rate, a carpooling order conversion rate, a carpooling order elasticity, an average price, an average discount, a practice price, a discount, a discount change amount, a billing ratio, or the like, or any combination thereof. An operation indicator may be associated with one or more price parameters, one or more distance (or mileage) parameters, etc. A relationship between a specific operation indicator and the one or more price parameters and/or distance parameters may be expressed using a function with the specific operation indicator as a dependent variable, one or more price parameters and/or distance parameters as one or more independent variables. In some embodiments, the one or more price parameters may include an average price, an average discount, a payment price of a service requester (i.e., order price) , a discount, a discount change amount, a ratio of a driver’s receivable amount to a passenger’s payable amount, a maximum price, a price of a starting distance, the unit price of distances excluding the corresponding starting distance, or the like, or any combination thereof. In some embodiments, the one or more distance parameters may include a starting distance, a total mileage, distances excepting the starting distance, or the like, or any combination thereof.

In some embodiments, the determination module 430 may determine the model for estimating a specific operation indicator statistically using a fitting technique based on the multiple groups of the plurality of routes clustered by the clustering module 420. Exemplary fitting techniques may include using a line regression model, a gradient boost decision tree (GBDT) model, a support vector machine (SVM) model, a naive Bayesian model, an extreme gradient boosting (XGBOOST) model, a causal model, or the like, or any combination thereof. In some embodiments, the determination module 430 may determine a value of the specific operation indicator (e.g., the total order count) of each of the multiple groups of the plurality of routes. The determination module 430 may obtain a value of each of the one or more price parameters (e.g., the discount, an average price for routes in each of the multiple groups) corresponding to each group of the multiple groups of the plurality of routes. The determination module 430 may obtain multiple values of the specific operation indicator (e.g., the total order count) and corresponding values of the one or more price parameters (e.g., the discount, an average price for routes in each of the multiple groups) . The determination module 430 may determine the model for estimating the specific operation indicator using the fitting technique based on the values of the specific operation indicator and the values of the one or more price parameters corresponding to the multiple groups of the plurality of routes. In some embodiments, using the fitting technique, the determination module 430 may determine the estimation model for estimating a specific operation indicator by performing a plurality of iterations (i.e., a training process) to update one or more learning parameters of the estimation model. In some embodiments, the determination module 430 may determine the estimation model for estimating a specific operation indicator based on a least-squares technique. In some embodiments, the determination module 430 may transmit the estimation model to the storage device 160, the storage 390, or any other storage device for storage.

In some embodiments, the determination module 430 may determine a model for estimating a first operation indicator (e.g., the total order count) based on one or more sub-models. Each of the one or more sub-models may be configured to provide a relationship between a second operation indicator (e.g., the carpooling order conversation rate, the carpooling order elasticity) , the one or more price parameters and/or one or more distance parameters. A sub-model for estimating the second operation indicator may be determined using a fitting technique as described elsewhere in the present disclosure. In some embodiments, the first operation indicator may be a GMV of the online to offline platform, and the second operation indicator may include a carpooling order conversion rate. The determination module 430 may determine a historical value of a carpooling order conversion rate corresponding to each of the multiple groups and a corresponding discount based on the one or more routes in each of the multiple groups.

The estimation module 440 may be configured to determine an operation indicator of the online to offline platform in a future period based on the model for estimating one or more operation indicators of the online to offline platform. In some embodiments, the estimation module 440 may input a pre-determined price parameter (e.g., a discount, a discount change amount, etc. ) in a certain time period (e.g., a future period) into the model for estimating a specific operation indicator. The value of the pre-determined price parameter may be a default setting of the online to offline service system 100. The model for estimating the specific operation indicator may calculate the value of the specific operation indicator corresponding to the pre-determined price parameter. The model for estimating the specific operation indicator may output a value of the specific operation indicator corresponding to the pre-determined price parameter.

In some embodiments, the estimation module 440 may determine an optimal value of a specific operation indicator based on the model for estimating the specific operation indicator under one or more constraint conditions. The estimation module 440 may determine a constraint condition based on the multiple groups of the plurality of routes. The constraint condition may be related to the price parameter, one or more additional parameters (e.g., distance parameters, etc. ) . In some embodiments, a constraint condition may be such that a price parameter satisfies a condition. In some embodiments, a constraint condition may include that an additional operation indicator (also referred to as a third operation indicator) satisfies a condition. In some embodiments, the estimation module 440 may determine the third operation indicator based on a constraint function with the third operation indicator as a dependent variable, and the price parameter and/or the one or more additional parameters as independent variables. In some embodiments, the constraint function may be determined statistically using a fitting technique based on the multiple groups of the plurality of routes clustered by the clustering module 420. In some embodiments, the estimation module 440 may determine the value of the specific operation indicator based on the constraint function according to the estimation model.

It should be noted that the above description is merely provided for the purposes of illustration, and not intended to limit the scope of the present disclosure. Apparently, for persons having ordinary skills in the art, multiple variations and modifications may be conducted under the teachings of the present disclosure. However, those variations and modifications do not depart from the scope of the present disclosure. For example, the processing device 112 may further include a storage module (not shown in FIG. 4) . The storage module may be configured to store data and information associated with operation indicators. As another example, the clustering module 420 and the determination module 430 may be integrated into one module.

FIG. 5 is a schematic flowchart illustrating an exemplary process for estimating an operation indicator according to some embodiments of the present disclosure. The process 500 may be executed by the online to offline service system 100. For example, the process 500 may be implemented as a set of instructions (e.g., an application) stored in the storage device 160, ROM 230 or RAM 240, or storage 390. The processing device 112, the processor 220 and/or the CPU 340 may execute the set of instructions, and when executing the instructions, the processing device 112, the processor 220 and/or the CPU 340 may be configured to perform the process 500. The operations of the illustrated process presented below are intended to be illustrative. In some embodiments, the process 500 may be accomplished with one or more additional operations not described and/or without one or more of the operations discussed. Additionally, the order in which the operations of the process 500 illustrated in FIG. 5 and described below is not intended to be limiting.

In 510, the processing device 112 (e.g., the obtaining module 410) may obtain a plurality of routes associated with a plurality of orders provided by an online to offline platform in a historical period. The online to offline platform may provide online to offline services (e.g., a transport service) for users implemented as the online to offline service system 100 as described elsewhere in the present disclosure (e.g., FIG. 1 and the descriptions thereof) . For generating an order, a service requester (e.g., a passenger) may send a request for an online to offline service via the online to offline platform associated with a client terminal (e.g., the requester terminal 130) of the service requester to the online to offline platform (e.g., a server terminal (e.g., the server 120) . A service provider (e.g., a driver) may accept the request for an online to offline service via the online to offline platform associated with a client terminal (e.g., the provider terminal 140) of the service provider and provide the online to offline service to the service requester. After the service requester pays for the online to offline service to the online to offline platform, the online to offline system 100 may store the request for the online to offline service as an order.

In some embodiments, the online to offline service may include a transport service as described elsewhere in the present disclosure (e.g., FIG. 1 and the descriptions thereof) . Exemplary transport services may include a taxi-hailing service, a chauffeur service, an express car service, a carpool service, a bus service, a driver hire service, a shuttle service, etc. A service provider may provide the transport service to a service requester by transport a subject (e.g., one or more goods, foods, etc. related to the service requester) or the service requester from a starting location to a destination along a route. An order provided by the online to offline platform may be a taxi-hailing order, an express car order, a carpooling order, a goods delivery order, or a short-term driver-renting order, etc. In some embodiments, an order in a historical period may be denoted as a historical order. The plurality of historical orders may be generated within a pre-determined time period. For example, the plurality of historical orders may include orders generated in a year (e.g., the last year, the current year, the recent one year) , a half of a year (e.g., the recent six months, the first half of the current year) , a quarter of a year (e.g., the recent three months, the second quarter of the current year) , or the like, or any combination thereof. In some embodiments, the plurality of orders in the historical period may be obtained from any database or storage (e.g., the storage device 160, the ROM 230, the RAM 240, etc. ) .

As used herein, the term “order” may include information associated with the order, also referred to as order information. The order information may include information associated with a service requestor (e.g., a passenger who requests for a service) , information associated with a service provider (e.g., a driver who provides the service for the passenger) , information of a route associated with the order (e.g., a starting location of the route, a destination of the route, a travel distance of the route, a travel duration of the route, an arrival time of the route, etc. ) , price information associated with the order (e.g., an order price, a cost of the order, etc. ) , discount information associated with the order, etc. As used herein, an order price associated with an order may refer to a price that a service requester needs to pay to the online to offline platform for the service associated with the order. A cost associated with the order may be referred to as an expense that the online to offline platform needs to spend for the order. In some embodiments, a cost associated with the order may include a revenue (or a receivable amount) of a driver (or a service provider) . A route associated with an order may be referred to as a trajectory for a service provider traveling from a starting location to a destination to finish the order. In some embodiments, order information may also be referred to as route information. For example, starting location information associated with an order may be starting location information associated with a route. As another example, discount information associated with an order may be discount information associated with a route.

In 520, the processing device 112 (e.g., the clustering module 420) may cluster the plurality of routes into multiple groups based on one or more features associated with each of the plurality of routes. Each group of the multiple groups may include one or more routes. In some embodiments, the one or more features associated with a route may include a starting location, a destination, a travel distance, a travel duration, a travel time, a departure time, an order price, a cost, a discount, or the like, or any combination thereof. In some embodiments, the one or more features associated with a route may be determined based on the order information as described in operation 510. In some embodiments, the routes in each of the multiple groups may have similar or identical features. As used herein, similar or identical features of two routes may refer to that a difference between features of the two routes may be less than a threshold or in a range. For example, a cost for each route in a group may be the same or similar. In other words, a difference of costs of two routes in a same group may be less than a threshold, such as less than 1 RMB, or less than 2 RMB, or less than 3 RMB, etc., or in a range, such as 0-1 RMB, 0-2 RMB, 0-3 RMB, etc. As another example, an order price of each route in a group may be the same or similar. In other words, a difference of order prices of two routes in a same group may be less than 1 RMB, or less than 2 RMB, or less than 3 RMB, etc., or in a range, such as 0-1 RMB, 0-2 RMB, 0-3 RMB, etc. As a further example, a discount of each route in a group may be the same or similar. In other words, a difference of discounts of two routes in a same group may be less than a threshold, such as less than 0.05, or less than 0.1, or less than 0.15, etc., or in a range, such as 0-0.05, 0-0.1, 0-0.15, etc.

In some embodiments, the processing device 112 may cluster the plurality of routes into the multiple groups using a clustering algorithm. Exemplary clustering algorithms may include a density-based clustering algorithm, a partition-based clustering algorithm, a hierarchical-based clustering algorithm, a grid-based clustering algorithm, a model-based algorithm, or the like, or any combination thereof. Exemplary density-based clustering algorithms may include a density-based spatial clustering of applications with noise (DBSCAN) algorithm, a maximum density clustering algorithm (MDCA) , an ordering points to identify the clustering structure (OPTICS) algorithm, a density clustering (DENCLUE) algorithm, a hierarchical DBSCAN algorithm, etc. Exemplary partition-based clustering algorithms may include a k-means algorithm, a k-medoids algorithm, a k-nearest neighbor (KNN) algorithm, etc. Exemplary hierarchical-based clustering algorithms may include an agglomerative nesting (AGENS) algorithm, a divisive analysis (DIANA) algorithm, a balanced iterative reducing and clustering using hierarchies (BIRCH) algorithm, a clustering using representative (CURE) algorithm, etc. Exemplary grid-based clustering algorithms may include a statistical information grid-based (STING) clustering algorithm, a clustering in quest (CLIQUE) algorithm, a clustering with wavelets (WAVECLUSTER) algorithm, etc. Exemplary model-based algorithms may include a Gaussian mixture model (GMM) , etc.

The processing device 112 may cluster the plurality of routes into the multiple groups based on a similarity degree between two routes among the plurality of routes. For example, the processing device 112 may cluster two routes among the plurality of routes whose similarity degree greater than a threshold into the same group. As another example, the processing device 112 may cluster two routes whose similarity degree greater than a similarity degree between one of the two routes and each of other routes among the plurality of routes into the same group. In some embodiments, the similarity degree between two routes may be determined based on a distance, such as a Euclidean distance, a Manhattan distance, a Minkowski distance, etc. In some embodiments, the processing device 112 may cluster the plurality of routes into the multiple groups based on the distance between two routes among the plurality of routes.

In some embodiments, the processing device 112 may determine a similarity degree between two routes among the plurality of routes based on the one or more features of each of the two routes. In some embodiments, the processing device 112 may use an M-dimensional feature vector to represent each of the plurality of routes based on the one or more features associated with each of the plurality of routes. The processing device 112 may determine a similarity degree between two routes by determining a similarity degree between two feature vectors of the two routes. M may be an integer greater than or equal to 2. The M-dimensional feature vector of a route may include a plurality of elements. Each of the plurality of elements may represent a feature of the route. For example, the M-dimensional feature vector of a route may be a 5-dimensional feature vector including a starting location of the route, a destination of the route, a travel distance of the route, a travel duration of the route, and a departure time of the route. As another example, the M-dimensional feature vector of a route may be a 2-dimensional feature vector including a starting location of the route and a destination of the route. As still another example, the M-dimensional feature vector of a route may be a 3-dimensional feature vector including a starting location of the route, a destination of the route, and a travel duration of the route. A location in the feature vector (e.g., the starting location of the route, the destination of the route) of a route may be denoted by an address name, a location name, geographical coordinates (e.g., the longitude and latitude) , etc.

In some embodiments, the processing device 112 may represent each of the plurality of routes with a point in an N-dimensional coordinate system based on the one or more features associated with each of the plurality of routes. The processing device 112 may determine a similarity degree between two routes by determining a distance between two points representing the two routes. N may be an integer greater than, or equal to 3. As used herein, coordinates of a point in an N-dimensional coordinate system may include N (N ≥ 3) factors. A factor may also be referred to as a coordinate of a point in the N-dimensional coordinate system. In some embodiments, a feature of a route may be represented by one or more factors. For example, the starting location (or the destination) of a specific route may be represented by a geographic coordinate system with two or more geographical coordinates (e.g., latitude and longitude coordinates) . The starting location (or the destination) of the specific route may be represented by two or more factors in the N-dimensional coordinate system based on the two or more geographical coordinates (e.g., latitude and longitude coordinates) of the starting location. In other words, the starting location, the destination, etc., may be represented, respectively by two or more coordinates of a point in the N-dimensional coordinate system. As another example, the departure time, the arrival time, the travel distance, the travel duration, the cost of an order associated with the specific route, etc., may be represented, respectively by one single factor in the N-dimensional coordinate system. In other words, the departure time, the arrival time, the travel distance, the travel duration, the cost of an order associated with the specific route, etc., may be represented, respectively by one single coordinate of a point in the N-dimensional coordinate system.

In some embodiments, a specific route may be represented with a specific point in the N-dimensional coordinate system based on the geographical coordinates of the starting location and/or the destination of the specific route in the geographic coordinate system. For example, the specific route may be represented with the specific point in a four-dimensional coordinate system including four coordinates (i.e., four factors denoted as (X _s, Y _s, X _d, Y _d) , wherein X _s and Y _s refer to a latitude and a longitude of the starting location, respectively; X _d and Y _d refer to a latitude and a longitude of the destination, respectively. ) . As another example, the specific route may be represented with the specific point in a three-dimensional coordinate system including three coordinates (i.e., factors denoted as (X _s, Y _s, T _d) , wherein X _s and Y _s refer to a latitude and a longitude of the starting location, respectively; and T _d refers to the arrival time. As still another example, the specific route may be represented with the specific point in an N-dimensional coordinate system including at least five coordinates (i.e., factors denoted as (X _s, Y _s, X _d, Y _d, T _s, T _d, D, T, C, …, etc. ) , wherein X _s and Y _s refer to a latitude and a longitude of the starting location, respectively; X _d and Y _d refer to a latitude and a longitude of the destination, respectively; and T _s, T _d, D, T, and C refer to the departure time, the arrival time, the travel distance, the travel duration, the cost of an order associated with the specific route, respectively) .

In some embodiments, the processing device 112 may cluster the plurality of routes into the multiple groups in the N-dimensional coordinate system. Merely by ways of example, the processing device 112 may cluster the plurality of routes into the multiple groups using a density-based clustering model. In some embodiments, using the density-based clustering model, the processing device 112 may represent each of the plurality of routes with a point in the N-dimensional coordinate system, also referred to as an N-dimensional space. Then processing device 112 may cluster the points representing the plurality of routes into the multiple groups based on locations of the points in the N-dimensional space using the density-based clustering model. In some embodiments, a distance between two points representing two routes may represent a level of similarity (i.e., similarity degree) between the two routes. In some embodiments, a distance between two points representing two routes belonging to a same group in the N-dimensional coordinate system may be lower than a distance threshold. In some embodiments, the points representing two routes belonging to a same group may form an area in the N-dimensional space. In some embodiments, the points in an area may also form one cluster, i.e., group. The area may include a center point. A distance between each point in the area and the center point may be less than a distance between each point in the area and another center point in another area. Taking the DBSCAN algorithm as an example, one or more parameters of the DBSCAN algorithm may be preset, such as a minimum number or count of points (MinPts) and a scanning radius denoted as an epsilon (Eps) . The processing device 112 may obtain a specific point representing a route. The processing device 112 may determine points in an area within the Eps from the specific point. The processing device 112 may determine the specific point as a core point (or center point) if the number or count of points within the area exceeds the MinPts. The processing device 112 may determine a cluster including the points and the specific point if the number or count of points within the area exceeds the MinPts. The processing device 112 may determine two clusters into one cluster if the distance of core points of the two clusters within the Eps. More descriptions for clustering the plurality of routes based on the distance between two points corresponding to any two of the plurality of routes in the N-dimensional coordinate system may be found in FIG. 6 and the descriptions thereof.

In some embodiments, the processing device 112 may determine two or more certain groups that satisfy a first condition from the multiple groups. The processing device 112 may re-cluster one or more certain routes that satisfy a second condition in each of the two or more groups into one or more additional groups. The one or more additional groups and at least a portion of the multiple groups may be used to estimate the model in operation 530. In some embodiments, the first condition may include that an average value of a certain feature (e.g., a travel duration, a travel distance, an order price, etc. ) of routes in a specific group is within a range, or exceeding a first threshold, or less than the first threshold, etc. For example, the processing device 112 may determine an average travel distance of routes in each of the multiple groups based on travel distances of the routes in each of the multiple groups. The processing device 112 may determine the one or more certain groups whose average travel distances are within a travel distance range, such as 13-15 km, or 15-18 km, or 18-20 km, or 10-23 km, etc. In some embodiments, the second condition may include that a value of the certain feature of a route in a certain group exceeds the range, or is lower than the first threshold, or exceeds the second threshold, etc. A certain route in a certain group satisfying the second condition may be also referred to as a normal route. A route in a certain group not satisfying the second condition may be also referred to as an abnormal route. For example, the processing device 112 may determine the one or more certain routes (i.e., normal routes) from a certain group whose travel distances are within the travel distance range, such as 13-15 km, or 15-18 km, or 18-20 km, or 10-23 km, etc. In some embodiments, the second condition may include that a difference between a value of the certain feature of a route in a certain group and the average value of the certain feature of the routes in the certain group may exceed a third threshold. For example, the processing device 112 may determine a route whose cost is within 10%difference from an average cost of the certain group as a normal route. In some embodiments, the processing device 112 may remove one or more abnormal routes from each of the one or more certain groups. The processing device 112 may cluster the one or more normal routes in each of the several certain groups that satisfy the first condition into the same group.

In some embodiments, the processing device 112 may assign the one or more normal routes that satisfy the second condition from each of the several certain groups into a same additional group. In some embodiments, the processing device 112 may re-cluster the one or more normal routes in each of the several certain groups that satisfy the first condition into different additional groups. In some embodiments, the processing device 112 may re-cluster the one or more normal routes in each of the several certain groups that satisfy the first condition based on the certain feature associated with each of the one or more certain routes. For example, the processing device 112 may cluster a plurality of certain routes in the several certain groups having a same or close value of the certain feature into a same group. As another example, if a travel distance of a certain route in a group is 25 km, and a travel distance of another certain route in another group is about 25 km, the processing device 112 may cluster the two certain routes into a same group. As used herein, “close to or same” may indicate that the deviation of two values does not exceed a threshold, e.g., 20%, or 15%, or 10%, or 5%, or 1%of one of the two similarity degrees. Accordingly, the homogeneity and statistical stability of routes belonging to a same group may be improved. As used herein, the homogeneity of routes belonging to a same group may refer to that the routes includes one or more similar features. The statistical stability of routes belonging to a same group may be associated with at least one of a volatility and discreteness. The multiple groups of routes may include different homogeneities in different features. For example, an order price associated with a route may be determined based on a travel distance of the route. A group of routes including similar or same travel distances may have the homogeneity in order price. But a price sensitivity of a user for an order may be associated with time. A user may have a low price sensitivity in the morning rush hour and in the evening rush hour. A group of routes including a similar or same time period may have the homogeneity in price sensitivity. According to the present disclosure, the processing device 112 may remove or filter routes (i.e., abnormal routes) that does not satisfy the second condition as described above from a portion of the multiple groups which may improve the homogeneity of each of the portion of the multiple groups. Data in each of the portion of the multiple groups may be sparse. The processing device 112 may re-cluster the portion of the multiple groups excluding the abnormal routes, which may improve the statistical stability of routes.

In 530, the processing device 112 (e.g., the determination module 430) may determine a model for estimating one or more operation indicators of the online to offline platform based on the one or more routes in at least a portion of the multiple groups. As used herein, an operation indicator of the online to offline platform may refer to a performance indicator that may be used to assess operation benefits of the online to offline platform. In some embodiments, the one or more operation indicators may include an order count, a gross merchandise volume (GMV) , a gross margin (e.g., a carpooling gross margin) , a gain and loss rate, a carpooling order conversion rate, a carpooling order elasticity, an average price, an average discount, a practice price, a discount, a discount change amount, a billing ratio, or the like, or any combination thereof. As used herein, an order count may refer to the number of orders (e.g., carpooling orders, total orders including express car orders and carpooling orders, etc. ) . A carpooling order elasticity may refer to a ratio of the carpooling order count and the total order count. A carpooling order conversion rate may refer to a probability that a service requester initiates a carpooling order according to the one or more price parameters. In some embodiments, a carpooling order conversion rate may be determined based on a carpooling order count and a total order count of each of the multiple groups. For example, the carpooling order count of a group may be x, the total order count of the group may be y. The processing device 112 may determine the carpooling order conversion rate as

The billing ratio may be denoted as a ratio of a receivable amount of a service provider (e.g., a driver) to a sum of payable amounts of one or more service requesters (or e.g., carpooling passengers) for a carpooling order. For example, for a specific carpooling order having two carpooling passengers, the online to offline platform may determine the receivable amount of the driver associated with the specific carpooling order as 40 RMB, and determine a first payable amount of one carpooling passenger as 30 RMB and a second payable amount of another carpooling passenger as 50 RMB. The processing device 112 may determine the billing ratio as 0.5.

An operation indicator may be associated with one or more price parameters, one or more distance (or mileage) parameters, etc. A relationship between a specific operation indicator and the one or more price parameters and/or distance parameters may be expressed using a function with the specific operation indicator as a dependent variable, one or more price parameters and/or distance parameters as one or more independent variables. In some embodiments, the one or more price parameters may include an average price, an average discount, a payment price of a service requestor, a discount, a discount change amount, a ratio of a driver’s receivable amount to a passenger’s payable amount, a maximum price, a price of a starting distance, the unit price of distances excluding the corresponding starting distance, or the like, or any combination thereof. In some embodiments, the one or more distance parameters may include a starting distance, a total mileage, distances excepting the starting distance, or the like, or any combination thereof.

In some embodiments, the model for estimating a specific operation indicator of the online to offline platform may be configured to determine, provide, and/or describe a relationship between the specific operation indicator and the one or more price parameters. The model for estimating the specific operation indicator of the online to offline platform may also be referred to as an estimation model for the specific operation indicator in the present disclosure. In some embodiments, the model for estimating a specific operation indicator of the online to offline platform may be expressed using an objective function with the specific operation indicator as a dependent variable and one or more price parameters as one or more independent variables.

In some embodiments, the model for estimating a specific operation indicator may be determined statistically using a fitting technique based on the multiple groups of the plurality of routes clustered in operation 520. Exemplary fitting techniques may include using a line regression model, a gradient boost decision tree (GBDT) model, a support vector machine (SVM) model, a naive Bayesian model, an extreme gradient boosting (XGBOOST) model, a causal model, or the like, or any combination thereof. In some embodiments, the processing device 112 may determine a value of the specific operation indicator (e.g., the total order count) of each of the multiple groups of the plurality of routes. The processing device 112 may obtain a value of each of the one or more price parameters (e.g., the discount, an average price for routes in each of the multiple groups) corresponding to each group of the multiple groups of the plurality of routes. For example, the processing device 112 may determine a value of a specific price parameter (e.g., the discount) corresponding to a specific group by averaging values of the specific price parameter of routes in the group. The processing device 112 may obtain multiple values of the specific operation indicator (e.g., the total order count) and corresponding values of the one or more price parameters (e.g., the discount, an average price for routes in each of the multiple groups) . The processing device 112 may determine the model for estimating the specific operation indicator using the fitting technique based on the values of the specific operation indicator and the values of the one or more price parameters corresponding to the multiple groups of the plurality of routes. For example, the specific operation indicator may be a GMV of the online to offline platform. The processing device 112 may determine a historical value of a GMV for one or more routes in each of the multiple groups based on prices of orders associated with the one or more routes in each of the multiple groups. The processing device 112 may determine a discount corresponding to each group of the multiple groups. The discount corresponding to each of the multiple groups may be determined based on a discount for each of the orders associated with the one or more routes in the each group of the multiple groups. For example, the discount for each of orders associated with the one or more routes in the each group of the multiple groups may be the same or similar. The processing device 112 may determine one of the discounts of the orders associated with the one or more routes in a specific group as the discount corresponding to the specific group. As another example, the processing device 112 may determine an average of the discounts of the orders associated with the one or more routes in a specific group as the discount corresponding to the specific group. The processing device 112 may determine the model for estimating the GMV using the fitting technique based on historical values of the GMV and discounts corresponding to the multiple groups of the plurality of routes.

In some embodiments, the processing device 112 may determine a model for estimating a first operation indicator (e.g., the total order count) based on one or more sub-models. Each of the one or more sub-models may be configured to provide a relationship between a second operation indicator (e.g., the carpooling order conversation rate, the carpooling order elasticity) , the one or more price parameters and/or one or more distance parameters. In some embodiments, a sub-model may be also referred to as a component of the model for estimating the first operation indicator. A sub-model for estimating the second operation indicator may be determined using a fitting technique as described elsewhere in the present disclosure. For example, the fitting technique used for determining the sub-model may include using a linear regression model, a deep causal model, etc. The processing device 112 may determine a value of the second operation indicator of each group of the multiple groups of the plurality of routes. The processing device 112 may obtain a value of a specific price parameter (e.g., the discount) and/or a value of a specific distance parameter (e.g., the total mileage or travel distance) corresponding to each group of the multiple groups of the plurality of routes. The specific distance parameter corresponding to each of the multiple groups may be determined based on the specific distance parameter for each of orders associated with the one or more routes in the each group of the multiple groups. For example, the specific distance parameter for each of orders associated with the one or more routes in the each group of the multiple groups may be the same or similar. The processing device 112 may determine one of values of the specific distance parameter of orders associated with the one or more routes in a specific group as the value of the specific distance parameter corresponding to the specific group. As another example, the processing device 112 may determine an average of the values of the specific distance parameter of orders associated with the one or more routes in a specific group as the value of the specific distance parameter corresponding to the specific group. The processing device 112 may determine the sub-model for estimating the second operation indicator using the fitting technique based on the value of the second operation indicator, the value of the one or more price parameters and/or the values of the one or more price distance parameters corresponding to each of the multiple groups of the plurality of routes. In some embodiments, the first operation indicator may be a GMV of the online to offline platform, and the second operation indicator may include a carpooling order conversion rate. The processing device 112 may determine a historical value of a carpooling order conversion rate corresponding to each of the multiple groups and a corresponding discount based on the one or more routes in each of the multiple groups. For example, the processing device 112 may determine the historical value of the carpooling order conversion rate corresponding to each of the multiple groups based on a ratio of a carpooling order count and an express car order count (or total order count) corresponding to each of the multiple groups. The processing device 112 may determine the model for estimating the carpooling order conversion rate using the fitting technique based on the historical value of the carpooling order conversion rate corresponding to each of the multiple groups and the corresponding discount.

In some embodiments, the estimation model for estimating a specific operation indicator may be obtained based on a least-squares technique. Using a least-squares technique, the processing device 112 may determine a value of the specific operation indicator of each group of the multiple groups of the plurality of routes. The processing device 112 may obtain the one or more price parameters (e.g., the discount, an average price for routes in each of the multiple groups) corresponding to each group of the multiple groups of the plurality of routes. Each group of the multiple groups of the plurality of routes may be denoted as p _i (x _i, y _i) , wherein i≤N, N refers to the count of the multiple groups, p _i refers to the ith group of the multiple groups, x _i refers to a value of the corresponding price parameter of the ith group of the multiple groups, and y _i refers to the value of the specific operation indicator of the ith group of the multiple groups. The estimation model for estimating the specific operation indicator may be denoted as Equation (1) as follows:

y=f (x; α ₁, α ₂, α ₃, α ₄, …, α _n) (1) ,

where n may be less than N, α ₁, α ₂, α ₃, α ₄, …, α _n refer to the one or more parameters of the estimation model for estimating the specific operation indicator. The one or more parameters (or α ₁, α ₂, α ₃, α ₄, …, α _n) of the estimation model for estimating the specific operation indicator may be determined when a fitting condition is satisfied. The fitting condition may include minimizing the sum of the absolute values of the deviations determined according to Equation (2) , minimizing the absolute value of the maximum deviation determined according to Equation (3) , minimizing the sum of the squares of the deviations determined according to Equation (4) , etc., as follows:

where δ _i refers to a deviation of the ith group of the multiple groups. The estimation model for estimating the specific operation indicator may be determined according to the one or more determined parameters.

In some embodiments, using the fitting technique, the estimation model for estimating a specific operation indicator may be obtained by performing a plurality of iterations (i.e., a training process) to update one or more learning parameters of the estimation model. The value of the specific operation indicator of each of the multiple groups and the value of the corresponding price parameter of each group of the multiple groups may be also referred to as a sample. The processing device 112 may determine a plurality of samples based on the multiple groups. For each of the plurality of iterations, a specific sample may first be input into a preliminary model and a cost function. For example, the value of the specific price parameter of the specific sample may first be input into the preliminary model as an input variable, and the value of the specific operation indicator of the specific sample may be input into the preliminary model as a desired output of the preliminary model. The preliminary model (e.g., one of the one or more objective functions) may determine a predicted result corresponding to the specific operation indicator based on the value of the specific price parameter. The predict result corresponding to the specific price parameter may then be compared with the inputted value of the specific operation indicator based on a cost function. The cost function in the preliminary model may be configured to assess a difference between an estimated value (e.g., the predicted output) of the preliminary model and an actual value (e.g., the desired output or the inputted value of the specific operation indicator) . If the value of the cost function exceeds a threshold in a current iteration, parameters of the one of the preliminary model may be adjusted and updated to cause the value of the cost function (i.e., the difference between the predicted output and the inputted value of the specific operation indicator) smaller than the threshold. Accordingly, in the next iteration, another sample may be input into the preliminary model as described above. Then the plurality of iterations may be performed to update the parameters of the preliminary model until a terminated condition is satisfied. The terminated condition may provide an indication of whether the preliminary model is sufficiently trained. For example, the terminated condition may be satisfied if the value of the cost function associated with the preliminary model is minimal or smaller than a threshold (e.g., a constant) . As another example, the terminated condition may be satisfied if the value of the cost function converges. The convergence may be deemed to have occurred if the variation of the values of the cost function in two or more consecutive iterations is smaller than a threshold (e.g., a constant) . As still an example, the terminated condition may be satisfied when a specified number of iterations are performed in the training process. The estimation model may be determined based on the updated parameters. In some embodiments, the estimation model may be transmitted to the storage device 160, the storage 390, or any other storage device for storage.

Merely by ways of example, the first operation indicator may be a total carpooling order amount, and the price parameter may be a discount. The processing device 112 may determine a first sub-model providing a first relationship between a carpooling order conversion rate and the discount. The processing device 112 may determine a second sub-model providing a second relationship between a change rate of the carpooling order conversion rate with the discount and a change rate of the discount. The processing device 112 may determine the estimation model associated with the total carpooling order count and the discount based on the first sub-model and the second sub-model. The estimation model may be expressed as Equation (5) as follows:

f (d) =∑n _i× (q _i+θ _i×Δr) (5) ,

where, f (d) refers the first operation indicator, i.e., the total carpooling order count; q refers to the first sub-model; θ refers to the second sub-model; i refers to the ith route in a certain time period, such as a future period.

In some embodiments, the first relationship (i.e., the first sub-model) between the carpooling order conversion rate and the discount may be also referred to as a carpooling order conversion rate determination model. The carpooling order conversion rate determination model may be determined using a fitting technique based on the multiple groups of the plurality of routes. In some embodiments, the processing device 112 may determine a value of the carpooling order conversion rate of each of the multiple groups of the plurality of routes. The processing device 112 may obtain the one or more price parameters (e.g., the discount, an average price for routes in each of the multiple groups) corresponding to each group of the multiple groups of the plurality of routes. The processing device 112 may determine the carpooling order conversion rate determination model using the fitting technique based on the value of the carpooling order conversion rate and the one or more price parameters of each of the multiple groups of the plurality of routes. For example, the processing device 112 may determine a historical value of the carpooling order conversion rate corresponding to each of the multiple groups based on a ratio of a carpooling order count and a total order count (or an express car order count) corresponding to each of the multiple groups. The processing device 112 may obtain a discount corresponding to each group of the multiple groups of the plurality of routes. The processing device 112 may determine the carpooling order conversion rate determination model using the fitting technique based on the historical value of the carpooling order conversion rate corresponding to each of the multiple groups and the corresponding discount.

In some embodiments, the second relationship (i.e., the second sub-model) between a change rate of the carpooling order conversion rate with the discount and a change rate of the discount may be also referred to as a carpooling order elasticity model. The carpooling order elasticity model may be determined using a fitting technique based on the multiple groups of the plurality of routes. In some embodiments, the processing device 112 may determine a value of the change rate of the carpooling order conversion rate based on two groups of the multiple groups of the plurality of routes. For example, the processing device 112 may determine carpooling order conversion rates based on two groups of the multiple groups of the plurality of routes. The processing device 112 may determine a ratio of a difference between the carpooling order conversion rates and a difference between discounts corresponding to the two groups of the multiple groups of the plurality of routes. The processing device 112 may designate the ratio as the value of the change rate of the carpooling order conversion rate. The processing device 112 may obtain multiple differences between discounts corresponding to each two groups of the multiple groups of the plurality of routes. The processing device 112 may determine the carpooling order elasticity model using the fitting technique based on the values of the change rate of the carpooling order conversion rate and the multiple differences between discounts corresponding to each two groups of the multiple groups of the plurality of routes.

In 540, the processing device 112 (e.g., the estimating module 430) may determine an operation indicator of the online to offline platform in a future period based on the model for estimating one or more operation indicators of the online to offline platform. An operation indicator of the online to offline platform in a future period may be an operation indicator of the online to offline platform in a next day, a next week, a next month, a next year, etc. In some embodiments, the future period may be a preset time value stored in a storage (e.g., the storage device 160, the ROM 230, the RAM 240, etc. ) of the online to offline service system 100, or may be determined according to different application scenarios (e.g., different service types, etc. ) .

In some embodiments, the processing device 112 may input a pre-determined price parameter (e.g., a discount, a discount change amount, etc. ) in a certain time period (e.g., a future period) into the model for estimating a specific operation indicator. The value of the pre-determined price parameter may be a default setting of the online to offline service system 100. The model for estimating the specific operation indicator may calculate the value of the specific operation indicator corresponding to the pre-determined price parameter. The model for estimating the specific operation indicator may output a value of the specific operation indicator corresponding to the pre-determined price parameter. For example, according to Equation (1) , the processing device 112 may input a discount and/or a discount change rate into Equation (1) . The processing device 112 may determine a maximum value of the total order count according to Equation (1) . In some embodiments, the processing device 112 may determine an optimal value of a specific operation indicator based on the model for estimating the specific operation indicator under one or more constraint conditions. The processing device 112 may determine a constraint condition based on the multiple groups of the plurality of routes. The constraint condition may be related to the price parameter, one or more additional parameters (e.g., distance parameters, etc. ) . In some embodiments, a constraint condition may be such that a price parameter satisfies a condition. For example, a constraint condition may include that the discount or the average order price must be smaller than or greater than a price threshold. In some embodiments, a constraint condition may include that an additional operation indicator (also referred to as a third operation indicator) satisfies a condition. For example, a constraint condition may include that the gain and loss rate must be smaller than a threshold. As another example, a constraint condition may include that the total order count must be greater than a count threshold.

In some embodiments, the third operation indicator may be determined based on a constraint function with the third operation indicator as a dependent variable, and the price parameter and/or the one or more additional parameters as independent variables. For example, if the model for estimating a specific operation indicator is associated with the total order count, the constraint function may be associated with at least one of the GMV, the gross margin, the gain and loss rate, etc. As another example, if the model for estimating a specific operation indicator is associated with the GMV, the constraint function may be associated with at least one of the total order count, the gross margin, the gain and loss rate, etc.

In some embodiments, the constraint function may be determined statistically using a fitting technique based on the multiple groups of the plurality of routes clustered in operation 520. For example, the processing device 112 may determine a value of the third operation indicator of each of the multiple groups of the plurality of routes. The processing device 112 may obtain values of the one or more price parameters (e.g., the discount, an average price for routes in each of the multiple groups) corresponding to each group of the multiple groups of the plurality of routes and/or the additional parameters (e.g., an average travel distance for routes in each of the multiple groups) . The processing device 112 may determine the constraint function using the fitting technique based on the value of the third operation indicator and the values of the one or more price parameters of each of the multiple groups of the plurality of routes, and/or the additional parameters.

In some embodiments, the processing device 112 may determine the value of the specific operation indicator based on the constraint function according to the estimation model. For example, the processing device 112 may determine a maximum value or a minimum value of the specific operation indicator under one or more constraint conditions being satisfied. Merely by ways of example, the first operation indicator may be a total order count, and the price parameter may be a discount. The constraint function may be associated with a gain and loss rate determination model providing a relationship between a gain and loss rate and the discount. The processing device 112 may determine the maximum of the objective function associated with the total order count and the discount based on the relationship between gain and loss rate and the discount. For example, the processing device 112 may preset a threshold, under the premise of ensuring that the gain and loss rate is greater than the threshold, the processing device 112 may determine a maximum of the objective function associated with the total order count and the discount (i.e., the model for estimating the total order count) . The processing device 112 may designate the maximum of the objective function (i.e., the model for estimating the total order count) associated with the total order count and the discount as the maximum total order count. In some embodiments, the gain and loss rate determination model may be associated with carpooling order conversion rate, the change rate of carpooling order conversion rate, the change rate of discount, travel distance, etc., as described in operation 530. The gain and loss rate determination model may be determined based on a carpooling order conversion rate corresponding to each group of routes, a changing rate of carpooling order conversion rates corresponding to two groups of routes, a changing rate of discounts corresponding to two groups of routes, a travel distance corresponding to each group of routes, and a gain and loss rate corresponding to each group of routes.

It should be noted that the above description is merely provided for the purposes of illustration, and not intended to limit the scope of the present disclosure. For persons having ordinary skills in the art, multiple variations and modifications may be made under the teachings of the present disclosure. However, those variations and modifications do not depart from the scope of the present disclosure. In some embodiments, one or more operations may be omitted and/or one or more additional operations may be added. For example, the operation 520 and the operation 530 may be combined into a single operation to determine the model for estimating one or more operation indicators of the online to offline platform. As another example, one or more other optional operations (e.g., a storing operation) may be added elsewhere in the process 500. In the storing operation, the processing device 112 may store information and/or data (e.g., the order information, information associated with the routes in each of the multiple groups, the model for estimating one or more operation indicators of the online to offline platform, etc. ) associated with the online to offline service system 100 in a storage device (e.g., the storage device 160) disclosed elsewhere in the present disclosure..

FIG. 6 is a schematic flowchart illustrating an exemplary process for clustering a plurality of routes using a density-based clustering model according to some embodiments of the present disclosure. The process 600 may be executed by the online to offline service system 100. For example, the process 600 may be implemented as a set of instructions (e.g., an application) stored in the storage device 160, ROM 230 or RAM 240, or storage 390. The processing device 112, the processor 220 and/or the CPU 340 may execute the set of instructions, and when executing the instructions, the processing device 112, the processor 220 and/or the CPU 340 may be configured to perform the process 600. The operations of the illustrated process presented below are intended to be illustrative. In some embodiments, the process 600 may be accomplished with one or more additional operations not described and/or without one or more of the operations discussed. Additionally, the order in which the operations of the process 600 illustrated in FIG. 6 and described below is not intended to be limiting. In some embodiments, one or more operations of the process 600 may be performed to achieve at least part of operation 520 as described in connection with FIG. 5.

In 610, the processing device 112 (e.g., the clustering module 420) may represent each of the plurality of routes with a point in an N-dimensional coordinate system based on one or more features associated with each of the plurality of routes. N may be an integer greater than, or equal to 3. In some embodiments, the one or more features associated with the each of the plurality of routes may include a starting location, a destination, a travel distance, a travel duration, a travel time, a price, a discount, or the like, or any combination thereof. As used herein, coordinates of a point in an N-dimensional coordinate system may include N (N ≥ 3) factors. A factor may also be referred to as a coordinate of the point in the N-dimensional coordinate system. In some embodiments, a feature of a route may be represented by one or more factors. For example, a starting location of the route may be denoted by a geographic coordinate system. The starting location of the route may be denoted as two or more geographic coordinates (e.g., the latitude and longitude) . The two or more geographic coordinates (e.g., the latitude and longitude) may be designated as two or more factors or coordinate components of a point representing the route in the N-dimensional coordinate system. As another example, a travel distance of the route may be denoted as a length. The length of the travel distance of the route may be designated as one single factor or a coordinate component of the point representing the route in the N-dimensional coordinate system. More descriptions for representing each of the plurality of routes with a point in the N-dimensional coordinate system may be found elsewhere in the preset disclosure (e.g., FIG. 5 and the descriptions thereof) .

In 620, the processing device 112 (e.g., the clustering module 420) may determine a distance between two points corresponding to any two of the plurality of routes in the N-dimensional coordinate system. In some embodiments, a distance between two points corresponding to two routes may represent a similarity degree between the two routes. The shorter the distance between two points corresponding to two routes is, the higher the similarity degree between the two routes may be.

In some embodiments, the distance may include a Euclidean distance, a Minikowski distance, a Camberra distance, a Mahalanobis distance, a Manhattan distance, a Chebyshev distance, or the like, or any combination thereof. Exemplary Euclidean distance may be calculated according to Equation (6) as follows:

where, x refers to a coordinate of a point in the N-dimensional coordinate system, y refers to a coordinate of another point, i refers to an ith coordinate of a point in the N-dimensional coordinate system. For example, route AB may be denoted as a point P _AB (X _A, Y _A, X _B, Y _B) , and route CD may be denoted as a point P _CD (X _C, Y _C, X _D, Y _D) based on starting locations and destinations of route AB and route CD, respectively, in a four-dimensional coordinate system. Euclidean distance between route AB and route CD may be calculated based on coordinates of point P _AB (X _A, Y _A, X _B, Y _B) and point P _CD (X _C, Y _C, X _D, Y _D) according to Equation (7) as follows:

where d (P _AB, P _CD) refers to a distance between route AB and route CD. The smaller the d (P _AB, P _CD) is, the higher the similarity degree between route AB and route CD may be. In some embodiments, if two routes have the same starting location (or destination) , such as route AB represented with a point P _AB (X _A, Y _A, X _B, Y _B) and route AC represented with a point P _AC (X _A, Y _A, X _C, Y _C) , the Euclidean distance between route AB and route AC in the four-dimensional coordinate system may be determined by calculating a distance between the destinations (or starting locations) of route AB and route AC according to Equation (8) as follows:

where d (P _AB, P _AC) refers to a distance between route AB and route AC.

In some embodiments, a route may be represented with a point in the N-dimensional coordinate system (N ≥ 5) . For example, in a five-dimensional coordinate system, a route EF may be represented with a point P _EF (X _E, Y _E, X _F, Y _F, T _E) , wherein X _E and Y _E refer to a latitude and a longitude of the starting location of the route EF, respectively, X _F and Y _F refer to a latitude and a longitude of the destination of the route EF, respectively, and T _E refers to a value associated with the departure time of an order associated with the route EF. A route GH may be represented with a point P _GH (X _G, Y _E, X _H, Y _H, T _G) , wherein X _G and Y _G refer to a latitude and a longitude of the starting location of the route GH, respectively, X _H and Y _H refer to a latitude and a longitude of the destination of the route GH, respectively, and T _G refers to a value associated with the departure time of an order associated with the route GH. A value associated with the departure time of an order associated with a route may be designated by the processing device 112 according to the departure time of the order. For example, the processing device 112 may determine a value of the departure time of an order as “1” when the departure time of the order is at 9: 00 am. The processing device 112 may determine a value of the departure time of another order as “500” when the departure time of another order is at 9: 00 pm. In some embodiments, the processing device 112 may determine departure times within a time period as the same value. For example, the processing device 112 may determine a value of the departure time of an order as “1” when the departure time of the order is in the range of 7: 00 am to 9: 00 am. The distance between the point P _EF (X _E, Y _E, X _F, Y _F, T _E) and the point P _GH (X _G, Y _E, X _H, Y _H, T _G) , may be determined as described above. For example, the Euclidean distance between the route EF and the route GH may be calculated according to Equation (9) as follows:

where d (P _EF, P _GH) refers to a distance between the route EF and the route GH.

In 630, the processing device 112 (e.g., the clustering module 420) may cluster the plurality of routes into multiple groups based on the distance between two points corresponding to any two of the plurality of routes in the N-dimensional coordinate system. The distance between two points in the N-dimensional coordinate system corresponding to any two of the routes in the same group may satisfy a criterion. For example, the distance between any two points in the N-dimensional coordinate system in the same group may be less than a first distance threshold. As another example, the distance between each point and a center point in the N-dimensional coordinate system in the same group may be less than a second distance threshold. As still another example, the distance between two points in the N-dimensional coordinate system corresponding to any two of the routes in a same group may be less than a distance between each of the two points corresponding to any two of the routes in the same group and a point corresponding to any other route in another group in the N-dimensional coordinate system. In some embodiments, the distance threshold may be a default setting of the online to offline service system 100. In some embodiments, the distance threshold may be preset by a user according to the user’s purpose. For example, the user may set a relatively high distance threshold when the user just wants to know a route distribution roughly. As another example, the user may set a relatively low distance threshold when the user wants to estimate the price of an order in the next week by using the clustered routes.

In some embodiments, the processing device 112 may cluster the plurality of routes into multiple groups using a density-based clustering model, a partition-based clustering algorithm, a hierarchical-based clustering algorithm, a grid-based clustering algorithm, a model-based algorithm, etc., as described in operation 520. Taking the DBSCAN algorithm as an example, one or more parameters of the DBSCAN algorithm may be preset, such as a minimum number or count of points (MinPts) and a scanning radius denoted as an epsilon (Eps) . The processing device 112 may obtain a specific point representing a route. The processing device 112 may determine points in an area within the Eps from the specific point. The processing device 112 may determine the specific point as a core point (or center point) if the number or count of points within the area exceeds the MinPts. The processing device 112 may determine a cluster including the points and the specific point if the number or count of points within the area exceeds the MinPts. The processing device 112 may determine two clusters into one cluster if the distance of core points of the two clusters within the Eps. The processing device 112 may transmit the clustered routes to a storage device (e.g., the storage device 160, the ROM 230, the RAM 240, etc. ) for storage.

It should be noted that the above description is merely provided for the purposes of illustration, and not intended to limit the scope of the present disclosure. For persons having ordinary skills in the art, multiple variations and modifications may be made under the teachings of the present disclosure. However, those variations and modifications do not depart from the scope of the present disclosure. In some embodiments, one or more operations may be omitted and/or one or more additional operations may be added. For example, the operation 610 and the operation 620 may be combined into a single operation to determine a distance between any two of the plurality of routes. As another example, one or more other optional operations (e.g., an obtaining operation) may be added in the process 500. In the obtaining operation, the processing device 112 may store information and/or data (e.g., route information, etc. ) associated with a plurality of orders in a storage device (e.g., the storage device 160) disclosed elsewhere in the present disclosure.

Having thus described the basic concepts, it may be rather apparent to those skilled in the art after reading this detailed disclosure that the foregoing detailed disclosure is intended to be presented by way of example only and is not limiting. Various alterations, improvements, and modifications may occur and are intended to those skilled in the art, though not expressly stated herein. These alterations, improvements, and modifications are intended to be suggested by this disclosure and are within the spirit and scope of the exemplary embodiments of this disclosure.

Moreover, certain terminology has been used to describe embodiments of the present disclosure. For example, the terms “one embodiment, ” “an embodiment, ” and/or “some embodiments” mean that a particular feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment of the present disclosure. 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 portions of this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures or characteristics may be combined as suitable in one or more embodiments of the present disclosure.

Further, it will be appreciated by one skilled in the art, aspects of the present disclosure may be illustrated and described herein in any of a number of patentable classes or context including any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof. Accordingly, aspects of the present disclosure may be implemented entirely hardware, entirely software (including firmware, resident software, micro-code, etc. ) or combining software and hardware implementation that may all generally be referred to herein as a “unit, ” “module, ” or “system. ” Furthermore, aspects of the present disclosure may take the form of a computer program product embodied in one or more computer-readable media having computer-readable program code embodied thereon.

A non-transitory computer-readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated signal may take any of a variety of forms, including electromagnetic, optical, or the like, or any suitable combination thereof. A computer-readable signal medium may be any computer-readable medium that is not a computer-readable storage medium and that may communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer-readable signal medium may be transmitted using any appropriate medium, including wireless, wireline, optical fiber cable, RF, or the like, or any suitable combination of the foregoing.

Computer program code for carrying out operations for aspects of the present disclosure may be written in any combination of one or more programming languages, including an object-oriented programming language such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB. NET, Python or the like, conventional procedural programming languages, such as the "C" programming language, Visual Basic, Fortran, Perl, COBOL, PHP, ABAP, dynamic programming languages such as Python, Ruby, and Groovy, or other programming languages. 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 type of network, including 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 using an Internet Service Provider) or in a cloud computing environment or offered as a service such as a Software as a Service (SaaS) .

Furthermore, the recited order of processing elements or sequences, or the use of numbers, letters, or other designations, therefore, is not intended to limit the claimed processes and methods to any order except as may be specified in the claims. Although the above disclosure discusses through various examples what is currently considered to be a variety of useful embodiments of the disclosure, 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 modifications and equivalent arrangements that are within the spirit and scope of the disclosed embodiments. For example, although the implementation of various components described above may be embodied in a hardware device, it may also be implemented as a software-only solution, e.g., an installation on an existing server or mobile device.

Similarly, it should be appreciated that in the foregoing description of embodiments of the present disclosure, various features are sometimes grouped together in a single embodiment, figure, or description thereof to streamline the disclosure aiding in the understanding of one or more of the various inventive embodiments. This method of disclosure, however, is not to be interpreted as reflecting an intention that the claimed object matter requires more features than are expressly recited in each claim. Rather, inventive embodiments lie in less than all features of a single foregoing disclosed embodiment.

In some embodiments, the numbers expressing quantities, properties, and so forth, used to describe and claim certain embodiments of the application are to be understood as being modified in some instances by the term “about, ” “approximate, ” or “substantially. ” For example, “about, ” “approximate” or “substantially” may indicate ±20%variation of the value it describes, unless otherwise stated. Accordingly, in some embodiments, the numerical parameters set forth in the written description and attached claims are approximations that may vary depending upon the desired properties sought to be obtained by a particular embodiment. In some embodiments, the numerical parameters should be construed in light of the number of reported significant digits and by applying ordinary rounding techniques. Notwithstanding that the numerical ranges and parameters setting forth the broad scope of some embodiments of the application are approximations, the numerical values set forth in the specific examples are reported as precisely as practicable.

Each of the patents, patent applications, publications of patent applications, and other material, such as articles, books, specifications, publications, documents, things, and/or the like, referenced herein is hereby incorporated herein by this reference in its entirety for all purposes, excepting any prosecution file history associated with same, any of same that is inconsistent with or in conflict with the present document, or any of same that may have a limiting effect as to the broadest scope of the claims now or later associated with the present document. By way of example, should there be any inconsistency or conflict between the description, definition, and/or the use of a term associated with any of the incorporated material and that associated with the present document, the description, definition, and/or the use of the term in the present document shall prevail.

In closing, it is to be understood that the embodiments of the application disclosed herein are illustrative of the principles of the embodiments of the application. Other modifications that may be employed may be within the scope of the application. Thus, by way of example, but not of limitation, alternative configurations of the embodiments of the application may be utilized in accordance with the teachings herein. Accordingly, embodiments of the present application are not limited to that precisely as shown and described.

Claims

A system for improving an online to offline platform, comprising:

at least one storage medium including a set of instructions;

at least one processor in communication with the at least one storage medium, wherein when executing the set of instructions, the at least one processor is directed to cause the system to perform operations including:

obtaining a plurality of routes associated with a plurality of orders provided by the online to offline platform in a historical period;

clustering, based on one or more features associated with each of the plurality of routes, the plurality of routes into multiple groups, each of the multiple groups including one or more routes;

determining, based on the one or more routes in at least a portion of the multiple groups, a model for estimating one or more operation indicators of the online to offline platform; and

determining, based on the model for estimating one or more operation indicators of the online to offline platform, an operation indicator of the online to offline platform in a future period.
The system of claim 1, wherein the one or more features of the each of the plurality of routes include at least one of a starting location, a destination, a travel distance, a travel duration, a departure time, an arrival time, a price, or a discount.
The system of claim 1 or claim 2, wherein to cluster the plurality of routes into the multiple groups, the at least one processor is directed to cause the system to perform additional operations including:

clustering the plurality of routes into the multiple groups using a density-based clustering model.
The system of any one of claims 1 to 3, wherein to cluster, based on one or more features associated with each of the plurality of routes, the plurality of routes into multiple groups, the at least one processor is directed to cause the system to perform operations including:

representing, based on the one or more features associated with each of the plurality of routes, each of the plurality of routes with a point in an N-dimensional coordinate system, N being an integer greater than or equal to 3; and

clustering, based on points representing the plurality of routes, the plurality of routes into the multiple groups.
The system of claim 4, wherein to represent each of the plurality of routes with a point in the N-dimensional coordinate system, the at least one processor is directed to cause the system to perform operations including:

denoting geographical coordinates of a starting location and geographical coordinates of a destination of each of the plurality of routes as coordinates of the point in the N-dimensional coordinate system.
The system of claim 5, wherein to cluster the plurality of routes into the multiple groups, the at least one processor is directed to cause the system to perform additional operations including:

determining a distance between two points corresponding to any two of the plurality of routes in the N-dimensional system; and

clustering, based on the distance between two points corresponding to any two of the plurality of routes in the N-dimensional system, the plurality of routes into the multiple groups, wherein whether the distance between two points corresponding to any two of the plurality of routes satisfies a criterion determines whether the two routes belong to a same group in the multiple groups.
The system of any one of claims 1 to 6, wherein the operation indicator of the online to offline platform includes at least one of:

an order amount,

a gross merchandise volume (GMV) ,

a gross margin, or

a gain and loss rate.
The system of any one of claims 1 to 7, wherein the model for estimating the one or more operation indicators of the online to offline platform is configured to provide a relationship between the operation indicator and a price parameter, and to determine, based on the one or more routes in at least a portion of the multiple groups, a model for estimating one or more operation indicators of the online to offline platform, the at least one processor is directed to cause the system to perform additional operations including:

determining statistically, based on the one or more routes in each group of the multiple groups, the relationship between the operation indicator and the price parameter using a fitting technique.
The system of claim 8, wherein to determine statistically, based on the one or more routes in each group of the multiple groups, the relationship between the operation indicator and the price parameter using a fitting technique, the at least one processor is directed to cause the system to perform additional operations including:

determining statistically, based on the one or more routes in each group of the multiple groups, multiple reference values of the operation indicator, each of the reference values corresponding to each group of the multiple groups; and

determining the relationship between the operation indicator and the price parameter using the fitting technique based on the multiple reference values of the operation indicator and the price parameter corresponding to each group of the multiple groups.
The system of claims 1 to 7, wherein the model for estimating the one or more operation indicators of the online to offline platform includes an objective function with the operation indicator as a dependent variable and a price parameter as an independent variable, and to determine, based on the model for estimating one or more operation indicators of the online to offline platform, an operation indicator of the online to offline platform in a future period, the at least one processor is directed to cause the system to perform additional operations including:

determining a maximum value or a minimum value of the objective function under one or more constraint conditions being satisfied; and

designating the maximum value or the minimum value of the objective function as the a predicted value of the operation indicator in the future period, wherein the each of the one or more constraint conditions is associated with an additional operation indicator.
The system of claim 10, wherein the operation indicator includes an order amount and the price parameter includes a discount, and the objective function is determined by:

determining a first component providing a first relationship between a probability that an order is a carpooling order and the discount of the order;

determining a second component providing a second relationship between the discount and a change of the probability changing with the discount; and

determining the objective function based on the first component and the second component.
The system of claim 10, wherein to determine, based on the one or more routes in at least a portion of the multiple groups, a model for estimating one or more operation indicators of the online to offline platform, the at least one processor is directed to cause the system to perform additional operations including:

determining two or more groups that satisfy a first condition from the multiple groups;

clustering one or more routes that satisfy a second condition in each of the two or more groups into one or more additional groups; and

determining, based on the one or more additional groups and the at least a portion of the multiple groups, the model.
A method implemented on a computing device having at least one processor and at least one storage device, the method comprising:

obtaining a plurality of routes associated with a plurality of orders provided by the online to offline platform in a historical period;

clustering, based on one or more features associated with each of the plurality of routes, the plurality of routes into multiple groups, each of the multiple groups including one or more routes;

determining, based on the one or more routes in at least a portion of the multiple groups, a model for estimating one or more operation indicators of the online to offline platform; and

determining, based on the model for estimating one or more operation indicators of the online to offline platform, an operation indicator of the online to offline platform in a future period.
The method of claim 13, wherein the clustering the plurality of routes into the multiple groups includes:

clustering the plurality of routes into the multiple groups using a density-based clustering model.
The method of claim 13 or 14, wherein the clustering, based on one or more features associated with each of the plurality of routes, the plurality of routes into multiple groups includes:

representing, based on the one or more features associated with each of the plurality of routes, each of the plurality of routes with a point in an N-dimensional coordinate system, N being an integer greater than or equal to 3; and

clustering, based on points representing the plurality of routes, the plurality of routes into the multiple groups.
The method of any one of claims 13 to 15, wherein the operation indicator of the online to offline platform includes at least one of:

an order amount,

a gross merchandise volume (GMV) ,

a gross margin, or

a gain and loss rate.
The method of any one of claims 13 to 16, wherein the model for estimating the one or more operation indicators of the online to offline platform is configured to provide a relationship between the operation indicator and a price parameter, and the determining, based on the one or more routes in at least a portion of the multiple groups, a model for estimating one or more operation indicators of the online to offline platform includes:

determining statistically, based on the one or more routes in each group of the multiple groups, the relationship between the operation indicator and the price parameter using a fitting technique.
The method of any one of claims 13 to 16, wherein the model for estimating the one or more operation indicators of the online to offline platform includes an objective function with the operation indicator as a dependent variable and a price parameter as an independent variable, and determining, based on the model for estimating one or more operation indicators of the online to offline platform, an operation indicator of the online to offline platform in a future period includes:

determining a maximum value or a minimum value of the objective function under one or more constraint conditions being satisfied; and

designating the maximum value or the minimum value of the objective function as the a predicted value of the operation indicator in the future period, wherein the each of the one or more constraint conditions is associated with an additional operation indicator.
The method of claim 18, wherein to determine, based on the one or more routes in at least a portion of the multiple groups, a model for estimating one or more operation indicators of the online to offline platform, the at least one processor is directed to cause the system to perform additional operations including:

determining two or more groups that satisfy a first condition from the multiple groups;

clustering one or more routes that satisfy a second condition in each of the two or more groups into one or more additional groups; and

determine, based on the one or more additional groups and the at least a portion of the multiple groups, the model.
The method of any one of claim 13 to19, wherein the one or more features of the each of the plurality of routes include at least one of a starting location, a destination, a travel distance, a travel duration, a departure time, an arrival time, a price, or a discount.
A non-transitory computer readable medium, comprising a set of instructions, wherein when executed by at least one processor, the set of instructions direct the at least one processor to effectuate a method, the method comprising:

obtaining a plurality of routes associated with a plurality of orders provided by the online to offline platform in a historical period;

clustering, based on one or more features associated with each of the plurality of routes, the plurality of routes into multiple groups, each of the multiple groups including one or more routes;

determining, based on the one or more routes in at least a portion of the multiple groups, a model for estimating one or more operation indicators of the online to offline platform; and

determining, based on the model for estimating one or more operation indicators of the online to offline platform, an operation indicator of the online to offline platform in a future period.
A system, comprising:

an obtaining module configured to obtain a plurality of routes associated with a plurality of orders provided by the online to offline platform in a historical period;

a clustering module configured to cluster, based on one or more features associated with each of the plurality of routes, the plurality of routes into multiple groups, each of the multiple groups including one or more routes;

a determination module configured to determine, based on the one or more routes in at least a portion of the multiple groups, a model for estimating one or more operation indicators of the online to offline platform; and

an estimation module configured to determining, based on the model for estimating one or more operation indicators of the online to offline platform, an operation indicator of the online to offline platform in a future period.