CN111262716A

CN111262716A - Registration probability estimation method and device and probability estimation model construction method and device

Info

Publication number: CN111262716A
Application number: CN201811459856.XA
Authority: CN
Inventors: 何龙
Original assignee: Beijing Didi Infinity Technology and Development Co Ltd
Current assignee: Beijing Didi Infinity Technology and Development Co Ltd
Priority date: 2018-11-30
Filing date: 2018-11-30
Publication date: 2020-06-09

Abstract

The application provides a registration probability pre-estimation method and device and a probability pre-estimation model construction method and device, wherein characteristic data corresponding to an unregistered service request end is obtained firstly, and the unregistered service request end obtains an information obtaining mode of each service resource information; and then, determining the probability of the unregistered service request terminal for executing the registration operation under the action of each service resource information based on the acquired characteristic data and information acquisition mode corresponding to the unregistered service request terminal, the probability of the service request terminal for executing the registration operation under the action of each service resource information, and the corresponding relation between the characteristic data and the information acquisition mode of the service request terminal. According to the technical scheme, the probability of executing the registration operation of the unregistered service request terminal under the action of each service resource information can be accurately obtained, and the service resource information matched with the unregistered service request terminal can be pushed to the unregistered service request terminal based on the obtained accurate probability.

Description

Registration probability estimation method and device and probability estimation model construction method and device

Technical Field

The application relates to the technical field of calculation and prediction analysis, in particular to a registration probability prediction method and device and a probability prediction model construction method and device.

Background

At present, with the improvement and the upgrade of network car booking services and the improvement of living standard of people, more and more users depend on network car booking for going out. In order to increase users using the online car appointment platform, some service resource information is pushed for users who are not registered on the online car appointment platform, and the users may perform registration operation on the online car appointment platform under the action of some service resource information. After registration, the probability that the user will use the net to make an appointment for a trip is obviously increased.

Since service resource information acting on registration behaviors of different users may be different, in order to enable unregistered users to perform registration operations on the online appointment platform to the maximum extent, service resource information matched with the unregistered users needs to be pushed for the different users. However, currently, the probability of the user performing the registration operation under the action of each service resource information cannot be accurately estimated, so that service resource information more beneficial to the user performing the registration operation cannot be pushed for the user, that is, service resource information matched with the user cannot be pushed for the user.

Disclosure of Invention

In view of this, an object of the embodiments of the present application is to provide a registration probability estimation method and apparatus, and a probability estimation model construction method and apparatus, which can accurately obtain the probability of executing a registration operation by an unregistered service request end under the action of each service resource information, and can push service resource information matched with the unregistered service request end based on the obtained accurate probability.

In a first aspect, an embodiment of the present application provides a registration probability estimation method, including:

acquiring characteristic data corresponding to the unregistered service request terminal and an information acquisition mode of each service resource information acquired by the unregistered service request terminal;

and determining the probability of executing the registration operation of the unregistered service request terminal under the action of each service resource information based on the acquired feature data and the acquired information acquisition mode corresponding to the unregistered service request terminal.

In a possible implementation manner, the obtaining feature data corresponding to an unregistered service request includes:

acquiring at least one registered service request end related to an unregistered service request end;

and determining the characteristic data corresponding to the unregistered service request terminal based on the acquired characteristic data corresponding to the at least one registered service request terminal.

In a possible implementation manner, the determining, based on the obtained feature data corresponding to the at least one registered service request end, the feature data corresponding to the unregistered service request end includes:

acquiring a correlation coefficient between each registered service request end and the unregistered service request end;

determining first characteristic subdata corresponding to the unregistered service request terminal based on each acquired association coefficient and characteristic data corresponding to the registered service request terminal corresponding to each association coefficient;

acquiring feature data of the unregistered service request terminal to obtain second feature subdata corresponding to the unregistered service request terminal;

and combining the first characteristic subdata and the second characteristic subdata to obtain characteristic data corresponding to the unregistered service request terminal.

In a possible implementation manner, the determining, based on the acquired feature data and the acquired information acquisition manner corresponding to the unregistered service request terminal, a probability that the unregistered service request terminal performs a registration operation under the action of each service resource information includes:

acquiring historical sample data, wherein the historical sample data corresponds to the probability of executing registration operation of each service request end in the historical sample data under the action of each service resource information; the historical sample data comprises characteristic data and an information acquisition mode corresponding to a plurality of service request terminals when the service request terminals are not registered;

and determining the probability of executing the registration operation of the unregistered service request terminal under the action of each service resource information based on the acquired corresponding relation and the characteristic data and the information acquisition mode corresponding to the unregistered service request terminal.

In a possible implementation manner, the method for estimating registration probability further includes the step of establishing a corresponding relationship between historical sample data and the probability that each service request terminal in the historical sample data performs registration operation under the action of each service resource information:

acquiring registration result data of each service request terminal in history sample data under the action of each service resource information;

based on the acquired registration result data, determining the probability of executing registration operation of each service request terminal in the historical sample data under the action of each service resource information;

and establishing the corresponding relation between the probability of each service request end in the historical sample data executing the registration operation under the action of each service resource information and the characteristic data and the information acquisition mode of the corresponding service request end.

In a possible implementation manner, the historical sample data is data within a predetermined area range; the unregistered service request terminal is located in the predetermined area range.

In a possible implementation manner, the registration probability estimation method further includes:

and determining the unit registration conversion rate corresponding to each service resource information based on each service resource information and the probability of executing registration operation of the unregistered service request terminal under the action of each service resource information.

In one possible embodiment, the unit registered conversion is determined using the following equation:

g＝(Pn-P)/Fn

wherein g represents the unit registration conversion; pn represents the probability of the unregistered service requester performing the registration operation under the action of the nth service resource information, Fn represents the nth service resource information, and P represents the probability of the unregistered service requester performing the registration operation under the action of no service resource information, where n is a positive integer.

selecting target service resource information from each service resource information based on the unit registration conversion rate corresponding to each service resource information and the probability of executing registration operation of an unregistered service request terminal under the action of each service resource information;

and pushing the selected target service resource information to an unregistered service request terminal.

In a second aspect, an embodiment of the present application provides a method for constructing a probability pre-estimation model, including:

acquiring corresponding characteristic data of a plurality of service request terminals when the service request terminals are not registered, and acquiring information of each service resource information by each service request terminal;

acquiring registration result data of each service request terminal under the action of each service resource information;

determining the probability of executing the registration operation of each service request terminal under the action of each service resource information based on the acquired registration result data;

and establishing a corresponding relation between the probability of each service request end executing the registration operation under the action of each service resource information and the characteristic data and the information acquisition mode of the corresponding service request end.

In one possible implementation, the plurality of service requesters are located within a predetermined area.

In a third aspect, an embodiment of the present application provides a registration probability estimating apparatus, including:

the information acquisition module is used for acquiring the characteristic data corresponding to the unregistered service request terminal and the information acquisition mode of each service resource information acquired by the unregistered service request terminal;

and the probability prediction module is used for determining the probability of executing the registration operation of the unregistered service request terminal under the action of each service resource information based on the acquired feature data and the acquired information acquisition mode corresponding to the unregistered service request terminal.

In one possible implementation, the information obtaining module includes:

the associated user determining submodule is used for acquiring at least one registered service request end associated with the unregistered service request end;

and the characteristic data acquisition submodule is used for determining the characteristic data corresponding to the unregistered service request terminal based on the acquired characteristic data corresponding to the at least one registered service request terminal.

In a possible implementation, the feature data obtaining sub-module is specifically configured to:

In one possible embodiment, the probability prediction module comprises:

the corresponding relation acquisition submodule is used for acquiring the corresponding relation between the historical sample data and the probability of executing the registration operation of each service request end in the historical sample data under the action of each service resource information; the historical sample data comprises characteristic data and an information acquisition mode corresponding to a plurality of service request terminals when the service request terminals are not registered;

and the probability prediction sub-module is used for determining the probability of executing the registration operation of the unregistered service request terminal under the action of each service resource information based on the acquired corresponding relation and the characteristic data and the information acquisition mode corresponding to the unregistered service request terminal.

In a possible implementation manner, the registration probability estimating apparatus further includes:

the historical data acquisition module is used for acquiring registration result data of each service request end in the historical sample data under the action of each service resource information;

the probability determining module is used for determining the probability of executing the registration operation of each service request end in the historical sample data under the action of each service resource information based on the acquired registration result data;

and the corresponding relation determining module is used for establishing the corresponding relation between the probability of executing the registration operation of each service request end in the historical sample data under the action of each service resource information and the characteristic data and the information acquisition mode of the corresponding service request end.

and the conversion rate determining module is used for determining the unit registration conversion rate corresponding to each service resource information based on each service resource information and the probability of executing registration operation of the unregistered service request terminal under the action of each service resource information.

In one possible embodiment, the conversion determination module determines the unit registered conversion using the following equation:

g＝(Pn-P)/Fn

the service resource information selection module is used for selecting target service resource information from each service resource information based on the unit registration conversion rate corresponding to each service resource information and the probability of executing registration operation of an unregistered service request terminal under the action of each service resource information;

and the service resource information pushing module is used for pushing the selected target service resource information to the unregistered service request terminal.

In a fourth aspect, an embodiment of the present application provides an apparatus for constructing a probability pre-estimation model, including:

the system comprises a characteristic information acquisition module, a characteristic information acquisition module and a characteristic information acquisition module, wherein the characteristic information acquisition module is used for acquiring corresponding characteristic data of a plurality of service request terminals when the service request terminals are not registered, and an information acquisition mode for each service request terminal to acquire each service resource information;

the result data acquisition module is used for acquiring registration result data of each service request end under the action of each service resource information;

a probability obtaining module, configured to determine, based on the obtained registration result data, a probability that each service request end performs a registration operation under the action of each service resource information;

and the model establishing module is used for establishing a corresponding relation between the probability of executing the registration operation of each service request end under the action of each service resource information and the characteristic data and the information acquisition mode of the corresponding service request end.

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, the steps of any of the possible implementations of the first aspect, the second aspect, or the steps of 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 of the first aspect, any of the possible implementations of the first aspect, the second aspect, or any of the possible implementations of the second aspect.

The registration probability pre-estimation method and the device provided by the embodiment of the application firstly acquire the characteristic data corresponding to the unregistered service request terminal and the information acquisition mode of each service resource information acquired by the unregistered service request terminal; and then, based on the acquired feature data and the acquired information acquisition mode corresponding to the unregistered service request terminal, determining the probability of executing the registration operation of the unregistered service request terminal under the action of each service resource information. According to the technical scheme, based on the acquired feature data and the information acquisition mode corresponding to the unregistered service request terminal, the probability of executing the registration operation of the unregistered service request terminal under the action of each service resource information can be accurately obtained, and the service resource information matched with the unregistered service request terminal can be pushed for the unregistered service request terminal based on the obtained accurate probability, so that the unregistered service request terminal can be prompted to execute the registration operation to the greatest extent.

The probability pre-estimation model construction method and device provided by the embodiment of the application provide the probability of executing the registration operation under the action of each service resource information of each service request end and the corresponding relation between the characteristic data of the corresponding service request end and the information acquisition mode, and based on the corresponding relation and the acquired characteristic data of the unregistered service request end and the acquired information acquisition mode, the probability of executing the registration operation under the action of each service resource information of the unregistered service request end can be accurately pre-estimated. Based on the obtained accurate probability, the service resource information matched with the unregistered service request terminal can be pushed to the unregistered service request terminal, so that the unregistered service request terminal can be prompted to execute registration operation to the greatest extent.

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 is a block diagram illustrating a registration probability estimation system according to an embodiment of the present application;

fig. 2 illustrates a block diagram of an electronic device provided by an embodiment of the present application;

fig. 3 is a flowchart illustrating a registration probability estimation method according to an embodiment of the present application;

fig. 4 is a flowchart illustrating a method for obtaining feature data corresponding to an unregistered service request terminal in another registration probability estimation method according to an embodiment of the present application;

fig. 5 is a flowchart illustrating a corresponding relationship between feature data and an information obtaining manner corresponding to each service request end in a plurality of service request ends when the service request end is unregistered and a probability that each service request end performs a registration operation under the action of each service resource information in another registration probability estimating method provided in the embodiment of the present application;

fig. 6 is a flowchart illustrating pushing service resource information for an unregistered service requester in another registration probability estimation method according to an embodiment of the present application;

FIG. 7 is a flowchart illustrating a method for constructing a probability prediction model according to an embodiment of the present disclosure;

fig. 8 is a block diagram illustrating a registration probability estimating apparatus according to an embodiment of the present application;

fig. 9 shows a block diagram of a probability prediction model construction device 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 present application is also applicable to any service system in which a user registers, for example, a system for sending and/or receiving a courier. Applications of the apparatus or method of the present application may include web pages, plug-ins to browsers, custom 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," "user" are used interchangeably in this application 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.

One aspect of the present application relates to a registration probability prediction system. The system can determine the probability of executing the registration operation of the unregistered service request terminal under the action of each service resource information based on the acquired feature data and the acquired information acquisition mode corresponding to the unregistered service request terminal. Compared with the prior art, the pre-estimated probability provided by the registration probability pre-estimation system is obviously improved in accuracy. Then, based on the obtained accurate probability, the service resource information matched with the unregistered service request terminal can be pushed to the unregistered service request terminal, and the unregistered service request terminal is prompted to execute the registration operation to the maximum extent.

FIG. 1 is a block diagram of a registration probability estimation system 100 according to some embodiments of the present application. For example, the registration probability prediction system 100 may be an online transportation service platform for transportation services such as taxis, designated driving services, express, carpools, bus services, driver rentals, or regular bus services, or any combination thereof. The registration probability estimation 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. 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 Computing, RISC), 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 requestor 130, service provider 140, and database 150) in the registration probability pre-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, one or more components (e.g., server 110, service requestor 130, service provider 140, etc.) in the registration probability prediction system 100 may have access to a database 150. In some embodiments, one or more components of the registration probability prediction system 100 may read and/or modify information related to the service requestor, 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.

In some embodiments, the exchange of information by one or more components in the registration probability prediction system 100 may be accomplished by requesting a service. The object of the service request is the probability of executing the registration operation by the unregistered service requester.

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 registration probability estimation 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 is a flowchart of a registration probability estimation method according to some embodiments of the present application, which is applied to a platform of a network appointment for determining a probability that an unregistered service requester performs a registration operation under the effect of each service resource information. Specifically, the registration probability estimation method comprises the following steps:

s310, acquiring feature data corresponding to the unregistered service request end, and acquiring information acquisition modes of each service resource information by the unregistered service request end.

Here, since the network appointment platform cannot acquire much data information of the unregistered server request end, in order to acquire more data information related to the unregistered server request end to improve accuracy of the estimated probability, the feature data corresponding to the unregistered server request end acquired in this step includes not only the data information of the unregistered server request end but also the data information of the registered server request end that has interacted with the unregistered server request end, for example, has red envelope interaction.

Here, the feature data includes an information acquisition method in which the corresponding service requester acquires information of each service resource, an identifier of the corresponding service requester, and the like.

Here, the information obtaining manner for obtaining the information of each service resource by the unregistered service requester may include at least one of the following: passively receiving service resource information; and actively acquiring service resource information. The service resource information herein may include at least one of: a red packet with a certain amount of money, a coupon with a certain discount, a red packet with a certain amount of money pushed for a certain period of time, a coupon with a certain discount pushed for a certain period of time.

S320, determining the probability of executing the registration operation of the unregistered service request terminal under the action of each service resource information based on the acquired feature data and the acquired information acquisition mode corresponding to the unregistered service request terminal.

Here, the probability of performing the registration operation by the unregistered service requester under the action of each service resource information may be determined by using a correspondence between the pre-established feature data and information acquisition manner corresponding to each service requester when the service requester is unregistered and the probability of performing the registration operation by each service requester under the action of each service resource information. Specifically, the following steps can be utilized to determine the probability that the unregistered service requester performs the registration operation under the action of each service resource information:

s3201, obtaining historical sample data, and corresponding relation between the historical sample data and the probability of each service request end in the historical sample data executing the registration operation under the action of each service resource information; the historical sample data comprises characteristic data and an information acquisition mode corresponding to each service request end in the plurality of service request ends when the service request ends are not registered.

S3202, determining, based on the obtained corresponding relationship and the feature data and information obtaining manner corresponding to the unregistered service request terminal, a probability that the unregistered service request terminal performs a registration operation under the action of each service resource information.

In some embodiments, as shown in fig. 4, the feature data corresponding to the unregistered service request terminal may be obtained specifically through the following steps:

s410, acquiring at least one registered service request end related to the unregistered service request end.

Here, the service requester associated with the unregistered service requester may be a service requester having interacted with the unregistered service requester. The association relationship can be obtained by the network car booking platform based on the red packet receiving condition among the service request terminals, or the network car booking platform based on the information intercommunication condition among the service request terminals. The embodiment of the present application does not limit the specific manner of obtaining the association relationship.

Here, in order to obtain more feature data, it is necessary to obtain registered service requesters associated with unregistered service requesters as many as possible.

S420, determining feature data corresponding to the unregistered service request terminal based on the obtained feature data corresponding to the at least one registered service request terminal.

The different degrees of association between the service request ends associated with the unregistered service request ends and the unregistered service request ends are different, so that not all the feature data of the service request ends associated with the unregistered service request ends are taken as the feature data of the unregistered service request ends, but part of the feature data of the service request ends associated with the unregistered service request ends is obtained according to the degrees of association of the two, or the weight of the feature data of the service request ends associated with the unregistered service request ends is determined according to the degrees of association of the two, and then the weighted service feature data is calculated based on the obtained weight. Specifically, the feature data corresponding to the unregistered service request terminal may be determined by the following steps:

s4201, obtaining a correlation coefficient between each registered service request end and the unregistered service request end.

The association coefficient here characterizes the degree of association of registered service requesters with unregistered service requesters. The correlation coefficient may be determined according to the interaction frequency of the registered service requester and the unregistered service requester.

S4202, determining first feature sub-data corresponding to the unregistered service request end based on each obtained association coefficient and feature data corresponding to the registered service request end corresponding to each association coefficient.

Here, based on the correlation coefficient, partial feature data of the service requester associated with the unregistered service requester is acquired, or the weight of the feature data of the service requester associated with the unregistered service requester is determined, and weighted feature data is obtained. The partial feature data or/and the weighted feature data are the first feature sub data.

According to the relation between the service request terminals, the characteristic data of the unregistered service request terminal is reversely deduced through the characteristic data of the registered service request terminal, for example, the service request terminal A and the service request terminal B have interaction, A is the registered service request terminal, and B is the unregistered service request terminal. The various feature data of the registered service requester A can be used to predict the feature data of the unregistered service requester B. Here, it should be emphasized that the various feature data using the registered service request terminal a includes only the feature data that the network appointment platform can acquire before it is registered.

S4203, obtaining the feature data of the unregistered service request end to obtain second feature sub data corresponding to the unregistered service request end.

Here, the second feature sub-data is feature data directly obtained from an unregistered service requester.

S4204, merging the first feature sub-data and the second feature sub-data to obtain feature data corresponding to the unregistered service request end.

It should be noted that the feature data corresponding to the unregistered service request peer may further include feature data corresponding to an unregistered server request peer associated with the unregistered service request peer.

In some embodiments, as shown in fig. 5, the registration probability estimation method may further include a step of establishing a corresponding relationship between feature data and an information obtaining manner corresponding to each service request end in the plurality of service request ends when the service request end is unregistered and a probability that each service request end performs a registration operation under the action of each service resource information:

and S510, acquiring registration result data of each service request terminal in the history sample data under the action of each service resource information.

The historical sample data can select the data within the latest preset time length so as to ensure that the corresponding relation obtained by training can be well adapted to the current registration trend.

S520, determining the probability of executing the registration operation of each service request end in the history sample data under the action of each service resource information based on the acquired registration result data.

S530, establishing the corresponding relation between the probability of each service request end in the historical sample data executing the registration operation under the action of each service resource information and the characteristic data and the information acquisition mode of the corresponding service request end. The historical sample data comprises characteristic data and an information acquisition mode corresponding to each service request terminal in a plurality of service request terminals when the service request terminal is not registered.

The established corresponding relation is historical sample data and the corresponding relation of the probability of executing the registration operation of each service request end in the historical sample data under the action of each service resource information.

It should be noted that, if the historical sample data is data in a predetermined area range, the established corresponding relationship is the corresponding relationship in the predetermined area range. The corresponding relation can be used for estimating the probability of executing the registration operation of the unregistered service request terminal in the preset area range under the action of each service resource information.

The predetermined area may be a city, a province, or areas with similar consumption ability and habit. Since the consumption abilities and consumption habits of different regions are different, it is necessary to individually train the corresponding relationships for some regions having similar consumption abilities and consumption habits. The corresponding relation obtained by training can accurately estimate the registration probability in the corresponding area, and the estimation of the registration probability in other areas may have deviation.

In some embodiments, the registration probability estimation method further includes the following steps: and determining the corresponding unit registration conversion rate of the unregistered service request terminal under the action of each service resource information based on each service resource information and the probability of executing registration operation of the unregistered service request terminal under the action of each service resource information.

In particular implementation, the unit registered conversion rate may be determined using the following formula:

g＝(Pn-P)/Fn

wherein g represents the unit registration conversion; pn represents the probability of executing the registration operation by the unregistered service requester under the action of the nth service resource information, Fn represents the nth service resource information, and P represents the probability of executing the registration operation by the unregistered service requester under the action of no service resource information; wherein n is a positive integer.

The unit registration conversion rate refers to the increased registration probability of the unregistered service request terminal under the action of the unit service resource. In specific implementation, the above formula can be further modified as follows:

g＝(Pn-P)×LTV/Fn

where LTV represents the long-term customer value of an unregistered service requester.

The long-term customer value comprises the consumption capacity of the service request terminal for using the network appointment. Since the data information of the unregistered service request terminal obtained by the network appointment platform is limited, the long-term customer value of the unregistered service request terminal can be determined by using the data information of the registered service request terminal associated with the unregistered service request terminal. In particular implementations, the long-term customer value of the online appointment used by the unregistered service requester is determined based on the registered service requester associated with the unregistered service requester using the long-term customer value of the online appointment.

Of course, when determining the long-term customer value of the network appointment used by the unregistered service requester, the determination may also be based on the association coefficient of the unregistered service requester with the registered service requester associated therewith. In particular implementation, the long-term customer value of using the online appointment by the unregistered service request terminal can be determined by the following formula:

T＝T1×a1+T2×a2+…+Tn×am

in the formula, T represents the long-term customer value of using the network appointment by the unregistered service request terminal; t1 represents the long term customer value of the first registered service requestor associated with the unregistered service requestor using the network appointment; a1 represents the association coefficient between the unregistered service requester and the first registered service requester associated therewith; t2 represents the long term customer value of a second registered service requestor associated with an unregistered service requestor using a net appointment; a2 represents the association coefficient between the unregistered service requester and the second registered service requester associated therewith; tm represents the long-term customer value of the mth registered service requester associated with the unregistered service requester using the network appointment; am represents the correlation coefficient between the unregistered service requester and the mth registered service requester associated therewith.

The above-mentioned correlation coefficient is a value smaller than 1, and the sum of the correlation coefficients of all the registered service requesters correlated with the unregistered service requester is 1.

In some embodiments, as shown in fig. 6, in the case that the probability of performing the registration operation by the unregistered service requester under each service resource information is determined, and the corresponding unit registration conversion rate by the unregistered service requester under each service resource information is determined, the service resource information may be pushed to the unregistered service requester by using the following steps:

s610, based on the corresponding unit registration conversion rate of the unregistered service request terminal under the action of each service resource information and the probability of executing registration operation of the unregistered service request terminal under the action of each service resource information, selecting target service resource information from each service resource information.

The target service resource information herein refers to service resource information that can achieve a high unit registration conversion rate and a high probability of performing a registration operation.

Of course, the target service resource information may be service resource information that can obtain the highest unit registration conversion rate.

S620, pushing the selected target service resource information to an unregistered service request end.

Fig. 7 is a flowchart illustrating a probability pre-estimation model building method according to some embodiments of the present application, where the model built by the method is a corresponding relationship between feature data and an information obtaining manner corresponding to each service request side when each service request side is unregistered, and a probability that each service request side performs a registration operation under the action of each service resource information. Specifically, the probability estimation model construction method comprises the following steps:

s710, acquiring corresponding characteristic data of a plurality of service request terminals when the service request terminals are not registered, and acquiring information of each service resource information by each service request terminal.

S720, obtaining the registration result data of each service request end under the action of each service resource information.

And S730, determining the probability of executing the registration operation of each service request terminal under the action of each service resource information based on the acquired registration result data.

And S740, establishing a corresponding relation between the probability of each service request end executing the registration operation under the action of each service resource information and the characteristic data and the information acquisition mode of the corresponding service request end.

In specific implementation, the XGboost can be used for constructing a probability estimation model.

It should be noted that the probability pre-estimation model is constructed based on the feature data, the information acquisition mode and the registration result data of a plurality of service request terminals located in the predetermined area range. And for areas with different consumption levels and consumption habits, corresponding probability prediction models can be constructed by using the method.

Fig. 8 is a block diagram illustrating a registration probability estimation apparatus according to some embodiments of the present application, which implements functions corresponding to the steps performed by the registration probability estimation method. The device 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, as shown in the figure, the registration probability prediction device may include an information obtaining module 810 and a probability prediction module 820.

The information obtaining module 810 may be configured to obtain feature data corresponding to the unregistered service request end, and an information obtaining manner in which the unregistered service request end obtains each service resource information.

The probability prediction module 820 may be configured to determine, based on the obtained feature data and the obtained information obtaining manner corresponding to the unregistered service request end, a probability that the unregistered service request end performs a registration operation under the action of each service resource information.

In some embodiments, the information acquisition module 810 comprises:

the associated user determining submodule 8101 is configured to obtain at least one registered service request terminal associated with an unregistered service request terminal.

The feature data obtaining sub-module 8102 is configured to determine, based on the obtained feature data corresponding to the at least one registered service request end, the feature data corresponding to the unregistered service request end.

In some embodiments, the feature data acquisition sub-module 8102 is specifically configured to:

In some embodiments, the probability prediction module 820 comprises:

the corresponding relation obtaining submodule 8201 is used for obtaining the corresponding relation between historical sample data and the probability of executing the registration operation of each service request end in the historical sample data under the action of each service resource information; the historical sample data comprises characteristic data and an information acquisition mode corresponding to a plurality of service request terminals when the service request terminals are not registered;

and a probability prediction sub-module 8202, configured to determine, based on the obtained correspondence, and the feature data and information obtaining manner corresponding to the unregistered service request, a probability that the unregistered service request performs a registration operation under the action of each service resource information.

In some embodiments, the registration probability estimating means further comprises:

a historical data obtaining module 830, configured to obtain registration result data of each service request end in the historical sample data under the action of each service resource information;

a probability determining module 840, configured to determine, based on the obtained registration result data, a probability that each service request in history sample data performs a registration operation under the action of each service resource information;

the corresponding relation determining module 850 is configured to establish a corresponding relation between the probability that each service request terminal in the history sample data performs the registration operation under the action of each service resource information and the feature data and the information obtaining manner of the corresponding service request terminal.

In some embodiments, the historical sample data is data within a predetermined area; the unregistered service request terminal is located in the predetermined area range.

and a conversion rate determining module 860, configured to determine, based on each service resource information and a probability that the unregistered service requester performs the registration operation under each service resource information, a unit registration conversion rate corresponding to the unregistered service requester under each service resource information.

The conversion determination module 860 determines the unit registered conversion using the following equation:

g＝(Pn-P)/Fn

the service resource information selection module 870 is configured to select target service resource information from each service resource information based on a corresponding unit registration conversion rate of the unregistered service request terminal under the action of each service resource information and a probability of performing a registration operation of the unregistered service request terminal under the action of each service resource information;

a service resource information pushing module 880, configured to push the selected target service resource information to an unregistered service request end.

Fig. 9 is a block diagram illustrating a probability prediction model construction device according to some embodiments of the present application, where the functions implemented by the probability prediction model construction device correspond to the steps executed by the probability prediction model construction method. The device may be understood as the server or a 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, as shown in the figure, the probability estimation model building device may include a feature information obtaining module 910, a result data obtaining module 920, a probability obtaining module 930, and a model building module 940.

The characteristic information obtaining module 910 may be configured to obtain characteristic data corresponding to a plurality of service request terminals when the service request terminals are unregistered, and an information obtaining manner for each service request terminal to obtain information of each service resource.

The result data obtaining module 920 may be configured to obtain registration result data of each service request under the action of each service resource information.

The probability obtaining module 930 may be configured to determine, based on the obtained registration result data, a probability that each service requester performs a registration operation under the effect of each service resource information.

The model establishing module 940 may be configured to establish a correspondence between the probability that each service request end performs the registration operation under the action of each service resource information and the feature data and the information obtaining manner of the corresponding service request end.

The service request terminals are located in a predetermined area range.

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.

The embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program performs the steps of the registration probability estimation method in any of the above embodiments, or performs the steps of the probability estimation model building method in any of the above embodiments.

Embodiments of the present application further provide a computer program product, which includes a computer-readable storage medium storing a non-volatile program code executable by a processor, where instructions included in the program code may be used to execute the method described in the foregoing method embodiments, and specific implementation may refer to the method embodiments, and is not described herein again.

It should be noted that, the present application is directed to predicting the registration probability at the server request side, and the method is also applicable to the service provider side.

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 registration probability estimation method is characterized by comprising the following steps:

acquiring characteristic data corresponding to the unregistered service request terminal and an information acquisition mode for acquiring each service resource information by the unregistered service request terminal;

2. The method according to claim 1, wherein the obtaining feature data corresponding to the unregistered service request terminal comprises:

3. The method according to claim 2, wherein the determining the feature data corresponding to the unregistered service requester based on the obtained feature data corresponding to the at least one registered service requester comprises:

and combining the first characteristic subdata and the second characteristic subdata to obtain final characteristic data of the unregistered service request terminal.

4. The method according to claim 1, wherein the determining, based on the obtained feature data and the obtained information obtaining manner corresponding to the unregistered service requester, a probability that the unregistered service requester performs the registration operation under the action of each service resource information includes:

acquiring historical sample data, wherein the historical sample data corresponds to the probability of executing registration operation of each service request end in the historical sample data under the action of each service resource information; the historical sample data comprises characteristic data and an information acquisition mode corresponding to each service request end in the plurality of service request ends when the service request ends are not registered;

5. The method according to claim 4, further comprising a step of establishing a corresponding relationship between historical sample data and a probability that each service request terminal in the historical sample data performs the registration operation under the action of each service resource information:

6. The method according to claim 5, wherein the historical sample data is data within a predetermined area; the unregistered service request terminal is located in the predetermined area range.

7. The method of claim 1, further comprising:

and determining the corresponding unit registration conversion rate of the unregistered service request terminal under the action of each service resource information based on each service resource information and the probability of executing registration operation of the unregistered service request terminal under the action of each service resource information.

8. The method of claim 7, wherein the method determines the unit registered conversion using the formula:

g＝(Pn-P)/Fn

wherein g represents the unit registration conversion; pn represents the probability of the unregistered service requester performing the registration operation under the action of the nth service resource information, Fn represents the nth service resource information, and P represents the probability of the unregistered service requester performing the registration operation under the action of no service resource information; wherein n is a positive integer.

9. The method of claim 7, further comprising:

selecting target service resource information from each service resource information based on corresponding unit registration conversion rate of the unregistered service request terminal under the action of each service resource information and the probability of executing registration operation of the unregistered service request terminal under the action of each service resource information;

10. A probability prediction model construction method is characterized by comprising the following steps:

acquiring characteristic data corresponding to each service provider in a plurality of service request terminals when the service provider is unregistered, acquiring information acquisition modes of each service request terminal for acquiring each service resource information, and registering result data of each service request terminal under the action of each service resource information;

11. The method of claim 10, wherein the plurality of service requestors are located within a predetermined area.

12. A registration probability estimation apparatus, comprising:

13. The apparatus of claim 12, wherein the information obtaining module comprises:

14. The apparatus of claim 13, wherein the feature data acquisition sub-module is specifically configured to:

15. The apparatus of claim 12, wherein the probability prediction module comprises:

the corresponding relation acquisition submodule is used for acquiring the corresponding relation between the historical sample data and the probability of executing the registration operation of each service request end in the historical sample data under the action of each service resource information; the historical sample data comprises characteristic data and an information acquisition mode corresponding to each service request end in the plurality of service request ends when the service request ends are not registered;

16. The apparatus of claim 15, further comprising:

17. The apparatus according to claim 16, wherein the historical sample data is data within a predetermined area; the unregistered service request terminal is located in the predetermined area range.

18. The apparatus of claim 12, further comprising:

and the conversion rate determining module is used for determining the corresponding unit registration conversion rate of the unregistered service request terminal under the action of each service resource information based on each service resource information and the probability of executing registration operation of the unregistered service request terminal under the action of each service resource information.

19. The apparatus of claim 18 wherein the conversion determination module determines the unit registered conversion using the formula:

g＝(Pn-P)/Fn

20. The apparatus of claim 18, further comprising:

the service resource information selection module is used for selecting target service resource information from each service resource information based on the corresponding unit registration conversion rate of the unregistered service request terminal under the action of each service resource information and the probability of executing registration operation of the unregistered service request terminal under the action of each service resource information;

21. A probability estimation model construction device is characterized by comprising the following steps:

the system comprises a characteristic information acquisition module, a characteristic data acquisition module and a characteristic information acquisition module, wherein the characteristic information acquisition module is used for acquiring characteristic data corresponding to each service request terminal in a plurality of service request terminals when the service request terminals are not registered, and acquiring information acquisition modes of each service resource information by each service request terminal;

22. The apparatus of claim 21, wherein the plurality of service requestors are located within a predetermined area.

23. 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 running, the processor executing the machine-readable instructions to perform the steps of the probability estimation registration method according to any one of claims 1 to 9 or the probability estimation model construction method according to claim 10 or 11.

24. A computer-readable storage medium, having stored thereon a computer program for performing the steps of the method for probability estimation registration according to any one of claims 1 to 9 or the method for probability estimation model construction according to claim 10 or 11 when the computer program is executed by a processor.