CN111222729B

CN111222729B - Service type determination method and device, electronic equipment and storage medium

Info

Publication number: CN111222729B
Application number: CN201811410119.0A
Authority: CN
Inventors: 薛盛杰
Original assignee: Beijing Didi Infinity Technology and Development Co Ltd
Current assignee: Beijing Didi Infinity Technology and Development Co Ltd
Priority date: 2018-11-23
Filing date: 2018-11-23
Publication date: 2022-07-05
Anticipated expiration: 2038-11-23
Also published as: CN111222729A

Abstract

The application provides a service type determination method, a service type determination device, electronic equipment and a storage medium, and relates to the field of services. According to the service type determining method, in the process of determining the service type of the service provider, before the historical service information is input into the service type evaluation model, a certain amount of historical service information is used for screening the service provider once, and then the screened service provider is input into the service type evaluation model for screening.

Description

Service type determination method and device, electronic equipment and storage medium

Technical Field

The present application relates to the field of services, and in particular, to a service type determination method, apparatus, electronic device, and storage medium.

Background

In recent years, with the prosperity of internet technology, some emerging service industries based on internet technology, such as internet appointment car service, take-out service and the like, appear.

These emerging services offer great convenience to both service requesters and service providers. Taking a network car appointment as an example, a service requester can make an order before going out to reserve the travel time and the travel place in advance so as to avoid spending a large amount of time waiting for a taxi at the roadside when going out; the taxi service provider can select the service requester to be transported according to the destination expected by the service requester, and then both the service requester and the service provider can better arrange own travel.

Disclosure of Invention

The application aims to provide a service type determining method, a service type determining device, electronic equipment and a storage medium.

The application provides a service type determination method, which comprises the following steps:

acquiring historical service information of a plurality of service providers;

selecting a service provider meeting the screening requirements from a plurality of service providers according to the screening requirements respectively corresponding to at least one preset service information type and the historical service information of each service provider;

and inputting the selected historical service information of the service provider into a service type evaluation model trained in advance to obtain the service type of the service provider.

In some embodiments, selecting a service provider meeting a screening requirement from a plurality of service providers according to the screening requirement respectively corresponding to at least one preset service information category and historical service information of each service provider includes:

clustering order service places in each historical order information aiming at the historical order information of each service provider to determine a place clustering result corresponding to each historical order information;

and selecting the service providers meeting the screening requirements from the plurality of service providers according to the place clustering result corresponding to each piece of historical order information.

In some embodiments, selecting a service provider meeting the screening requirement from a plurality of service providers according to the location clustering result corresponding to each historical order information includes:

calculating a ratio of the first quantity to the second quantity; the first quantity is the quantity of order service places contained in the appointed place clustering result in the place clustering result corresponding to the appointed historical order information; the second quantity is the quantity of all order service places corresponding to the appointed historical order information;

and selecting the service provider meeting the screening requirement from the plurality of service providers according to the ratio of the first number to the second number.

clustering order service routes in each historical order information aiming at the historical order information of each service provider to determine route clustering results corresponding to each historical order information;

and selecting the service providers meeting the screening requirements from the plurality of service providers according to the route clustering result corresponding to each piece of historical order information.

and determining the service provider meeting the screening requirement according to the ratio of the number of the orders of the specified service type to the number of all the orders in each historical order information.

In some embodiments, the historical service information includes: the number of real-time orders allocated by the service provider after setting the real-time destination, and the number of all orders allocated by the service provider;

selecting a service provider meeting screening requirements from a plurality of service providers according to the screening requirements respectively corresponding to at least one preset service information type and the historical service information of each service provider, and the method comprises the following steps:

and determining the service provider meeting the screening requirement according to the ratio of the number of the real-time orders to the number of all orders in each historical order information.

In some embodiments, inputting the historical service information of the selected service provider into a pre-trained service type evaluation model to obtain the service type of the service provider includes:

inputting the historical service information of the selected service provider into a service type evaluation model trained in advance to determine the probability that the selected service provider meets the specified service type;

and determining the service type of the service provider according to the probability that the selected service provider meets the specified service type.

In some embodiments, determining the service type of the selected service provider based on the probability that the service provider meets the specified service type comprises:

ranking the probability that the plurality of selected service providers meet the specified service type;

the service type of each selected service provider is determined according to the rank order.

the service level at the specified service type is determined for each selected service provider according to the rank order.

In some embodiments, the method further comprises:

determining an order distribution strategy of each service provider in the selected service providers according to the corresponding relation between the service level and the order distribution strategy;

and distributing the service orders for each service provider in the selected service providers according to the determined order distribution strategy.

In some embodiments, the historical service information includes any one or more of:

service provider attribute information, service process information, and service requestor attribute information.

In some embodiments, the method further comprises:

determining an order distribution strategy of each service provider in the selected service providers according to the corresponding relation between the service types and the order distribution strategies;

and according to the determined order distribution strategy, distributing service orders for each service provider in the selected service providers.

The application provides a service type determination device, including:

the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring historical service information of a plurality of service providers;

the system comprises a first selection module, a second selection module and a third selection module, wherein the first selection module is used for selecting a service provider meeting the screening requirements from a plurality of service providers according to the screening requirements respectively corresponding to at least one preset service information type and the historical service information of each service provider;

and the first input module is used for inputting the selected historical service information of the service provider into a service type evaluation model trained in advance to obtain the service type of the service provider.

In some embodiments, the first selection module comprises:

the first clustering unit is used for clustering order service places in each piece of historical order information respectively according to the historical order information of each service provider so as to determine a place clustering result corresponding to each piece of historical order information;

and the first selection unit is used for selecting the service providers meeting the screening requirements from the plurality of service providers according to the place clustering result corresponding to each piece of historical order information.

In some embodiments, the first selection unit includes:

a first sub-calculation unit for calculating a ratio of the first number and the second number; the first quantity is the quantity of order service places contained in the appointed place clustering result in the place clustering result corresponding to the appointed historical order information; the second quantity is the quantity of all order service places corresponding to the appointed historical order information;

and the first sub-selection unit is used for selecting the service providers meeting the screening requirement from the plurality of service providers according to the ratio of the first number to the second number.

In some embodiments, the first selection module comprises:

the second clustering unit is used for clustering the order service routes in each piece of historical order information according to the historical order information of each service provider so as to determine route clustering results corresponding to each piece of historical order information;

and the second selection unit is used for selecting the service providers meeting the screening requirements from the plurality of service providers according to the route clustering result corresponding to each piece of historical order information.

In some embodiments, the first selection module comprises:

and the first determining unit is used for determining the service provider meeting the screening requirement according to the ratio of the number of the orders of the specified service type to the number of all the orders in each historical order information.

a first selection module comprising:

and the second determining unit is used for determining the service provider meeting the screening requirement according to the ratio of the number of the real-time orders to the number of all orders in each historical order information.

In some embodiments, a first input module, comprising:

a third determining unit, configured to input historical service information of the selected service provider into a service type evaluation model trained in advance, so as to determine a probability that the selected service provider meets a specified service type;

and the fourth determining unit is used for determining the service type of the service provider according to the probability that the selected service provider meets the specified service type.

In some embodiments, the fourth determination unit comprises:

a first ranking subunit, configured to rank probabilities that a plurality of selected service providers meet a specified service type;

and the first determining subunit is used for determining the service type of each selected service provider according to the front-back order of the ranking.

In some embodiments, the fourth determination unit comprises:

a second ranking subunit, configured to rank probabilities that the plurality of selected service providers meet the specified service type;

and the second determining subunit is used for determining the service level of each selected service provider in the specified service type according to the front-back order of the ranking.

In some embodiments, the apparatus further comprises:

the first determining module is used for determining the order distribution strategy of each service provider in the selected service providers according to the corresponding relation between the service level and the order distribution strategy;

and the first distribution module is used for distributing the service orders to each service provider in the selected service providers according to the determined order distribution strategy.

In some embodiments, the apparatus further comprises:

the second determining module is used for determining the order distribution strategy of each service provider in the selected service providers according to the corresponding relation between the service types and the order distribution strategies;

and the second distribution module is used for distributing service orders to each service provider in the selected service providers according to the determined order distribution strategy.

The application provides an electronic equipment, includes: 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 steps such as service type determination.

A computer-readable storage medium is provided having a computer program stored thereon, which when executed by a processor performs steps such as service type determination.

According to the service type determining method provided by the embodiment of the application, after historical service information of a plurality of service providers is obtained, firstly, according to screening requirements respectively corresponding to at least one preset service information type and the historical service information of each service provider, a service provider meeting the screening requirements is selected from the plurality of service providers, and then, the selected historical service information of the service provider is input into a service type evaluation model trained in advance to obtain the service type of the service provider. That is, in the process of determining the service type of the service provider, before the historical service information is input into the service type evaluation model, a certain amount of historical service information is used to screen the service provider once, and then the screened service provider is input into the service type evaluation model to be screened.

In a certain embodiment, when a service provider meeting the screening requirement is selected from a plurality of service providers, a mode of clustering order service places and screening the service providers according to a place clustering result is adopted, so that the accuracy of screening the service providers is improved.

In a certain embodiment, when a service provider meeting the screening requirement is selected from a plurality of service providers, a mode of clustering order service routes and screening the service providers according to route clustering results is adopted, so that the accuracy of screening the service providers is improved.

In a certain embodiment, when a service provider meeting the screening requirement is selected from a plurality of service providers, the service provider is screened according to the ratio of the number of real-time orders to the number of all orders, so that the accuracy of screening the service provider is improved.

In a certain embodiment, historical service information of service providers is input into a model to determine service types of the service providers, a mode that a plurality of selected service providers are ranked according to the probability that the selected service providers meet the specified service types, service levels are divided for the service providers according to the ranking sequence, and corresponding order distribution strategies are set for the service providers with different service levels is adopted, so that the accuracy and pertinence of the order distribution strategies set for the service providers are improved.

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 basic flow chart of a service type determination method provided by an embodiment of the present invention;

FIG. 2 is a schematic diagram showing location clustering results for clustering order service locations for a given one of the service providers;

FIG. 3 illustrates a detailed flow diagram of a method for determining a type of service provided by an embodiment of the present invention;

FIG. 4 shows a schematic diagram of an electronic device provided by an embodiment of the application;

fig. 5 illustrates a block diagram of a service system in which a service type determination method of some embodiments of the present application is located.

Detailed Description

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 is obvious that 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.

In the related art, with the rise of internet technology, some emerging service industries based on the internet technology, such as internet appointment car service, take-out service, and the like, appear.

Taking the car-booking service as an example, when a service requester enjoys the car-booking service, the service requester (such as a user) firstly places a service order to a service platform (server), then the service platform broadcasts the service order to some service providers (such as drivers), the service providers can choose to reply the broadcast or ignore the broadcast after receiving the broadcast, and then the service platform can determine to which service provider the service order is distributed according to the condition of the service provider replying the broadcast. Furthermore, after the service platform distributes the service order to the specified service provider, the service provider distributed with the service order can deliver the service requester according to the requirement in the service order, and further the network car booking service is completed.

Generally, the service types included in any service are various, such as express service, special car service, taxi service, and the like. For another example, the express service may be divided into a general express, an express delivery, and an express delivery according to different delivery speeds.

Corresponding to these service types, service providers providing services may be classified into different types, for example, in a web-booking service, the types of service providers may be classified into fast drivers, special drivers, short-range drivers, long-range drivers, and the like. In some cases, the preferences of different driver types are different, e.g., a specialized driver prefers to take a specialized type of service order; close drivers prefer to take service orders with closer pick-up and drop-off locations (such service orders can typically be completed faster); remote drivers are more likely to take service orders that are located further from the boarding and disembarking locations (such service orders typically take longer to complete, but get more returns per completed service order).

As described above, the server, upon receiving the service order, broadcasts the service order to certain service providers to complete the distribution of the service order. When broadcasting a service order to some service providers, the server generally broadcasts the service order in batches, that is, each broadcast is broadcast to only one part of drivers, and then broadcasts the service order to other drivers if the part of drivers are not willing to take the service order. Furthermore, the batch broadcasting method can control the number of drivers in the broadcasting, but a certain service order is broadcasted many times and then accepted by the service provider.

In view of the above situation, the applicant of the present application believes that, when a service order is allocated, the accuracy of allocating the service order can be improved by determining the type of the service provider and the type of the service order accurately in advance, and then determining which service providers to broadcast the service order preferentially according to the corresponding relationship between the type of the service provider and the type of the service order.

In order to know the service type of each service provider in advance, in the related art, the server usually prompts the service provider to select its type in the service providers when the service providers are registered, but this way of determining the service provider type is not accurate enough. Further, the present inventors have considered that classification can be performed by means of a mathematical model, but if all parameters are input to the model at once, the model may be operated too slowly due to the excessive number of parameters that may be used, and further, the present application provides a service type determination method, as shown in fig. 1, including:

s101, acquiring historical service information of a plurality of service providers;

s102, selecting service providers meeting screening requirements from a plurality of service providers according to screening requirements respectively corresponding to at least one preset service information type and historical service information of each service provider;

and S103, inputting the selected historical service information of the service provider into a service type evaluation model trained in advance to obtain the service type of the service provider.

The historical service information refers to information on a service that a service provider has provided. The historical service information may differentiate different service providers to some extent. Specifically, the historical service information may be divided into a plurality of categories according to the difference of the description contents, for example, the following categories:

The service provider attribute information may be information describing a personal condition of the service provider, for example, the provider attribute information may include any one or more of the following: age, gender, occupation, working age (e.g., length of time to drive) in an industry, average monthly revenue by taking service orders for a specified service type, total historical revenue by taking service orders for a specified service type, average hourly revenue by taking service orders for a specified service type, etc. of a service provider;

the service procedure information is information used to describe the service order during execution. For example, the service procedure information may include any one or more of: the number of service orders of a certain service type to be accepted, the number of all accepted service orders, a boarding location, a disembarking location, a ratio of the number of service orders of a certain service type to the number of service orders of all service types, a time length consumed for completing the service orders, a cost (such as gasoline consumption) consumed for completing the service orders, a distance traveled by completing the service orders, a return received by completing the service orders, an amount paid by a service provider after completing the service orders, a navigation route (a route from the boarding location to the disembarking location) corresponding to each service order, a violation (such as a violation of a traffic rule) occurring in the process of completing the service orders, a mobile terminal of the service provider, and the like.

The service requester attribute information may be information describing a personal condition of the service requester, for example, the service requester attribute information may include any one or more of the following: age, gender, occupation, working years engaged in a certain industry, etc. of the service requester.

By means of this information, the historical service situation of the service provider can be reflected from different perspectives.

In S101, the historical service information may be from various sources, for example, the historical service information may be uploaded actively by the service provider, or may be uploaded actively by the service requester. In general, the service provider attribute information, the service process information and the service requester attribute information are stored in the system along with the service order, so that when the system needs to read the three kinds of information, in most cases, only the data need to be directly called from the database of the system.

The main purpose of S102 is to filter out using one or more types of historical service information to select a suitable service provider. As explained in the foregoing, there are many kinds of history service information, which describe the history service condition of the service provider from different angles, but the filtering time is too long if such information is considered at the same time, and the filtering meaning is not great. Therefore, after the meeting of step S102 is performed, some kinds of history service information are selected for filtering.

In the specific screening, the screening requirements that can be respectively corresponding to each service information category should be differentiated. For example, the screening requirement corresponding to the working life of a certain industry should be a screening requirement in units of time (for example, the screening requirement is to select a service provider with a working life of more than 3 years); the filtering requirement for the average monthly revenue by taking over service orders of the specified service type should be a filtering requirement in units of monetary amount (e.g., filtering requires more than 1 million service providers for the average monthly revenue by choosing to take over service orders of the specified service type).

Furthermore, after the screening requirement corresponding to each service information type is determined, whether the service provider meets the pre-screening requirement can be determined according to whether the historical service information meets the screening requirement.

In addition to setting corresponding screening requirements for each type of historical service information, joint screening requirements can also be set for various types of historical service information, for example, during screening, if various types of historical service information occur at the same time, the joint screening requirements can be used, so that even if a certain historical service information does not meet the corresponding screening requirements, but various types of historical service information meet the joint screening requirements, the service requester can be considered to meet the preset screening requirements.

That is, in the scheme provided by the present application, the screening requirements may be divided into two types, the first type is an independent screening requirement (the independent screening requirement is only used to determine whether a certain historical service information meets the independent screening requirement, and if so, it is determined that the service provider meets the screening requirement), and the second type is a joint screening requirement (the joint screening requirement is only used to simultaneously determine whether multiple types of historical service information all meet the screening requirement, and if so, it is determined that the service provider meets the screening requirement).

Furthermore, in the method provided by the present application, step S102 can be implemented in the following first manner:

judging whether each type of historical service information of the service providers meets the corresponding independent screening requirement or not aiming at each service provider in the multiple service providers;

if each type of historical service information meets the corresponding independent screening requirement, the service provider is determined to be the service provider meeting the screening requirement;

and if the at least one type of historical service information does not meet the corresponding screening requirement, determining that the service provider is a service provider which does not meet the screening requirement.

Step S102 can also be implemented in the second manner as follows:

judging whether the associated multiple kinds of historical service information in the multiple kinds of historical service information of the service providers meet the corresponding joint screening requirements or not aiming at each service provider in the multiple kinds of service providers;

and if the associated various historical service information in the various historical service information of the service provider meets the corresponding joint screening requirement, determining that the service provider is the service provider meeting the screening requirement.

Compared with the second implementation manner, the main difference of the first implementation manner of the step S102 is that, in the first implementation manner, for a specified service provider, it is determined that the specified service provider meets the screening requirement only if it needs to judge whether the historical service information meeting the screening requirement meets the independent screening requirement; in the second implementation manner, the specified service provider can be considered to meet the screening requirement as long as it is determined that, of all the historical service information, a plurality of associated historical service information meet the corresponding joint screening requirement (no matter whether other historical service information meets the screening requirement or not). The specific associated historical service information meeting the corresponding joint screening requirement can be determined according to specific situations.

The screening is performed once through step S102, so that the number of service providers that need to be identified through step S103 is reduced, and the difficulty in executing S103 is reduced.

Further, in step S103, the historical service information of the service provider selected in step S102 may be input into the trained service type evaluation model to determine the service type of the service provider.

According to the method provided by the application, since the screening action is performed once in the step S102, the number of service providers which need to identify the service type through the step S103 is greatly reduced, and the execution efficiency of the step S103 is ensured. It should be noted that, when step S103 is actually executed, in order to ensure the accuracy of determining the service type, a large amount of data (historical service information) is generally input into the model for calculation, and the amount of data that may be input into the model is hundreds of thousands, so the amount of calculation in step S103 is very large. By pre-screening a part of the service providers which do not meet the requirements in step S102, the overall processing difficulty of step S103 is reduced, and the overall calculation efficiency is improved.

Specifically, in the step S102, the data to be filtered should not be too much, and if the data is too much, the calculation amount is reduced; meanwhile, the data to be filtered should not be too small, and if the data to be filtered is too small, the data cannot be used for filtering, and the filtered historical service information should have a certain pertinence, that is, the filtered historical service information should be capable of distinguishing different service providers.

Further, the inventors of the present application, through experiments and analyses, have considered that it is appropriate to select several types of historical service information as follows:

order service location, order service route, and order quantity. That is, in the method provided by the present application, the screening may be performed simultaneously according to at least one of the three information (order service location, order service route, and order quantity) to select the service provider meeting the screening requirement.

The screening process using these three pieces of information is explained below:

when the order service location is used for filtering, as shown in fig. 3, step S102 can be implemented as follows:

s1021, clustering order service places in each historical order information aiming at the historical order information of each service provider to determine a place clustering result corresponding to each historical order information;

and S1022, selecting a service provider meeting the screening requirement from the multiple service providers according to the place clustering result corresponding to each piece of historical order information.

In step S1021, there are two types of order service locations, namely, a boarding location and a alighting location. The boarding point here refers to a point where the service provider picks up the service requester, and the alighting point here refers to a destination to which the service provider delivers the service requester.

When the step S102 is implemented specifically, the methods of the steps S1021 and S1022 may be used only for the boarding point, or the methods of the steps S1021 and S1022 may be used only for the alighting point; the method may use both the boarding point and the alighting point in step S1021 and step S1022.

After determining the location clustering result, there are two ways to determine the service provider meeting the screening requirement, which are respectively described below:

the first way to determine the service provider that meets the screening requirements:

as shown in fig. 2, a schematic diagram of a location clustering result for clustering order service locations of a specified one of the service providers is shown. In fig. 2, black dots indicate places (getting-on or getting-off places), and circles surrounding the places indicate results of clustering, and places enclosed in each circle are clustered. Further, it can be seen that the places in fig. 2 can be grouped into three categories, which are clustering result 1, clustering result 2, and clustering result 3, respectively. Wherein, there are two places in the clustering result 1, there are four places in the clustering result 2, and there are two places in the clustering result 1. That is, S1022, may be implemented as follows: and taking the service providers with the number of the place clustering results less than a preset value as the service providers meeting the screening requirement. For example, a service provider with 5 fewer location clustering results can be used as a service provider meeting the screening requirement. In this case, the number of the clustering results shown in fig. 2 is only 3, and the service provider corresponding to fig. 2 can be used as the service provider meeting the screening requirement.

By clustering the order service locations, the behavior rules of the service provider can be obtained. For example, if the clustering result of the places is less (for example, the clustering result is only 2-4), the more the behavior of the service provider is very regular, the service provider belongs to the service provider which can accurately predict the behavior, or the service orders taken by the service provider have accurate directionality. Such service providers may be attributed to service providers that prefer to take on-route service requestors (i.e., take on-route service orders during work or work). Further, the method provided in the present application may be considered to be a method used for the purpose of searching for such a service provider.

A second way to determine the service providers that meet the screening requirements:

besides that the fewer the clustering results of the places, the more the service provider has the service requirement, the more the clustering results of the places have the centralized number of the places, and the more the driver has regular behavior. For example, there are 8 clustering results, and the 8 clustering results cluster 100 locations together, where one clustering result includes 40 locations, another clustering result includes 50 locations, and the other 10 locations are in the remaining 9 clustering results, respectively. This can also indicate that the service provider is behaving very regularly. That is, it may be considered that such service providers may be service providers that meet the screening requirements. Further, the method provided in the present application may be considered to be a method used for the purpose of searching for such a service provider.

I.e., S1022, may be implemented as follows: and selecting the service providers meeting the screening requirements according to the number of the order service places contained in the appointed place clustering result in the place clustering result.

Here, a specified location clustering result generally refers to one or more clustering results that contain the most order service locations.

Here, it may be determined whether the number of order service locations included in the specified location clustering result exceeds a predetermined value, and if so, the service provider may be considered as a service provider meeting the screening requirement.

In order to more accurately judge whether the service provider is the service provider meeting the screening requirement, a judgment mode of introducing a ratio can be adopted.

Specifically, step 1022 may be implemented as follows:

step 10221, calculating a ratio of the first quantity to the second quantity; the first quantity is the quantity of order service places contained in the appointed place clustering result in the place clustering result corresponding to the appointed historical order information; the second quantity is the quantity of all order service places corresponding to the appointed historical order information;

at step 10222, a service provider meeting the screening requirement is selected from the plurality of service providers according to the ratio of the first number to the second number.

In step 10221, the designated location clustering result generally refers to one or more clustering results that include the most order service locations. That is, if the order service places included in a certain clustering result are very many (for example, the ratio of the order service places included in the clustering result to the total order service places reaches 80%), it indicates that the behavior of the service provider is very regular, and further, the service provider can be used as a service provider meeting the screening requirement.

When the order service route is used for filtering, step S102 may be implemented as follows:

s1023, clustering order service routes in each historical order information aiming at the historical order information of each service provider to determine route clustering results corresponding to each historical order information;

and S1024, selecting a service provider meeting the screening requirement from the multiple service providers according to the route clustering result corresponding to each piece of historical order information.

Here, the order service route may be recorded directly with the service order (directly using the actual route of the service provider carrying the service requester as the order service route), or may be restored according to the getting-on point and the getting-off point (but this may not be accurate).

After determining the route clustering result, there are two ways to determine the service provider that meets the screening requirement, which are respectively described below:

s1024, it can be implemented as follows: and taking the service providers with the route clustering results less than a preset value as the service providers meeting the screening requirement. For example, a service provider with 3 fewer route clustering results can be used as a service provider meeting the screening requirement.

By clustering the order service routes, the behavior rules of the service provider can be obtained. For example, if the clustering result of the places is less (for example, the clustering result is only 2-4), the more the behavior of the service provider is very regular, the service provider belongs to the service provider which can accurately predict the behavior, or the service orders taken by the service provider have accurate directionality. Such service providers may be attributed to service providers that prefer to take on-route service requestors (i.e., take on-route service orders during work or work). Further, the method provided in the present application may be considered to be a method used for the purpose of searching for such a service provider.

besides that the fewer the clustering results of the places, the more the service provider will have the service requirement, the more the number of places in the clustering results of a certain route is concentrated, the more the driver's behavior is regular. For example, there are 5 clustering results, the 5 clustering results cluster 80 routes, one clustering result includes 35 locations, another clustering result includes 36 locations, and the other 9 locations are in the remaining 4 clustering results respectively. This can also indicate that the service provider is behaving very regularly. That is, it may be considered that such service providers may be service providers that meet the screening requirements. Further, the method provided in the present application may be considered to be a method used for the purpose of searching for such a service provider.

I.e., S1024, can be implemented as follows: and selecting the service providers meeting the screening requirements according to the number of the order service routes contained in the specified route clustering result in the route clustering result.

Here, the designated route clustering result generally refers to one or more clustering results that include the most order service routes.

Here, it may be determined whether the number of order service routes included in the specified route clustering result exceeds a predetermined value, and if so, the service provider is considered to be a service provider meeting the screening requirement.

In order to more accurately judge whether the service provider is the service provider meeting the screening requirement, a ratio judging mode can be introduced.

Specifically, step 1024 may be implemented as follows:

step 10241, calculating the ratio of the third quantity to the fourth quantity; the third quantity is the quantity of order service routes contained in the specified route clustering result in the route clustering result corresponding to the specified historical order information; the fourth quantity is the quantity of all order service routes corresponding to the specified historical order information;

and 10242, selecting the service provider meeting the screening requirement from the plurality of service providers according to the ratio of the third number to the fourth number.

In step 10241, the designated route clustering result generally refers to one or more clustering results that include the most order service routes. That is, if the order service routes included in a certain clustering result are very many (for example, the ratio of the order service routes included in the clustering result to the total order service routes reaches 80%), it indicates that the behavior of the service provider is very regular, and further, the service provider can be used as the service provider meeting the screening requirement.

When the order quantity is used for filtering, step S102 may be implemented as follows:

and taking the service provider with the order quantity exceeding a preset value as the service provider meeting the screening requirement.

This is simple, i.e. only enough service providers to fill a service order need to determine its service type.

In addition to the filtering by the order number, it may be determined whether the service provider is a service provider meeting the filtering requirement further according to the number of some specific types of orders in the order number.

For example, step S102 may be implemented as follows:

Here, the specified service type may be any one or more of types such as an express type, a special car type, and the like. By comparing the ratio of the number of orders for a given service type to the number of total orders, it can be determined which type of service order the service provider is more inclined to take over.

On the basis, the service type can be further refined to more accurately determine the washing of the service provider.

Specifically, step S102 may be implemented as follows:

Wherein the number of real-time orders is the number of service orders allocated by the service provider after setting the real-time destination; the quantity of all orders refers to the quantity of all types of service orders that the service provider has ever assigned (and may also be assigned and completed), or the quantity of all orders refers to the quantity of certain types of service orders that the service provider has ever assigned (and may also be assigned and completed), specified.

Here, the real-time order means a service order distributed after the service provider temporarily sets a destination. It should be noted here that real-time orders should be distinguished from reservation orders.

Here, a reservation order generally refers to a service order in which the time when the system allocates the service order is far from the time when the service provider performs a service according to the service order (e.g., the service time agreed by the service provider and the service requester). Such reservation orders are typically service orders placed hours in advance. Correspondingly, the real-time order is a service order with a smaller distance between the time of distributing the service order by the system and the time of performing service according to the service order by the service provider.

In general, the service orders (which may be different types of service orders such as express service orders and special service orders) allocated by the system are only real-time orders within a predetermined time after the real-time destination is set (after the real-time destination is set, it is stated that the service provider starts to take real-time orders).

That is, if the real-time orders accepted by the service provider are all orders that follow a certain rule, the service provider's travel is very regular.

In the above, the manner of selecting the service provider meeting the screening requirement by the order service location, the order service route, and the order number is described, and in a specific implementation, the service provider meeting the screening requirement may be selected from a plurality of service providers by considering at least one of the three cases.

Specifically, step S102 may be implemented as follows:

selecting a service provider from a plurality of service providers that meets the screening requirements according to any one or more of the following information:

order service location, order service route, and order quantity.

More specifically, step S102 may be implemented as follows:

and in the place clustering result corresponding to each historical order information, the route clustering result corresponding to each historical order information and each historical order information, the ratio of the number of orders of the specified service type to the number of all orders is large.

Specifically, the manner of calculating the ratio of the number of orders of the specified service type to the number of all orders in the location clustering result corresponding to each piece of historical order information, the route clustering result corresponding to each piece of historical order information, and each piece of historical order information has already been described in the foregoing, and the manner of selecting a service provider meeting the screening requirement according to the three pieces of information is also described in the foregoing, and is not repeated here.

In step S103, what is actually output by the service type evaluation model is a probability value, that is, what is output by the service type evaluation model is a probability that the service provider conforms to the specified service type, and the greater the probability is, the more the service provider should be marked/attributed with the service type.

In a specific implementation, step S103 may be implemented as follows:

step 1031, inputting the historical service information of the selected service provider into a service type evaluation model trained in advance to determine the probability that the selected service provider meets the specified service type;

step 1032, determining the service type of the selected service provider according to the probability that the service provider meets the specified service type.

In step 1031, the service type may be preset, and considering that the service provider may be once screened by the order service location, the order service route, and the order quantity in step S102 of the scheme itself, the method provided in this application is more desirable to determine the probability that the service provider is a service provider with certain regularity (such as frequently walking a certain route or frequently arriving at a certain location) in the trip.

The output of step 1031 is a probability value, such as 0.76 (which indicates that the probability that the service provider is of the specified service type is 76%).

Further, in step 1032, the service type of the service provider can be determined directly from the probability that the service provider is the specified service type. The service type is determined according to the probability in many ways, for example, if the probability exceeds 60%, it may be determined that the service requester is the specified service type, otherwise, it indicates that the service requester is not the specified service type.

In addition to this way of determining the service type of a service provider in an absolute way, the service type of a service provider can also be determined in a relative way. That is, step 1032 may be implemented as follows:

step 10321, ranking probabilities that the plurality of selected service providers meet the specified service type;

step 10322 determines the service type for each selected service provider based on the rank order.

In step 10321, each service provider is ranked according to its probability and the type of each service provider is determined in order of ranking.

As shown in table 1 below, the probabilistic ranking for each service provider is shown.

TABLE 1

Table 1 shows the probabilities and corresponding probability rankings for the respective service providers, and it can be seen from table 1 that the probabilities for service providers a and B are high, and the probabilities for service providers I and G are low. If the pre-established policy is that the service provider with probability rank top 5 is the XXX service type, then only the XXX of the service types of service providers A, B, Z, F and E; the service type of service providers I and G is not XXX.

After the service type of the service provider is determined, an order allocation policy can be determined for each service provider for the service type, and then, when a service order is allocated, the service order can be allocated according to the determined order allocation policy.

It is often the case that after the service type of a service provider is determined, a certain service order complying with that service type is allocated more to that service provider.

That is, when a service order is allocated to a service provider, it may be allocated according to the service type of the service provider.

That is, the method provided by the present application further includes:

The correspondence between the service type and the order allocation policy is predetermined, for example, the service provider of the service type a may allocate the service order of the service type a preferentially (this allocation formula may be considered as one of the order allocation policies).

In specific implementation, a table may be established in advance in the system to store the corresponding relationship between the service type and the order allocation policy, and the order allocation policy may be invoked according to the service type during specific execution.

More specifically, service providers of different levels can be determined according to the sequence of the probability ranking. For example, the pre-established policy is that service providers with a probability ranking of top 2 are service providers of the first level a service type, and service providers with a probability ranking of 3-4 are service providers of the second level a service type; service providers with a probabilistic ranking of 5-6 are the third level a service type. Then as in the case shown in table 1, it can be determined that service providers a and B are service providers of the first level a service type; service providers Z and F are service providers of the second level a service type; service providers E and I are service providers of the third tier a service type.

If the service level of each selected service provider at the specified service type is determined (e.g., service provider of the first class a service type, service provider of the second class a service type, and service provider of the third class a service type), then the assignment of the specified type of service order to the higher class service provider may be considered first, or the assignment of the service order may be determined according to the service provider's level (e.g., more service orders are assigned at higher levels), when implemented.

That is, the method provided by the present application further includes the following steps:

In fact, the service level is determined according to the rank order determined for the same service type, for example, if the service providers A, B, C are all service providers that prefer to receive an on-road order (a certain type of service order), but all the service orders received by the service provider a are on-road orders, and only half of the service orders received by the service provider B are on-road orders, the probability of the service provider a meeting on-road drivers is greater than that of the service provider B, that is, the level of the service provider a should be greater than that of the service provider a. Further, the server will typically allocate more of the on-road order to service provider a.

The order distribution policy determined according to the service level is generally a policy for adjusting the distribution ratio, distribution upper limit, and the like of the service orders of the specified type. The specific order allocation strategy can be determined according to specific situations, and is not limited too much in the application.

In the solution provided by the present application, the specific processing strategy is to select a service provider with a certain rule, so in response to the above specific solution, the applicant believes that the method provided by the present application can also be regarded as a service provider type determination method that mainly accepts an in-route service order.

Based on the method, the application also provides a method for training the service type evaluation model, and specifically, the service type evaluation model can be trained according to the following steps:

acquiring sample historical service information of a plurality of service providers; the historical service information comprises any one or more of the following information: service provider attribute information, service process information, and service requester attribute information;

and training to obtain a service type evaluation model based on the historical service information of the plurality of samples.

Here, the historical service information has already been described in the foregoing, and the description is not repeated here.

Specifically, the original service type evaluation model may select a common classifier, such as a logistic Regression (logistic Regression) model, a Support Vector Machine (Support Vector Machine) model, a Decision Tree (Decision Tree) model, and a Gradient Boosting Decision Tree (Gradient Boosting Decision Tree) model. In addition to this, deep machine learning (neural network) models may also be used as an option. If a neural network model is used, before data is input into the model, normalization processing needs to be performed on the data, and a proper initialization scheme is adopted to ensure that the model can be converged to a better state.

When the service type evaluation model is trained, a large number of training samples are prepared in advance, and each training sample comprises historical service information of one service provider and a corresponding service type (such as an a service type and not an a service type). Then, the training samples are input into the service type evaluation model to train the service type evaluation model.

When the training sample is determined, the historical service information of the service provider with the number of real-time orders taken each day being less than a preset value can be used as a positive sample, namely the service type of the service provider is the A service type; or determining which service provider's historical service information is used as a positive sample according to the position clustering result/route clustering result of a certain service requester.

As shown in fig. 5, a block diagram of a service system 100 in which the method for presenting prompt information according to some embodiments of the present application is located is shown. For example, the service system 100 may be an online transportation service platform for transportation services such as taxi cab, designated drive service, express, carpool, bus service, driver rental, or shift service, or any combination thereof. The service system 100 may include one or more of a server 110 (one of execution bodies of the methods provided herein), a network 120, a service requester terminal 130 (service requester), a service provider terminal 140 (service provider), and a database 150, and the server 110 may include a processor therein that performs 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 terminal 130, the service provider terminal 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 terminal 130, the service provider terminal 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 1000 having one or more of the components illustrated in FIG. 4 herein.

Network 120 may be used for the exchange of information and/or data. In some embodiments, one or more components in the service system 100 (e.g., the server 110, the service requester terminal 130, the service provider terminal 140, and the database 150) may send information and/or data to other components. For example, the server 110 may obtain a service request from the service requester terminal 130 via the network 120. In some embodiments, the network 120 may be any type of wired or wireless network, or combination thereof. Merely by way of example, Network 130 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 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 serving system 100 may connect to network 120 to exchange data and/or information.

In some embodiments, the service requester of the service requester terminal 130 may be a person other than the actual demander of the service. For example, the service requester a of the service requester terminal 130 may use the service requester terminal 130 to initiate a service request for the service actual demander B (for example, the service requester a may call a car for its friend B), or receive service information or instructions from the server 110. In some embodiments, the service requester of the service provider terminal 140 may be the actual provider of the service or may be another person than the actual provider of the service. For example, the service requester C of the service provider terminal 140 may use the service provider terminal 140 to receive a service request for services provided by the service provider entity D (e.g., the service requester C may order the service provider entity D employed by itself), and/or information or instructions from the server 110. In some embodiments, "service requester" and "service requester terminal" may be used interchangeably, and "service provider" and "service provider terminal" may be used interchangeably.

In some embodiments, the service requester terminal 130 may comprise 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 terminal 130 may be a device having a location technology for locating the location of the service requester and/or service requester terminal.

In some embodiments, the service provider terminal 140 may be a similar or identical device as the service requestor terminal 130. In some embodiments, the service provider terminal 140 may be a device with location technology for locating the location of the service provider and/or the service provider terminal. In some embodiments, the service requester terminal 130 and/or the service provider terminal 140 may communicate with other locating devices to determine the location of the service requester, service requester terminal 130, service provider, or service provider terminal 140, or any combination thereof. In some embodiments, the service requester terminal 130 and/or the service provider terminal 140 may transmit the location information to the server 110.

Database 150 may store data and/or instructions. In some embodiments, the database 150 may store data obtained from the service requester terminal 130 and/or the service provider terminal 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 (DDR SDRAM); 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.

Corresponding to the method, the application also provides a service type determining device, which comprises:

the system comprises a first selection module, a second selection module and a selection module, wherein the first selection module is used for selecting a service provider meeting the screening requirement from a plurality of service providers according to the screening requirement respectively corresponding to at least one preset service information type and the historical service information of each service provider;

In some embodiments, the first selection module comprises:

In some embodiments, the first selection unit includes:

a first sub-calculation unit for calculating a ratio of the first number and the second number; the first quantity is the quantity of order service places contained in the appointed place clustering result in the place clustering result corresponding to the appointed historical order information; the second quantity is the quantity of all order service places corresponding to the specified historical order information;

and the first sub-selection unit is used for selecting the service providers meeting the screening requirements from the plurality of service providers according to the ratio of the first number to the second number.

In some embodiments, the first selection module comprises:

a first selection module comprising:

In some embodiments, a first input module, comprising:

In some embodiments, the fourth determining unit comprises:

In some embodiments, the fourth determination unit comprises:

In some embodiments, the apparatus further comprises:

In correspondence with the above method, the present application also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method as service type determination.

As shown in fig. 4, a schematic view of an electronic device provided in an embodiment of the present application, the electronic device 1000 includes: a processor 1001, a memory 1002 and a bus 1003, wherein the memory 1002 stores execution instructions, when the electronic device runs, the processor 1001 and the memory 1002 communicate through the bus 1003, and the processor 1001 executes the steps of the service type determination method stored in the memory 1002.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

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 embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units 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 units through some communication interfaces, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units 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 may be stored in a computer-readable storage medium if they are implemented in the form of software functional units and sold or used as separate products. 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: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

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 determining a service type, comprising:

acquiring historical service information of a plurality of service providers;

selecting a service provider meeting the screening requirements from the plurality of service providers according to the screening requirements respectively corresponding to at least one preset service information type and the historical service information of each service provider;

inputting the selected historical service information of the service provider into a service type evaluation model trained in advance to obtain the service type of the service provider;

inputting the selected historical service information of the service provider into a service type evaluation model trained in advance to obtain the service type of the service provider, wherein the service type evaluation model comprises the following steps:

inputting the selected historical service information of the service provider into a service type evaluation model trained in advance to determine the probability that the selected service provider meets a specified service type;

2. The method according to claim 1, wherein selecting a service provider from the plurality of service providers that meets the screening requirement according to the screening requirement corresponding to at least one preset service information category and the historical service information of each service provider comprises:

clustering order service places in each historical order information according to the historical order information of each service provider to determine a place clustering result corresponding to each historical order information;

3. The method of claim 2, wherein selecting a service provider from the plurality of service providers that meets the screening requirements according to the location clustering result corresponding to each historical order information comprises:

calculating a ratio of the first quantity to the second quantity; the first quantity is the quantity of order service places contained in the appointed place clustering result in the place clustering result corresponding to the appointed historical order information; the second quantity is the quantity of all order service places corresponding to the specified historical order information;

and selecting the service provider which meets the screening requirement from the plurality of service providers according to the ratio of the first number to the second number.

4. The method according to claim 1, wherein selecting a service provider from the plurality of service providers that meets the screening requirement according to the screening requirement corresponding to at least one preset service information category and the historical service information of each service provider comprises:

5. The method according to claim 1, wherein selecting a service provider from the plurality of service providers that meets the screening requirement according to the screening requirement corresponding to at least one preset service information category and the historical service information of each service provider comprises:

6. The method of claim 1, wherein the historical service information comprises: the number of real-time orders allocated by the service provider after setting the real-time destination, and the number of all orders allocated by the service provider;

selecting a service provider meeting the screening requirements from the plurality of service providers according to the screening requirements respectively corresponding to at least one preset service information category and the historical service information of each service provider, and the method comprises the following steps:

7. The method of claim 1, wherein determining the service type of the selected service provider based on the probability that the service provider meets a specified service type comprises:

ranking the probability that a plurality of the selected service providers meet a specified service type;

and determining the service type of each selected service provider according to the front-back sequence of the ranking.

8. The method of claim 1, wherein determining the service type of the selected service provider based on the probability that the service provider meets a specified service type comprises:

determining a service level of each of the selected service providers in the specified service type according to a front-to-back order of the ranking.

9. The method of claim 8, further comprising:

and distributing service orders to each service provider in the selected service providers according to the determined order distribution strategy.

10. The method of claim 1, wherein the historical service information comprises any one or more of:

11. The method of claim 1, further comprising:

and distributing service orders for each service provider in the selected service providers according to the determined order distribution strategy.

12. A service type determination apparatus, comprising:

the system comprises a first acquisition module, a first processing module and a first processing module, wherein the first acquisition module is used for acquiring historical service information of a plurality of service providers;

the system comprises a first selection module, a second selection module and a selection module, wherein the first selection module is used for selecting a service provider meeting the screening requirements from a plurality of service providers according to the screening requirements respectively corresponding to at least one preset service information type and the historical service information of each service provider;

the first input module is used for inputting the selected historical service information of the service provider into a service type evaluation model trained in advance to obtain the service type of the service provider;

the first input module includes:

13. The apparatus of claim 12, wherein the first selection module comprises:

14. The apparatus of claim 13, wherein the first selecting unit comprises:

15. The apparatus of claim 12, wherein the first selection module comprises:

and the second selection unit is used for selecting the service providers meeting the screening requirement from the plurality of service providers according to the route clustering result corresponding to each piece of historical order information.

16. The apparatus of claim 12, wherein the first selection module comprises:

17. The apparatus of claim 12, wherein the historical service information comprises: the number of real-time orders allocated by the service provider after setting the real-time destination, and the number of all orders allocated by the service provider;

the first selection module comprises:

18. The apparatus of claim 12, wherein the fourth determining unit comprises:

a first ranking subunit configured to rank probabilities that a plurality of the selected service providers meet a specified service type;

a first determining subunit, configured to determine, according to a front-back order of the ranking, a service type of each selected service provider.

19. The apparatus of claim 12, wherein the fourth determining unit comprises:

a second ranking subunit configured to rank probabilities that a plurality of the selected service providers meet a specified service type;

a second determining subunit, configured to determine, according to a front-back order of the ranking, a service level of each of the selected service providers in the specified service type.

20. The apparatus of claim 19, further comprising:

a first determining module, configured to determine, according to a correspondence between a service level and an order allocation policy, an order allocation policy of each service provider in the selected service providers;

and the first distribution module is used for distributing service orders to each selected service provider according to the determined order distribution strategy.

21. The apparatus of claim 12, wherein the historical service information comprises any one or more of:

22. The apparatus of claim 12, further comprising:

a second determining module, configured to determine, according to a correspondence between a service type and an order allocation policy, an order allocation policy of each service provider in the selected service providers;

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 operating, the processor executing the machine-readable instructions to perform the service type determination method according to any one of claims 1 to 11 when executed.

24. A computer-readable storage medium, having stored thereon a computer program which, when executed by a processor, performs a method of service type determination according to any one of claims 1 to 11.