CN111192071A

CN111192071A - Invoice amount estimation method and device and invoice probability model training method and device

Info

Publication number: CN111192071A
Application number: CN201811362414.3A
Authority: CN
Inventors: 谢梁; 李盼
Original assignee: Beijing Didi Infinity Technology and Development Co Ltd
Current assignee: Beijing Didi Infinity Technology and Development Co Ltd
Priority date: 2018-11-15
Filing date: 2018-11-15
Publication date: 2020-05-22
Anticipated expiration: 2038-11-15
Also published as: CN111192071B

Abstract

The invention provides an order delivery amount pre-estimation method and device, a method and device for training an order delivery probability model, the order delivery amount pre-estimation method and device can accurately predict the probability of issuing a trip order by each service request end and the probability of issuing a trip order by each service request end in a plurality of service request ends in each trip type according to a service strategy to be evaluated and a service strategy which does not change, the quantity of trip orders corresponding to each trip type can be accurately pre-estimated based on the obtained accurate probability under the condition that the service strategy of a certain trip type changes, the accuracy of pre-estimating the quantity of trip orders corresponding to each trip type is improved, the pre-estimation efficiency is improved, the pre-estimation cost is reduced, more importantly, when the service strategy of each trip type changes, influence on the quantity of the travel orders corresponding to each travel type.

Description

Invoice amount estimation method and device and invoice probability model training method and device

Technical Field

The application relates to the technical field of network appointment and data processing, in particular to a method and a device for estimating an order delivery amount, a method and a device for training an order delivery probability model, electronic equipment and a computer-readable storage medium.

Background

The service strategy is an important factor influencing the selection of different travel types by the service request terminal on the network car booking platform to initiate a travel order. When the service strategy of a certain trip type changes, the quantity of trip orders corresponding to other trip types can be influenced.

Currently, when a service policy of a certain trip type changes, the number of trip orders corresponding to all trip types is determined by generally adopting an experimental mode, and the method is not only low in efficiency and high in cost, but also cannot exhaust the influence of various changes of the service policy on each trip type on the number of trip orders corresponding to each trip type.

Disclosure of Invention

In view of this, an object of the embodiments of the present application is to provide an order quantity estimation method and apparatus, and an order probability model training method and apparatus, which can estimate the quantity of travel orders corresponding to each travel type based on a service policy to be evaluated, and avoid the defects that an experimental mode in the prior art is poor in efficiency and high in cost, and the influence of various changes of the service policy on the quantity of the travel orders corresponding to each travel type cannot be exhausted.

In a first aspect, an embodiment of the present application provides a method for predicting an invoice amount, including:

predicting the probability of each service request terminal in the plurality of service request terminals initiating a travel order based on the obtained service strategy to be evaluated;

for each travel type in multiple travel types, predicting the probability of each service request end in the multiple service request ends issuing a travel order in the travel type based on the service strategy of the travel type;

and predicting the quantity of the travel orders corresponding to each travel type based on the probability of each service request end in the service request ends initiating the travel orders and the probability of each service request end initiating the travel orders in each travel type.

In a possible implementation manner, the service policy to be evaluated is a service policy to be evaluated corresponding to a target trip type.

In a possible implementation manner, the predicting, based on the obtained service policy to be evaluated, a probability that each service requester in the plurality of service requesters initiates a travel order includes:

and predicting the probability of the trip order initiated by each service request terminal in the plurality of service request terminals under the service strategy to be evaluated based on the corresponding relation between each service strategy of the target trip type and the probability of the trip order initiated by the plurality of service request terminals and the service strategy to be evaluated.

In a possible implementation manner, the method further includes a step of constructing a corresponding relationship between the service policy of the target trip type and probabilities of multiple service request terminals initiating trip orders:

acquiring first sample data, wherein the first sample data comprises a plurality of service strategies of a target trip type and result data of whether a plurality of service request terminals initiate trip orders or not under each service strategy;

and constructing a corresponding relation between each service strategy of the target trip type and the probability of the plurality of service request terminals initiating trip orders based on the first sample data.

In a possible implementation manner, the method for predicting an invoice amount further includes:

and constructing a corresponding relation between each service strategy of the target trip type and the probability of initiating a trip order by a plurality of service request terminals by using a binary classification logic Stent model.

In one possible embodiment, the obtaining the first sample data includes:

acquiring first sample data of a trip demand initiated by a service request end within a preset historical time period and a mileage corresponding to the trip demand within a preset mileage range; the travel demand comprises a departure place of the service request terminal and a destination of the service request terminal; the travel demand corresponds to the travel order;

and the corresponding relation between the service strategy of the target trip type and the probability of launching trip orders by a plurality of service request terminals takes the preset historical time period and the preset mileage range as dummy variables.

In one possible embodiment, the service policy includes at least one of the following service characteristics:

price, trip comfort level, trip quietness of the trip order.

In a possible implementation manner, the constructing, based on the first sample data, a correspondence between the service policy of the target travel type and probabilities of multiple service requesters initiating travel orders includes:

performing function operation on each service characteristic in each service strategy of the target trip type to obtain a processed service strategy of the target trip type;

constructing a corresponding relation between each processed service strategy of the target trip type and the probability of each service request end of the plurality of service request ends initiating a trip order based on the processed service strategies of the target trip type and the result data of whether each service request end of the plurality of service request ends initiates the trip order under each processed service strategy;

the predicting the probability of each service request end in the plurality of service request ends initiating the travel order comprises the following steps:

performing function operation on each service characteristic in the service strategy to be evaluated of the target trip type to obtain a processed service strategy to be evaluated;

and determining the probability of initiating the travel order by each service request terminal based on the corresponding relation between each processed service strategy of the target travel type and the probability of initiating the travel order by each service request terminal in the plurality of service request terminals and the processed service strategy to be evaluated.

In one possible embodiment, the function operation is a logarithmic function operation.

In one possible implementation, predicting the probability of each of the plurality of service requesters initiating a row order for each of the travel types includes:

determining the probability of issuing the outgoing order by each service request terminal in the plurality of service request terminals in each trip type based on the corresponding relation between the service strategy of each trip type and the probability of issuing the outgoing order by each service request terminal in the plurality of service request terminals in each trip type and the service strategy of each trip type.

In a possible implementation manner, the method further includes the step of establishing a corresponding relationship between each service policy of each travel type and a probability of issuing a travel order by each service requester in the plurality of service requesters in each travel type:

acquiring second sample data, wherein the second sample data comprises at least one service strategy of each trip type and result data of whether a plurality of service request terminals initiate trip orders in the trip type or not based on each service strategy of the trip type aiming at each trip type in a plurality of trip types;

and constructing a corresponding relation between each service strategy of each trip type and the probability of issuing a trip order by each service request end in the plurality of service request ends in each trip type based on the second sample data.

and constructing a corresponding relation between the service strategy of each trip type and the probability of issuing a trip order by each service request end in the plurality of service request ends in each trip type by using the conditional logic model.

In a possible implementation, the obtaining second sample data includes:

acquiring second sample data of a trip demand time issued by a service request end in a preset historical time period and a mileage corresponding to the trip demand in a preset mileage range; the travel demand comprises a departure place of the service request terminal and a destination of the service request terminal; the travel demand corresponds to the travel order;

and the service strategy of each trip type corresponds to the probability of issuing a trip order by each service request end in a plurality of service request ends in each trip type, and the preset historical time period and the preset mileage range are used as dummy variables.

In a possible implementation manner, the predicting the probability of each of the plurality of service requesters initiating a row order in the travel type includes:

selecting a corresponding relation between each service strategy of each trip type with a corresponding dummy variable and the probability of issuing a trip order by each service request end in a plurality of service request ends in each trip type based on the issuing time of each trip demand of each service request end and the mileage corresponding to each trip demand;

and determining the probability of issuing the outgoing order by each service request end in the plurality of service request ends in the trip type based on the corresponding relation between each selected service strategy of each trip type and the probability of issuing the outgoing order by each service request end in the plurality of service request ends in each trip type and each service strategy of the trip type.

price, trip comfort level, trip quietness of the trip order.

In a possible implementation manner, the constructing, based on the second sample data, a corresponding relationship between the service policy of each travel type and a probability of each service requester in the plurality of service requesters issuing a travel order in each travel type includes:

based on each service strategy of each trip type in the second sample data and for each trip type in the second sample data, based on each service strategy of the trip type, whether each service request terminal in a plurality of service request terminals initiates result data of a trip order in the trip type or not is determined, and the probability that each service request terminal in the plurality of service request terminals initiates the trip order in the trip type under each service strategy of the trip type is determined;

determining tendency scores of each service request terminal in the service request terminals for issuing the travel orders under each service strategy of each travel type based on the probability of each service request terminal in the service request terminals for issuing the travel orders under each travel type under each service strategy of each travel type;

determining an index coefficient corresponding to each service characteristic of each service strategy of each trip type based on a tendency score of each service request terminal of the plurality of service request terminals initiating a trip order under each service strategy of each trip type and a value of each service characteristic of each service strategy of each trip type, and obtaining a corresponding relation between each service strategy of each trip type and a probability of each service request terminal of the plurality of service request terminals initiating a trip order under each trip type.

In a possible implementation manner, the predicting, based on the service policy for the travel type, a probability that each service requester in the service requesters initiates a travel order in the travel type includes:

determining an index coefficient of each service feature in the travel type service strategy based on the value of each service feature in the travel type service strategy;

determining a tendency score of each server request end in a plurality of service request ends issuing a outgoing order in the trip type based on the index coefficient of each service characteristic in the trip type service strategy and the value of each service characteristic in the trip type service strategy;

and predicting the probability of each service request end in the plurality of service request ends initiating the order of the line under the type of the line based on the tendency score.

In one possible implementation, the probability that each service requester in the plurality of service requesters initiates a row order in the travel type i is determined by the following formula:

in the formula, V_niRepresents the tendency score, P, of the nth service request end initiating the outgoing order in the outgoing type i_niRepresenting the probability of the nth service request end initiating a trip order in a trip type i, and J representing the number of trip typesAmount, V_niAnd the tendency score represents that the nth service request end initiates a line order in the line type j.

In one possible implementation, the tendency score corresponding to the travel type i is determined by the following formula:

in the formula, V_niRepresents the tendency score of the nth service request end to initiate a line order in the line type i, β_kIndex coefficient, X, representing the kth service characteristic in the service strategy for travel type i_kiAnd K represents the number of service features in the service strategy of the trip type i.

In a second aspect, an embodiment of the present application provides a method for training a hair singles probability model, including:

acquiring second sample data, wherein the second sample data comprises at least one service strategy of each of a plurality of trip types and result data of whether a plurality of service request terminals initiate a trip order in each of the plurality of trip types based on each service strategy of the trip type;

and constructing a corresponding relation between each service strategy of each trip type and the probability of issuing a trip order by each service request end in the plurality of service request ends in each trip type based on the second sample data to obtain an order issuing probability calculation model.

In a possible implementation manner, the method for training the issue ticket probability model further includes:

In a possible implementation, the obtaining second sample data includes:

price, trip comfort level, trip quietness of the trip order.

In one possible embodiment, the singles probability computation model includes:

in the formula, β_kIndex coefficient, P, representing the kth service characteristic in the service strategy for travel type i_niRepresenting the probability of the nth service request end initiating a trip order in a trip type i, J representing the number of trip types, and X_kiValue, V, representing the kth service feature in the service policy for travel type i_niA tendency score V representing the tendency of the nth service request end to initiate a line order in the line type i_niAnd K represents the number of service features in the service strategy of the trip type i.

In a third aspect, an embodiment of the present application provides an invoice amount estimation device, including:

the probability prediction module is used for predicting the probability of each service request end in the plurality of service request ends initiating the travel order based on the acquired service strategy to be evaluated;

the single quantity prediction module is used for predicting the quantity of the travel orders corresponding to each travel type based on the probability of each service request end in the service request ends initiating the travel orders and the probability of each service request end initiating the travel orders in each travel type.

In a possible embodiment, the probability prediction module comprises a first prediction sub-module configured to:

and predicting the probability of the trip order initiated by each service request terminal in the plurality of service request terminals under the service strategy to be evaluated based on the corresponding relation between the service strategy of the target trip type and the probability of the trip order initiated by the plurality of service request terminals and the service strategy to be evaluated.

In a possible implementation, the first prediction sub-module is specifically configured to:

and constructing a corresponding relation between the service strategy of the target trip type and the probability of the plurality of service request terminals initiating trip orders based on the first sample data.

In a possible implementation manner, the first prediction sub-module is specifically configured to construct, by using a binary logic stett model, a correspondence between the service policy of the target trip type and probabilities of multiple service requesters initiating trip orders.

price, trip comfort level, trip quietness of the trip order.

In a possible implementation, the probability prediction module includes a second prediction submodule configured to: and determining the probability of issuing the outgoing order by each service request terminal in the plurality of service request terminals in each trip type based on the corresponding relation between each service strategy of each trip type and the probability of issuing the outgoing order by each service request terminal in the plurality of service request terminals in each trip type and the service strategy of each trip type.

In a possible implementation, the second predictor module is specifically configured to:

In a possible embodiment, the second predictor module is specifically adapted to

price, trip comfort level, trip quietness of the trip order.

In a possible implementation, the second predictor module is specifically configured to: :

in the formula, V_niRepresents the tendency score, P, of the nth service request end initiating the outgoing order in the outgoing type i_niRepresenting the probability of the nth service request end initiating a trip order in a trip type i, J representing the number of trip types, V_niAnd the tendency score represents that the nth service request end initiates a line order in the line type j.

in the formula, V_niRepresents the tendency score of the nth service request end to initiate a line order in the line type i, β_kIn the service strategy for representing the travel type iIndex coefficient of kth service characteristic, X_kiAnd K represents the number of service features in the service strategy of the trip type i.

In a fourth aspect, an embodiment of the present application provides an apparatus for training a hair singles probability model, including:

the data acquisition module is used for acquiring second sample data, wherein the second sample data comprises at least one service strategy of each of a plurality of trip types and result data of whether each service request terminal of a plurality of service request terminals initiates a trip order in each trip type based on each service strategy of the trip type;

and the model training module is used for constructing a corresponding relation between each service strategy of each trip type and the probability of issuing a trip order by each service request end in the plurality of service request ends in each trip type based on the second sample data to obtain an order issuing probability calculation model.

In a possible implementation manner, the model training module uses a conditional logic model to construct a corresponding relationship between the service policy of each travel type and the probability of each service requester in the plurality of service requesters initiating a travel order in each travel type.

In a possible implementation manner, the data obtaining module is specifically configured to: acquiring second sample data of a trip demand time issued by a service request end in a preset historical time period and a mileage corresponding to the trip demand in a preset mileage range; the travel demand comprises a departure place of the service request terminal and a destination of the service request terminal; the travel demand corresponds to the travel order;

price, trip comfort level, trip quietness of the trip order.

In a possible implementation, the model training module is specifically configured to:

In one possible embodiment, the singles probability computation model includes:

in the formula, β_kIndex coefficients representing the kth service characteristics in the service policy of the trip type i,

P_nirepresenting the probability of the nth service request end initiating a trip order in a trip type i, J representing the number of trip types, and X_kiValue, V, representing the kth service feature in the service policy for travel type i_niA tendency score V representing the tendency of the nth service request end to initiate a line order in the line type i_niAnd K represents the number of service features in the service strategy of the trip type i.

In a fifth aspect, an embodiment of the present application further provides an electronic device, including: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory communicating via the bus when the electronic device is operating, the machine-readable instructions when executed by the processor performing the steps of the first aspect, or any of the possible implementations of the first aspect, or the second aspect, or any of the possible implementations of the second aspect.

In a sixth aspect, this application further provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to perform the steps in the first aspect, or any one of the possible implementations of the first aspect, or the steps in the second aspect, or any one of the possible implementations of the second aspect.

According to the method and the device for predicting the amount of issued orders, firstly, the probability of each service request end in a plurality of service request ends initiating the travel orders is predicted based on the obtained service strategy to be evaluated; predicting the probability of each service request end in the plurality of service request ends issuing a trip order in the trip type based on the service strategy of the trip type aiming at each trip type in the plurality of trip types; and then, predicting the quantity of the travel orders corresponding to each travel type based on the probability of each service request end in the plurality of service request ends initiating the travel orders and the probability of each service request end initiating the travel orders in each travel type. According to the technical scheme, the probability of each service request end initiating a trip order and the probability of each service request end in a plurality of service request ends initiating a trip order in each trip type can be accurately predicted according to the service strategy to be evaluated and the service strategy which does not change, the quantity of trip orders corresponding to each trip type can be accurately predicted on the basis of the obtained accurate probability under the condition that the service strategy of a certain trip type changes, so that the accuracy of predicting the quantity of trip orders corresponding to each trip type is improved, the prediction efficiency is improved, the cost is reduced due to no experiment, and more importantly, the influence on the quantity of trip orders corresponding to each trip type can be exhausted when the service strategy in each trip type changes.

According to the method and the device for training the order issuance probability model, based on the at least one obtained service strategy of each of the multiple trip types and the result data of whether the multiple service request terminals initiate the trip orders in the trip type based on each service strategy of the trip type for each of the multiple trip types, the corresponding relation between each service strategy of each trip type and the probability of the each service request terminal of the multiple service request terminals initiating the trip orders in each trip type is constructed, and the order issuance probability calculation model is obtained. By utilizing the issuing probability calculation model, the probability of issuing the travel orders in each travel type by each service request end in the service request ends under the action of each service strategy of each travel type can be accurately obtained, and the obtained accurate probability is favorable for improving the accuracy of predicting the number of the travel orders corresponding to each travel type.

In order to make the aforementioned objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.

Fig. 1 shows a schematic structural diagram of an invoice amount prediction system provided in an embodiment of the present application.

Fig. 2 shows a schematic structural diagram of an electronic device provided in an embodiment of the present application.

Fig. 3 shows a flowchart of an invoice amount estimation method provided in an embodiment of the present application.

Fig. 4 is a flowchart illustrating a correspondence relationship between a service policy for determining a target trip type and a probability of a trip order being initiated by each service requester in a plurality of service requesters in another method for estimating an issue quantity provided in an embodiment of the present application.

Fig. 5 is a flowchart illustrating a method for predicting a probability that each service requester initiates a travel order in another method for predicting an order issuance amount according to an embodiment of the present application.

Fig. 6 is a flowchart illustrating a method for predicting a probability that each service requester in a plurality of service requesters initiates a travel order in each travel type in another method for estimating an amount of issuance provided in the embodiment of the present application.

Fig. 7 is a flowchart illustrating a correspondence relationship between each service policy of each trip type and a probability of each service requester issuing a trip order in each trip type in another method for estimating an issue quantity provided in an embodiment of the present application.

Fig. 8 is a flowchart illustrating a method for predicting a probability that each service requester in a plurality of service requesters initiates a travel order under a certain travel type in another method for estimating an amount of issuance provided in the embodiment of the present application.

Fig. 9 shows a flowchart of a method for training a hair singles probability model according to an embodiment of the present disclosure.

Fig. 10 is a flowchart illustrating a method for training an order issuance probability model according to another embodiment of the present application, where a corresponding relationship between each service policy of each travel type and a probability of issuing an order in each travel type by each service requester in a plurality of service requesters is constructed.

Fig. 11 shows a schematic structural diagram of an invoice amount prediction apparatus provided in an embodiment of the present application.

Fig. 12 shows a schematic structural diagram of an apparatus for training a hair-single probability model according to an embodiment of the present application.

Detailed Description

In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it should be understood that the drawings in the present application are for illustrative and descriptive purposes only and are not used to limit the scope of protection of the present application. Additionally, it should be understood that the schematic drawings are not necessarily drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of the present application. It should be understood that the operations of the flow diagrams may be performed out of order, and steps without logical context may be performed in reverse order or simultaneously. One skilled in the art, under the guidance of this application, may add one or more other operations to, or remove one or more operations from, the flowchart.

In addition, the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application.

To enable those skilled in the art to utilize the present disclosure, the following embodiments are presented in conjunction with a specific application scenario, "network appointment". It will be apparent to those skilled in the art that the general principles defined herein may be applied to other embodiments and applications without departing from the spirit and scope of the application. Although the present application is described primarily in the context of a net appointment, it should be understood that this is only one exemplary embodiment. The application can be applied to any other traffic type. For example, the present application may be applied to different transportation system environments, including terrestrial, marine, or airborne, among others, or any combination thereof. The vehicle of the transportation system may include a taxi, a private car, a windmill, a bus, a train, a bullet train, a high speed rail, a subway, a ship, an airplane, a spacecraft, a hot air balloon, or an unmanned vehicle, etc., or any combination thereof. The application can also comprise any service system for initiating orders by a service request end or selecting orders by a service providing end, for example, a system for sending and/or receiving express delivery, and a service system for trading between buyers and sellers. Applications of the system or method of the present application may include web pages, plug-ins for browsers, client terminals, customization systems, internal analysis systems, or artificial intelligence robots, among others, or any combination thereof.

It should be noted that in the embodiments of the present application, the term "comprising" is used to indicate the presence of the features stated hereinafter, but does not exclude the addition of further features.

The terms "passenger," "service requestor," and "service requestor" are used interchangeably herein to refer to an individual, entity, or tool that can request or order a service. The terms "driver" and "service provider" are used interchangeably in this application to refer to an individual, entity or tool that can provide a service. In the present application, "passenger" and "service requester" are used interchangeably, and "driver" and "service provider" are used interchangeably.

One aspect of the present application relates to an invoice amount prediction system. The system can predict the probability of each service request end in a plurality of service request ends initiating a travel order based on the obtained service strategy to be evaluated; and predicting the probability of issuing a travel order by each service request end in the plurality of service request ends in the travel type based on the service strategy of the travel type for each travel type in the plurality of travel types, and predicting the quantity of the travel orders corresponding to each travel type based on the probability of issuing the travel order by each service request end in the plurality of service request ends and the probability of issuing the travel order by each service request end in each travel type. The invoice amount estimation system can accurately estimate the order amount corresponding to each travel type under the condition that the service strategy of a certain travel type changes.

It is noted that, before the application is filed, the influence of the change of the service policy of a certain travel type on the order quantity corresponding to each travel type is determined through experiments. However, the issue amount estimation system provided by the application can estimate the number of travel orders corresponding to each travel route based on the service strategy to be estimated and the service strategy which does not change, so that the accuracy of estimated order amount is improved, estimation efficiency is improved and estimation cost is reduced due to no need of experiments, and more importantly, the system can exhaust the influence on the number of travel orders corresponding to each travel type when each service strategy on each travel type changes.

FIG. 1 is a block diagram of an invoice amount prediction system 100 according to some embodiments of the present application. For example, the invoice amount prediction system 100 may be an online transportation service platform for transportation services such as taxi cab, designated driving service, express, carpool, bus service, driver rental, or regular bus service, or any combination thereof. The invoice amount prediction system 100 may include one or more of a server 110, a network 120, a service requester 130, a service provider 140 and a database 150, and the server 110 may include a processor for executing instruction operations.

In some embodiments, the server 110 may be a single server or a group of servers. The set of servers can be centralized or distributed (e.g., the servers 110 can be a distributed system). In some embodiments, the server 110 may be local or remote to the terminal. For example, the server 110 may access information and/or data stored in the service requester 130, the service provider 140, or the database 150, or any combination thereof, via the network 120. As another example, the server 110 may be directly connected to at least one of the service requester 130, the service provider 140, and the database 150 to access stored information and/or data. In some embodiments, the server 110 may be implemented on a cloud platform; by way of example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud (community cloud), a distributed cloud, an inter-cloud, a multi-cloud, and the like, or any combination thereof. In some embodiments, the server 110 may be implemented on an electronic device 200 having one or more of the components shown in FIG. 2 in the present application.

In some embodiments, server 110 may include processor 220. Processor 220 may process information and/or data related to the service request to perform one or more of the functions described herein. For example, the processor 220 may estimate the number of travel orders corresponding to each travel type based on the service policy to be evaluated and the service policy that has not changed. In some embodiments, a processor may include one or more processing cores (e.g., a single-core processor (S) or a multi-core processor (S)). Merely by way of example, a Processor 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 Physical 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 (Reduced Instruction Set computer), a microprocessor, or the like, or any combination thereof.

Network 120 may be used for the exchange of information and/or data. In some embodiments, one or more components (e.g., server 110, service requester 130, service provider 140, and database 150) in the invoice estimation system 100 may send information and/or data to other components. For example, the server 110 may obtain a service request from the service requester 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, Network 120 may include a wired Network, a Wireless Network, a fiber optic Network, a telecommunications Network, an intranet, the internet, a Local Area Network (LAN), a Wide Area Network (WAN), a Wireless Local Area Network (WLAN), a Metropolitan Area Network (MAN), a Wide Area Network (WAN), a Public Switched Telephone Network (PSTN), a bluetooth Network, a ZigBee Network, a Near Field Communication (NFC) Network, or the like, or any combination thereof. In some embodiments, network 120 may include one or more network access points. For example, network 120 may include wired or wireless network access points, such as base stations and/or network switching nodes, through which one or more components of order prediction system 100 may connect to network 120 to exchange data and/or information.

In some embodiments, the user of the service requestor 130 may be someone other than the actual demander of the service. For example, the user a of the service requester 130 may use the service requester 130 to initiate a service request for the actual service demander B (for example, the user a may call a car for his friend B), or receive service information or instructions from the server 110. In some embodiments, the user of the service provider 140 may be the actual provider of the service or may be another person other than the actual provider of the service. For example, user C of service provider 140 may use service provider 140 to receive a service request serviced by actual service provider D (e.g., user C may take an order for driver D employed by user C), and/or information or instructions from server 110.

In some embodiments, the service requester 130 may include a mobile device, a tablet computer, a laptop computer, or a built-in device in a motor vehicle, etc., or any combination thereof. In some embodiments, the mobile device may include a smart home device, a wearable 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 devices may include smart lighting devices, control devices for smart electrical devices, smart monitoring devices, smart televisions, smart cameras, or walkie-talkies, or the like, or any combination thereof. In some embodiments, the wearable device may include a smart bracelet, a smart lace, smart glass, a smart helmet, a smart watch, a smart garment, a smart backpack, a smart accessory, and the like, or any combination thereof. In some embodiments, the smart mobile device may include a smartphone, a Personal Digital Assistant (PDA), a gaming device, a navigation device, or 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 glass, a virtual reality patch, an augmented reality helmet, augmented reality glass, an augmented reality patch, or the like, or any combination thereof. For example, the virtual reality device and/or augmented reality device may include various virtual reality products and the like. In some embodiments, the built-in devices in the motor vehicle may include an on-board computer, an on-board television, and the like. In some embodiments, the service requester 130 may be a device that places a travel order.

Database 150 may store data and/or instructions. In some embodiments, the database 150 may store data obtained from the service requester 130 and/or the service provider 140. In some embodiments, database 150 may store data and/or instructions for the exemplary methods described herein. In some embodiments, database 150 may include mass storage, removable storage, volatile Read-write Memory, or Read-Only Memory (ROM), among others, or any combination thereof. By way of example, mass storage may include magnetic disks, optical disks, solid state drives, and the like; removable memory may include flash drives, floppy disks, optical disks, memory cards, zip disks, tapes, and the like; volatile read-write Memory may include Random Access Memory (RAM); the RAM may include Dynamic RAM (DRAM), Double Data Rate Synchronous Dynamic RAM (DDRSDRAM); static RAM (SRAM), Thyristor-based Random Access Memory (T-RAM), Zero-capacitor RAM (Zero-RAM), and the like. By way of example, ROMs may include Mask Read-Only memories (MROMs), Programmable ROMs (PROMs), Erasable Programmable ROMs (PERROMs), Electrically Erasable Programmable ROMs (EEPROMs), compact disk ROMs (CD-ROMs), digital versatile disks (ROMs), and the like. In some embodiments, database 150 may be implemented on a cloud platform. By way of example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, across clouds, multiple clouds, or the like, or any combination thereof.

In some embodiments, a database 150 may be connected to network 120 to communicate with one or more components of the invoice prediction system 100 (e.g., server 110, service requestor 130, service provider 140, etc.). One or more components in the invoice estimation system 100 may access data or instructions stored in the database 150 via the network 120. In some embodiments, the database 150 may be directly connected to one or more components in the invoice amount projection system 100 (e.g., the server 110, the service requester 130, the service provider 140, etc.); alternatively, in some embodiments, database 150 may also be part of server 110.

In some embodiments, one or more components (e.g., server 110, service requestor 130, service provider 140, etc.) in the invoice estimation system 100 may have access to the database 150. In some embodiments, one or more components in the invoice amount projection system 100 may read and/or modify information related to the service requester, the service provider, or the public, or any combination thereof, when certain conditions are met. For example, server 110 may read and/or modify information for one or more users after receiving a service request. As another example, the service provider 140 may access information related to the service requester when receiving the service request from the service requester 130, but the service provider 140 may not modify the related information of the service requester 130.

Fig. 2 illustrates a schematic diagram of exemplary hardware and software components of an electronic device 200 of a server 110, a service requester 130, a service provider 140, which may implement the concepts of the present application, according to some embodiments of the present application. For example, the processor 220 may be used on the electronic device 200 and to perform the functions herein.

The electronic device 200 may be a general purpose computer or a special purpose computer, both of which may be used to implement the invoice amount prediction method of the present application. Although only a single computer is shown, for convenience, the functions described herein may be implemented in a distributed fashion across multiple similar platforms to balance processing loads.

For example, the electronic device 200 may include a network port 210 connected to a network, one or more processors 220 for executing program instructions, a communication bus 230, and a different form of storage medium 240, such as a disk, ROM, or RAM, or any combination thereof. Illustratively, the computer platform may also include program instructions stored in ROM, RAM, or other types of non-transitory storage media, or any combination thereof. The method of the present application may be implemented in accordance with these program instructions. The electronic device 200 also includes an Input/Output (I/O) interface 250 between the computer and other Input/Output devices (e.g., keyboard, display screen).

For ease of illustration, only one processor is depicted in the electronic device 200. However, it should be noted that the electronic device 200 in the present application may also comprise a plurality of processors, and thus the steps performed by one processor described in the present application may also be performed by a plurality of processors in combination or individually. For example, if the processor of the electronic device 200 executes steps a and B, it should be understood that steps a and B may also be executed by two different processors together or separately in one processor. For example, a first processor performs step a and a second processor performs step B, or the first processor and the second processor perform steps a and B together.

Fig. 3 shows a flowchart of an order quantity estimation method according to an embodiment of the present application, where the method may be applied to a network car appointment scenario to estimate the quantity of travel orders corresponding to each travel type when a service policy of a certain travel type changes. Specifically, as shown in fig. 3, the method for estimating the invoice amount in this embodiment includes the following steps:

s310, predicting the probability of each service request terminal in the plurality of service request terminals initiating a travel order based on the obtained service strategy to be evaluated;

and predicting the probability of each service request end in the plurality of service request ends issuing the outgoing order in the outgoing type based on the service strategy of the outgoing type aiming at each outgoing type in the plurality of outgoing types.

Here, the travel type is a service line corresponding to each vehicle type, and for example, the travel type may include express, car pooling, and sharing. The service policy is a policy that can affect whether the service requester initiates a travel order and at which travel type the travel order is initiated, for example, the service policy includes at least one of the following service characteristics: price, trip comfort level, trip quietness of the trip order. Since the service request end is most sensitive to the price of the travel order, the price of the travel order has the most obvious influence on the quantity of the travel order corresponding to each travel type.

Here, the service policy to be evaluated may be a service policy to be evaluated corresponding to the target trip type. The target trip type is a trip type of the current service strategy to be adjusted, for example, the target trip type is a express train. Since the service request end is most sensitive to the price of the travel order of the express train, and the price of the travel order of the express train can most influence whether the service request end initiates the travel order, when the price of the travel order corresponding to the express train is adjusted, that is, the target travel type is the express train, and the service policy to be evaluated is the price of the travel order corresponding to the express train, the probability of initiating the travel order by each service request end in the plurality of service request ends, which is predicted by the embodiment, is most accurate.

The service policy based on the trip type includes a service policy to be evaluated of a target trip type and a current service policy of other trip types.

The probability that each service request terminal of the plurality of service request terminals initiates a travel order in the travel type means that the service request terminal selects each travel type to initiate the travel order under the condition that it is determined that the service request terminal must initiate the travel order.

And S320, predicting the quantity of the travel orders corresponding to each travel type based on the probability of each service request end in the service request ends initiating the travel orders and the probability of each service request end initiating the travel orders in each travel type.

Here, based on a product of a probability that each service request terminal of the plurality of service request terminals initiates a trip order and a probability that each service request terminal selects each trip type to initiate a trip order, it can be obtained that each service request terminal of the plurality of service request terminals will certainly initiate a trip order, and a probability of initiating a trip order in each trip type, and according to the probability obtained by the multiplication, the number of trip orders corresponding to each trip type can be estimated, and then, a variation of the number of trip orders corresponding to each trip type including the target trip type when the service policy of the target trip type is adjusted to the service policy to be evaluated can be obtained.

In this embodiment, according to the service policy to be evaluated and the service policy that does not change, the probability that each service request terminal initiates a trip order and the probability that each service request terminal of the plurality of service request terminals initiates a trip order in each trip type can be accurately predicted, based on the obtained accurate probability, the number of trip orders corresponding to each trip type can be accurately predicted under the condition that the service policy of a certain trip type changes, so that the accuracy of predicting the number of trip orders is improved, and due to no need of experiments, the prediction efficiency is improved, the prediction cost is reduced, and more importantly, the influence on the number of trip orders corresponding to each trip type when the service policies in each trip type change can be exhausted

In one embodiment, the following steps may be utilized to predict the probability that each service requester in the plurality of service requesters initiates a travel order based on the obtained service policy to be evaluated in the above implementation: and predicting the probability of the trip order initiated by each service request terminal in the plurality of service request terminals under the service strategy to be evaluated based on the corresponding relation between each service strategy of the target trip type and the probability of the trip order initiated by each service request terminal in the plurality of service request terminals and the service strategy to be evaluated.

The correspondence between each service policy of the target trip type and the probability of initiating a trip order by each of the plurality of service requesters is obtained by training according to historical data, where the historical data includes the plurality of service policies of the target trip type and result data of whether each of the plurality of service requesters initiates a trip order under each service policy.

In specific implementation, a Binary logic Model (Binary logic Model) may be used to construct a correspondence between each service policy of the target trip type and a probability that each service requester of the multiple service requesters initiates a trip order, where the obtained correspondence may be regarded as a Model and recorded as a first Model. According to the corresponding relation in the first model and the service strategy to be evaluated, the probability of each service request end in the plurality of service request ends initiating the travel order can be obtained through prediction. The first model simulates the influence of the change of the service strategy on the selection of whether the service request terminal initiates the travel order.

The historical data used for training the first model may be historical data in which the time when the service request terminal initiates the travel demand is within a predetermined historical time period, and the mileage corresponding to the travel demand is within a predetermined mileage range. At this time, the obtained first model has the predetermined history period and the predetermined mileage range as dummy variables. The travel demand comprises a departure place of the service request terminal and a destination of the service request terminal; the travel demand corresponds to the travel order.

The travel demand is input into the order quantity estimation system by the service request terminal, and after the travel demand is input by the service request terminal and the service request terminal determines to initiate a travel order, the order quantity estimation system generates a corresponding travel order according to the travel demand.

When the travel demand is limited by the preset historical time period and the preset mileage range, the first model trained by the historical data matched with the limit is more accurate in predicting the initiation probability of the travel order matched with the limit.

In one embodiment, the building of the corresponding relationship between each service policy of the target trip type and the probability of each service requester in the plurality of service requesters initiating a trip order, that is, the building of the first model, includes the following steps: firstly, performing function operation on each service characteristic in each service strategy of a target trip type to obtain a processed service strategy of the target trip type; and then, constructing a corresponding relation between each processed service strategy of the target trip type and the probability of each service request end of the plurality of service request ends initiating the trip order based on the processed service strategy of the target trip type and the result data of whether each service request end of the plurality of service request ends initiates the trip order under each processed service strategy.

Correspondingly, when the probability that each service request terminal in the plurality of service request terminals initiates the travel order is predicted by using the first model, the method comprises the following steps: firstly, performing function operation on each service characteristic in a service strategy to be evaluated of a target trip type to obtain a processed service strategy to be evaluated; and then, determining the probability of initiating a travel order by each service request terminal based on the corresponding relation between each processed service strategy of the target travel type and the probability of initiating a travel order by each service request terminal in the plurality of service request terminals and the processed service strategies to be evaluated.

In one embodiment, as shown in fig. 4, when the first model is trained by using historical data in the case that the service policy includes only prices of travel orders, the following steps may be further performed:

and S410, performing function operation on the price of each travel order corresponding to the target travel type to obtain the price of the processed travel order.

The function operation can be a logarithmic function operation, and the preprocessing of the historical data is realized.

And S420, based on the price of each processed travel order and result data of whether each service request end of the plurality of service request ends initiates a travel order or not under the price of each processed travel order, constructing a corresponding relation between the price of each processed travel order and the probability of each service request end of the plurality of service request ends initiating a travel order, and obtaining a first model.

The present embodiment trains the first model using the preprocessed historical data.

Since the historical data is preprocessed during model training, when the first model is used to predict the probability of each service requester initiating a travel order, the service policy to be evaluated also needs to be correspondingly preprocessed, and specifically, as shown in fig. 5, the probability of each service requester initiating a travel order can be predicted by using the following steps:

and S510, performing function operation on the price of the to-be-evaluated travel order corresponding to the target travel type to obtain the processed price of the to-be-evaluated travel order.

S520, determining the probability of the trip order initiated by each service request terminal based on the corresponding relation between the processed price of each trip order and the probability of the trip order initiated by each service request terminal in the plurality of service request terminals and the processed price of the trip order to be evaluated.

In one embodiment, the probability of each service requester in the plurality of service requesters initiating a travel order in each travel type may be predicted by: and determining the probability of issuing the outgoing order by each service request terminal in the plurality of service request terminals in each trip type based on the corresponding relation between each service strategy of each trip type and the probability of issuing the outgoing order by each service request terminal in the plurality of service request terminals in each trip type and the service strategy of each trip type.

The correspondence between each service policy of each trip type and the probability of each service requester in the plurality of service requesters initiating a trip order in each trip type is obtained by training according to historical data, where the historical data includes at least one service policy of each trip type and, for each trip type in the plurality of trip types, result data of whether each service requester in the plurality of service requesters initiates a trip order in the trip type based on each service policy of the trip type.

In specific implementation, a Conditional logic Model (Conditional logic Model) may be used to construct a correspondence between each service policy of each trip type and a probability that each service requester of the plurality of service requesters issues a outgoing order in each trip type. The correspondence obtained here can be regarded as one model and is denoted as a second model. According to the corresponding relation in the second model and the service strategy of each current trip type, the probability of each service request end in the plurality of service request ends issuing the trip order in the trip type can be predicted and obtained.

The second model quantificationally measures the influence of the change of the service strategy of a certain trip type on the selection of different trip types by the service request terminal under the condition of giving selectable different trip types. The variation of a certain travel type service strategy can be evaluated through the probability obtained by the first model and the probability obtained by the second model, so that how the quantity of travel orders corresponding to each travel type varies.

Taking the service strategy including only the price of the travel order, taking the travel types as express, carpool and excellent as examples, the historical data used for training the second model is specifically explained as follows:

the price of the travel orders corresponding to the three travel types seen by each service request end is listed into three rows of data, wherein the service request ends ID of the three rows of data are the same, the prices of the travel orders are different, and finally the travel order initiated by the service request end in which travel type needs to be marked, wherein the travel type initiating the travel order is marked as 1, and the rest travel types are marked as 0. The following were used:

the historical data used for training the second model may be historical data in which the time when the service request end issues the travel demand is within a preset historical time period, and the mileage corresponding to the travel demand is within a preset mileage range. At this time, the second model is obtained with the predetermined history period and the predetermined mileage range as dummy variables.

When the travel demand is limited by the preset historical time period and the preset mileage range, the second model trained by the historical data matched with the limit is more accurate in predicting the probability of the travel order matched with the limit being initiated in each travel type.

In a specific implementation, a plurality of different predetermined historical time periods and a plurality of predetermined mileage ranges may be set, a plurality of second models may be trained according to historical data of the different predetermined historical time periods and the different predetermined mileage ranges, each second model has a predetermined historical time period and a plurality of predetermined mileage ranges matched therewith, and then when predicting a probability that each service requester in the plurality of service requesters initiates a trip order in each trip type by using the second models, as shown in fig. 6, the method may include the following steps:

s610, selecting a corresponding relation between each service strategy of each trip type with corresponding dummy variables and the probability of issuing a trip order in each trip type of each service request end from a plurality of service request ends based on the release time of each trip requirement of each service request end and the mileage corresponding to each trip requirement.

In this case, a second model is selected according to the release time of the travel demand of the service request terminal and the mileage corresponding to the travel demand.

S620, determining the probability of issuing the outgoing order by each service request end in the plurality of service request ends in the trip type based on the corresponding relation between each selected service strategy of each trip type and the probability of issuing the outgoing order by each service request end in the plurality of service request ends in each trip type and the service strategy of each trip type.

In essence, the probability of each service requester in the plurality of service requesters issuing a row order in the travel type is determined by using the selected second model and the current service policy of each travel type.

In one embodiment, as shown in FIG. 7, the second model may be constructed using the following steps:

s710, based on each service policy of each trip type in the second sample data and for each trip type in the second sample data, based on result data of whether each service requester in the plurality of service requesters initiates a trip order in the trip type under each service policy of the trip type, determining a probability that each service requester in the plurality of service requesters initiates a trip order in the trip type under each service policy of the trip type.

Here, the travel order may be a travel order that matches the predetermined historical time period and the predetermined mileage range described above.

S720, based on the probability that each service request end in the plurality of service request ends initiates a travel order under each travel type under each service strategy of each travel type, determining the tendency score of each service request end in the plurality of service request ends initiating the travel order under each service strategy of each travel type.

And S730, determining an index coefficient corresponding to each service feature of each service strategy of each trip type based on the tendency score of each service request terminal of the plurality of service request terminals initiating the trip order under each service strategy of each trip type and the value of each service feature of each service strategy of each trip type, and obtaining the corresponding relation between each service strategy of each trip type and the probability of each service request terminal of the plurality of service request terminals initiating the trip order under each trip type, namely obtaining a second model.

Specifically, the second model may be:

As shown in fig. 8, predicting the probability of issuing a row order by each service requester in a plurality of service requesters in a certain row type by using the second model constructed in the embodiment may include the following steps:

and S810, determining an index coefficient of each service characteristic in the travel type service strategy based on the value of each service characteristic in the travel type service strategy.

S820, determining the tendency score of each server request end in the plurality of service request ends for issuing the order for the trip in the trip type based on the index coefficient of each service characteristic in the service strategy of the trip type and the value of each service characteristic in the service strategy of the trip type.

Specifically, the trend score can be calculated using the following formula:

in the formula, V_niRepresents the tendency score of the nth service request end to initiate a line order in the line type i, β_kIndex coefficient, X, representing the kth service characteristic in the service strategy for travel type i_kiAnd K represents the number of service features in the current service strategy of the trip type i.

And S830, predicting the probability of each service request end in the plurality of service request ends initiating a row order in the travel type based on the tendency score.

Specifically, the probability that each service requester in the plurality of service requesters initiates a row order in the travel type can be predicted by using the following formula:

Fig. 9 shows a method for training an order issuance probability model according to an embodiment of the present application, where the order issuance probability model is a second model in the above embodiment, and the training method is the same as the above-mentioned corresponding relationship between each service policy for constructing each trip type and a probability of issuing a row order by each service requester in a plurality of service requesters in each trip type, specifically, as shown in fig. 9, the method includes the following steps: :

s910, second sample data is obtained, wherein the second sample data comprises at least one service strategy of each of the multiple trip types and result data of whether each of the multiple service request terminals issues a trip order in each of the multiple trip types based on each service strategy of the trip type.

S920, based on the second sample data, constructing a corresponding relation between the service strategy of each trip type and the probability of each service request end of the plurality of service request ends issuing the trip order in each trip type, and obtaining an order issuing probability calculation model.

In one embodiment, a conditional logic model is utilized to construct a corresponding relation between each service strategy of each trip type and the probability of each service request end in a plurality of service request ends issuing a trip order in each trip type.

In one embodiment, the obtaining the second sample data includes the following steps: and acquiring second sample data of the trip demand issued by the service request end within a preset historical time period and the mileage corresponding to the trip demand within a preset mileage range. The travel demand comprises a departure place of the service request terminal and a destination of the service request terminal; the travel demand corresponds to the travel order.

And the singing probability model takes the preset historical time period and the preset mileage range as dummy variables.

In one embodiment, the service policy includes at least one of the following service characteristics: price, trip comfort level, trip quietness of the trip order. As shown in fig. 10, based on the second sample data, constructing a corresponding relationship between each service policy of each trip type and a probability that each service requester of the plurality of service requesters issues a trip order in each trip type includes:

s1010, based on each service policy of each trip type in the second sample data and for each trip type in the second sample data, based on result data of whether each service requester in the plurality of service requesters initiates a trip order in the trip type under each service policy of the trip type, and determining a probability that each service requester in the plurality of service requesters initiates a trip order in the trip type under each service policy of the trip type.

S1020, based on the probability that each service requester in the plurality of service requesters initiates a travel order in each travel type under each service policy of each travel type, determining a tendency score of each service requester in the plurality of service requesters initiating a travel order in each service policy of each travel type.

S1030, determining an index coefficient corresponding to each service feature of each service strategy of each trip type based on the tendency score of each service request terminal of the plurality of service request terminals initiating trip orders under each service strategy of each trip type and the value of each service feature of each service strategy of each trip type, and obtaining the corresponding relation between each service strategy of each trip type and the probability of each service request terminal of the plurality of service request terminals initiating trip orders under each trip type.

Here, the singles probability computation model includes:

Fig. 11 is a block diagram illustrating an invoice amount prediction apparatus according to some embodiments of the present application, which implements functions corresponding to the steps performed by the invoice amount prediction method described above. The device may be understood as the server or the processor of the server, or may be understood as a component that is independent from the server or the processor and implements the functions of the present application under the control of the server, and as shown in the figure, the invoice amount prediction device may include a probability prediction module 1110 and an invoice amount prediction module 1120.

The probability prediction module 1110 may be configured to predict, based on the obtained service policy to be evaluated, a probability that each service request terminal of the plurality of service request terminals initiates a travel order;

The single quantity prediction module 1120 may be configured to predict the quantity of the travel orders corresponding to each travel type based on the probability of each service requester initiating a travel order and the probability of each service requester initiating a travel order in each travel type.

The service strategy to be evaluated is a service strategy to be evaluated corresponding to the target trip type.

In one embodiment, the probabilistic prediction module 1110 includes a first prediction sub-module 11101 for: and predicting the probability of each service request terminal in the plurality of service request terminals initiating the trip order under the service policy to be evaluated based on the corresponding relation between each service policy of the target trip type and the probability of each service request terminal in the plurality of service request terminals initiating the trip order and the service policy to be evaluated.

In one embodiment, the first prediction sub-module 11101 is specifically configured to:

and constructing a corresponding relation between each service strategy of the target trip type and the probability of each service request end in a plurality of service request ends initiating a trip order based on the first sample data.

The first prediction sub-module 11101 is specifically configured to construct, by using a binary logic stett model, a corresponding relationship between each service policy of the target trip type and a probability of initiating a trip order by each service requester of a plurality of service requesters.

and the corresponding relation between each service strategy of the target trip type and the probability of launching a trip order by each service request end in a plurality of service request ends takes the preset historical time period and the preset mileage range as dummy variables.

In one embodiment, the service policy includes at least one of the following service characteristics: price, trip comfort level, trip quietness of the trip order. The first prediction submodule 11101 is specifically configured to:

The function operation is a logarithmic function operation.

In one embodiment, the probabilistic prediction module 1110 includes a second prediction sub-module 11102, the second prediction sub-module 11102 configured to: and determining the probability of issuing the outgoing order by each service request terminal in the plurality of service request terminals in each trip type based on the corresponding relation between each service strategy of each trip type and the probability of issuing the outgoing order by each service request terminal in the plurality of service request terminals in each trip type and the service strategy of each trip type.

In one embodiment, the second prediction sub-module 11102 is specifically configured to:

acquiring second sample data, wherein the second sample data comprises at least one service strategy of each trip type and result data of whether each service request terminal of a plurality of service request terminals initiates a trip order in each trip type according to each service strategy of the trip types;

and constructing a corresponding relation between each service strategy of each trip type and the probability of issuing a trip order by each service request end in the plurality of service request ends in each trip type by using the conditional logic model.

acquiring second sample data of a trip demand issued by a service request end within a preset historical time period and a mileage corresponding to the trip demand within a preset mileage range; the travel demand comprises a departure place of the service request terminal and a destination of the service request terminal; the travel demand corresponds to the travel order;

and the corresponding relation between each service strategy of each trip type and the probability of each service request end in the plurality of service request ends for issuing the trip order in each trip type takes the preset historical time period and the preset mileage range as dummy variables.

and determining the probability of issuing the outgoing order by each service request end in the plurality of service request ends in the trip type based on the corresponding relation between each selected service strategy of each trip type and the probability of issuing the outgoing order by each service request end in the plurality of service request ends in each trip type and the service strategy of the trip type.

In one embodiment, the service policy includes at least one of the following service characteristics: price, trip comfort level, trip quietness of the trip order. The second prediction sub-module 11102 is specifically configured to:

Determining the probability of each service request end in the plurality of service request ends initiating a row order in a row type i by using the following formula:

in the formula, V_niIndicating that the nth service request end initiates the sending in the travel type iTrend score, P, of line order_niRepresenting the probability of the nth service request end initiating a trip order in a trip type i, J representing the number of trip types, V_niAnd the tendency score represents that the nth service request end initiates a line order in the line type j.

Determining a tendency score corresponding to the travel type i by using the following formula:

Fig. 12 is a block diagram illustrating an apparatus for training a probabilistic model for a billing system according to some embodiments of the present application, where the apparatus for training the probabilistic model for a billing system implements functions corresponding to the steps performed by the method for training the probabilistic model for a billing system as described above. The apparatus may be understood as the server or the processor of the server, or may be understood as a component that is independent of the server or the processor and implements the functions of the present application under the control of the server, and as shown in the figure, the apparatus for training the singleton probability model may include a data obtaining module 1210 and a model training module 1220.

The data obtaining module 1210 may be configured to obtain second sample data, where the second sample data includes at least one service policy for each of multiple trip types, and result data of whether each of the multiple service requesters issues a trip order in each of the multiple trip types based on the service policy for the trip type.

The model training module 1220 may be configured to construct, based on the second sample data, a correspondence between each service policy of each trip type and a probability that each service requester of the multiple service requesters issues a trip order in each trip type, so as to obtain an order issuance probability calculation model.

In one embodiment, the model training module 1220 uses a conditional logic model to construct a correspondence between each service policy of each travel type and a probability that each service requester of a plurality of service requesters will initiate a travel order in each travel type.

In one embodiment, the data obtaining module 1210 is specifically configured to: acquiring second sample data of a trip demand issued by a service request end within a preset historical time period and a mileage corresponding to the trip demand within a preset mileage range; the travel demand comprises a departure place of the service request terminal and a destination of the service request terminal; the travel demand corresponds to the travel order;

In one embodiment, the service policy includes at least one of the following service characteristics: price, trip comfort level, trip quietness of the trip order. In this embodiment, the model training module 1220 is specifically configured to:

The singleout probability calculation model comprises:

The present embodiment discloses a computer-readable storage medium having stored thereon a computer program which, when being executed by a processor, performs the steps of the method for estimating an invoice amount or the steps of the method for training an invoice probability model of the above-mentioned embodiments.

The present invention further provides a computer program product for performing route recommendation, which includes a computer-readable storage medium storing processor-executable nonvolatile program code, where instructions included in the program code may be used to execute the method described in the foregoing method embodiment, and specific implementation may refer to the method embodiment, which is not described herein again.

The modules may be connected or in communication with each other via a wired or wireless connection. The wired connection may include a metal cable, an optical cable, a hybrid cable, etc., or any combination thereof. The wireless connection may comprise a connection over a LAN, WAN, bluetooth, ZigBee, NFC, or the like, or any combination thereof. Two or more modules may be combined into a single module, and any one module may be divided into two or more units.

It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system and the apparatus described above may refer to corresponding processes in the method embodiments, and are not described in detail in this application. In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. The above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical division, and there may be other divisions in actual implementation, and for example, a plurality of modules or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or modules through some communication interfaces, and may be in an electrical, mechanical or other form.

The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a U disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method for predicting an invoice amount is characterized by comprising the following steps:

2. The method according to claim 1, wherein the service policy to be evaluated is a service policy to be evaluated corresponding to a target trip type.

3. The method according to claim 2, wherein predicting the probability of each service requester initiating a travel order based on the obtained service policy to be evaluated comprises:

and predicting the probability of the trip order initiated by each service request terminal in the plurality of service request terminals under the service strategy to be evaluated based on the corresponding relation between each service strategy of the target trip type and the probability of the trip order initiated by each service request terminal in the plurality of service request terminals and the service strategy to be evaluated.

4. The method of claim 3, further comprising the step of constructing a correspondence between each service policy of the target travel type and a probability of each service requester of a plurality of service requesters initiating a travel order:

acquiring first sample data, wherein the first sample data comprises a plurality of service strategies of a target trip type and result data of whether each service request terminal in a plurality of service request terminals initiates a trip order or not under each service strategy in the first sample data;

and constructing a corresponding relation between each service strategy of the target trip type and the probability of each service request end in the plurality of service request ends initiating the trip order based on the first sample data.

5. The method of claim 4, further comprising:

and constructing a corresponding relation between each service strategy of the target trip type and the probability of each service request end in the plurality of service request ends initiating the trip order by utilizing a binary classification logic Stent model.

6. The method of claim 5, wherein the obtaining the first sample data comprises:

and the corresponding relation between each service strategy of the target trip type and the probability of each service request end in a plurality of service request ends initiating a trip order takes the preset historical time period and the preset mileage range as dummy variables.

7. The method of claim 4, wherein the service policy comprises at least one of the following service characteristics:

price, trip comfort level, trip quietness of the trip order.

8. The method according to claim 7, wherein the constructing a corresponding relationship between each service policy of the target travel type and a probability of each service requester initiating a travel order based on the first sample data comprises:

9. The method of claim 8, wherein the function operation is a logarithmic function operation.

10. The method of claim 1, wherein predicting the probability of each of the plurality of service requesters initiating a row order for each of the travel types comprises:

and determining the probability of issuing the outgoing order by each service request terminal in the plurality of service request terminals in each trip type based on the corresponding relation between each service strategy of each trip type and the probability of issuing the outgoing order by each service request terminal in the plurality of service request terminals in each trip type and the service strategy of each trip type.

11. The method of claim 10, further comprising the step of establishing a correspondence between each service policy for each travel type and a probability that each service requester of the plurality of service requesters will place a travel order for each travel type:

12. The method of claim 11, further comprising:

13. The method of claim 12, wherein said obtaining second sample data comprises:

14. The method of claim 13, wherein predicting the probability of each of the plurality of service requesters initiating a row order for the travel type comprises:

15. The method of claim 11, wherein the service policy comprises at least one of the following service characteristics:

price, trip comfort level, trip quietness of the trip order.

16. The method of claim 15, wherein the constructing a correspondence between each service policy for each travel type and a probability of each service requester in the plurality of service requesters initiating a travel order for each travel type based on the second sample data comprises:

17. The method of claim 16, wherein predicting the probability of each of the plurality of service requesters initiating a travel order for the travel type based on the service policy for the travel type comprises:

18. The method of claim 17, wherein the probability of each of the plurality of service requesters initiating a row order under row type i is determined using the following equation:

19. The method according to claim 18, wherein the tendency score corresponding to the travel type i is determined by using the following formula:

20. A method of training a hair singles probability model, comprising:

acquiring second sample data, wherein the second sample data comprises at least one service strategy of each of a plurality of trip types and result data of whether each of a plurality of service request terminals initiates a trip order in each of the plurality of trip types based on each service strategy of the trip type;

21. The method of claim 20, further comprising:

22. The method of claim 21, wherein said obtaining second sample data comprises:

23. The method of claim 20, wherein the service policy comprises at least one of the following service characteristics:

price, trip comfort level, trip quietness of the trip order.

24. The method of claim 23, wherein said constructing a correspondence between each service policy for each travel type and a probability of each service requester in the plurality of service requesters initiating a travel order for each travel type based on the second sample data comprises:

25. The method of claim 23, wherein the singles probability computation model comprises:

26. An invoice amount estimation device, comprising:

27. The apparatus according to claim 26, wherein the service policy to be evaluated is a service policy to be evaluated corresponding to a target trip type.

28. The apparatus of claim 27, wherein the probabilistic prediction module comprises a first prediction sub-module configured to:

29. The apparatus of claim 28, wherein the first predictor module is further configured to:

30. The apparatus according to claim 29, wherein the first prediction sub-module is specifically configured to use a binary logic stedt model to construct a correspondence between each service policy of the target travel type and a probability of each service requester initiating a travel order among a plurality of service requesters.

31. The apparatus of claim 30, wherein the first prediction sub-module is specifically configured to:

32. The apparatus of claim 29, wherein the service policy comprises at least one of the following service characteristics:

price, trip comfort level, trip quietness of the trip order.

33. The apparatus of claim 32, wherein the first predictor module is further configured to:

34. The apparatus of claim 33, wherein the function operation is a logarithmic function operation.

35. The apparatus of claim 26, wherein the probabilistic prediction module comprises a second prediction sub-module configured to: and determining the probability of issuing the outgoing order by each service request terminal in the plurality of service request terminals in each trip type based on the corresponding relation between each service strategy of each trip type and the probability of issuing the outgoing order by each service request terminal in the plurality of service request terminals in each trip type and the service strategy of each trip type.

36. The apparatus of claim 35, wherein the second predictor module is further configured to:

acquiring second sample data, wherein the second sample data comprises at least one service strategy of each trip type and result data of whether each service request terminal of a plurality of service request terminals issues a trip order in each trip type according to each service strategy of the trip type;

37. The apparatus of claim 36, wherein the second predictor module is further configured to:

38. The apparatus of claim 37, wherein the second predictor module is further configured to:

39. The apparatus of claim 38, wherein the second predictor module is further configured to:

40. The apparatus of claim 36, wherein the service policy comprises at least one of the following service characteristics:

price, trip comfort level, trip quietness of the trip order.

41. The apparatus of claim 40, wherein the second predictor module is further configured to:

42. The apparatus according to claim 41, wherein the second predictor module is further configured to:

43. The apparatus of claim 41, wherein the probability of each of the plurality of service requesters initiating a row order under row type i is determined using the following formula:

44. The apparatus according to claim 43, wherein the tendency score corresponding to the travel type i is determined by using the following formula:

45. An apparatus for training a hair singles probability model, comprising:

the data acquisition module is used for acquiring second sample data, wherein the second sample data comprises at least one service strategy of each of a plurality of trip types and result data of whether each service request of a plurality of service request terminals issues a trip order in each service strategy of the trip type or not for each trip type of the plurality of trip types;

46. The apparatus of claim 45, wherein the model training module uses a conditional logic model to construct a correspondence between each service policy for each travel type and a probability that each of the plurality of service requesters will place outgoing orders for each travel type.

47. The apparatus of claim 46, wherein the data acquisition module is specifically configured to: acquiring second sample data of a trip demand issued by a service request end within a preset historical time period and a mileage corresponding to the trip demand within a preset mileage range; the travel demand comprises a departure place of the service request terminal and a destination of the service request terminal; the travel demand corresponds to the travel order;

48. The apparatus of claim 45, wherein the service policy comprises at least one of the following service characteristics:

price, trip comfort level, trip quietness of the trip order.

49. The apparatus of claim 48, wherein the model training module is specifically configured to:

50. The apparatus of claim 48, wherein the singles probability computation model comprises:

in the formula, β_kIndex coefficient, P, representing the kth service characteristic in the service strategy for travel type i_niIndicating that the nth service request end is onThe probability of issuing a line order is issued for line type i, J represents the number of travel types, X_kiValue, V, representing the kth service feature in the service policy for travel type i_niA tendency score V representing the tendency of the nth service request end to initiate a line order in the line type i_niAnd K represents the number of service features in the service strategy of the trip type i.

51. An electronic device, comprising: a processor, a storage medium and a bus, the storage medium storing machine-readable instructions executable by the processor, the processor and the storage medium communicating via the bus when the electronic device is operating, the processor executing the machine-readable instructions to perform the steps of the method for estimating a invoice amount according to any one of claims 1 to 19 or the steps of the method for training a probabilistic model of invoice according to any one of claims 20 to 25.

52. A computer-readable storage medium, having stored thereon a computer program for performing, when being executed by a processor, the steps of the method for estimating an invoice amount according to any one of claims 1 to 19 or the steps of the method for training an invoice probability model according to any one of claims 20 to 25.