CN111126849A

CN111126849A - Method, device and equipment for assisting target logistics transfer by computer

Info

Publication number: CN111126849A
Application number: CN201911355626.3A
Authority: CN
Inventors: 燕江弟
Original assignee: Beike Technology Co Ltd
Current assignee: Seashell Housing Beijing Technology Co Ltd
Priority date: 2019-12-25
Filing date: 2019-12-25
Publication date: 2020-05-08

Abstract

A computer-implemented method, apparatus, medium, and device for facilitating targeted logistics is disclosed. The method comprises the following steps: according to the service data, role information which each service party to be allocated acts in the circulation process of the subject matter to be circulated and service experience parameters of each service party to be allocated are obtained; acquiring multiple groups of carrying factors of each service party to be distributed aiming at the to-be-transferred standard object according to the role information and the business experience parameters; respectively predicting the probability of successful circulation of the to-be-circulated subject matter of each to-be-distributed service party by utilizing multiple preset prediction algorithms according to multiple groups of carrying factors to obtain multiple groups of probabilities; the group of probabilities corresponds to a prediction algorithm, and the group of probabilities comprises the probabilities corresponding to the service parties to be distributed respectively; and selecting at least one service candidate party for the to-be-transferred target from the to-be-distributed service parties according to the plurality of groups of probabilities. The technical scheme provided by the disclosure is beneficial to improving the circulation efficiency of the object to be circulated.

Description

Method, device and equipment for assisting target logistics transfer by computer

Technical Field

The present disclosure relates to computer technologies, and in particular, to a computer-implemented method for assisting a target logistics turn, a computer-implemented apparatus for assisting a target logistics turn, a storage medium, and an electronic device.

Background

The circulation of subject matter, particularly larger subject matter (e.g., properties, etc.), often requires the intervention of a server. And selecting a proper service party for the objects to be transferred, which is favorable for promoting the successful transfer of the objects to be transferred.

Under the condition that the number of service parties is huge, how to configure a corresponding service party for a to-be-circulated target object so that the to-be-circulated target object can be successfully circulated as soon as possible is a technical problem worthy of attention.

Disclosure of Invention

The present disclosure is proposed to solve the above technical problems. Embodiments of the present disclosure provide a computer-implemented method for assisting a target logistics turn, a computer-implemented apparatus for assisting a target logistics turn, a storage medium, and an electronic device.

According to an aspect of an embodiment of the present disclosure, there is provided a computer-implemented method for assisting a subject logistics, the method including: according to the service data, role information which each service party to be allocated acts in the circulation process of the subject matter to be circulated and service experience parameters of each service party to be allocated are obtained; acquiring multiple groups of carrying factors of each service party to be distributed aiming at the object to be transferred according to the role information and the business experience parameters, wherein one group of carrying factors corresponds to the service party to be distributed, and one group of carrying factors comprises multiple carrying factors used for measuring the success transfer of the object to be transferred by the service party to be distributed; according to the multiple groups of carrying factors, utilizing multiple preset prediction algorithms to respectively predict the probability of successful circulation of the to-be-circulated standard objects of each to-be-distributed service provider, and obtaining multiple groups of probabilities; the group of probabilities corresponds to a prediction algorithm, and the group of probabilities comprises the probabilities corresponding to the service parties to be distributed respectively; and selecting at least one service candidate party for the to-be-transferred standard object from each to-be-distributed service party according to the plurality of groups of probabilities.

In an embodiment of the present disclosure, the obtaining, according to the service data, role information that each service to be allocated serves in a transfer process of a transfer subject to be transferred and a service experience parameter of each service to be allocated includes: inquiring the role information corresponding to the to-be-circulated object in business data, and obtaining at least one of information entry role information of the to-be-circulated object, field investigation role information of the to-be-circulated object, maintenance role information of the to-be-circulated object and accessory holding role information of the to-be-circulated object.

In another embodiment of the present disclosure, the obtaining, according to the service data, role information that each service to be allocated serves in a transfer process of a transfer subject to be transferred and a service experience parameter of each service to be allocated includes: and for any service party to be distributed, inquiring information related to the service party to be distributed in the business data, and obtaining at least one of information of the service party to be distributed accompanying with checking the object to be transferred, successful transfer information of the historical object carried by the service party to be distributed, conversion information of the business opportunity of the object of the service party to be distributed, business credit information of the service party to be distributed and successful transfer information of the historical object carried by a group where the service party to be distributed is located.

In another embodiment of the present disclosure, the obtaining, according to the role information and the service experience parameter, a plurality of sets of carrying factors of each service to be allocated for the object to be transferred to the target object includes: generating a plurality of groups of carrying factors of the service parties to be distributed aiming at the standard objects to be transferred respectively according to the role information, the service experience parameters and the excitation information of the service parties to be distributed; wherein the incentive information of the service party to be distributed represents compensation for the service party to be distributed belonging to a predetermined group.

In another embodiment of the present disclosure, the generating, according to the role information, the service experience parameter, and the incentive information of each to-be-allocated service provider, a plurality of sets of carrying factors of each to-be-allocated service provider for the to-be-allocated target object includes: respectively carrying out standardization processing on the role information, the service experience parameters and the excitation information to obtain the standard value of the role information, the standard value of the service experience parameters and the standard value of the excitation information; generating a receiving factor matrix data table of each service to be distributed for the to-be-circulated standard object according to the standard value of the role information, the standard value of the service experience parameter and the standard value of the excitation information; wherein, one table entry in the adapting factor matrix data table comprises a group of adapting factors.

In yet another embodiment of the present disclosure, the predetermined plurality of prediction algorithms includes at least one of: a prediction algorithm for performing weighted average calculation on the carrying factors based on a preset weight value; a neural network based prediction algorithm; a prediction algorithm based on a decision tree; a prediction algorithm based on a support vector machine; prediction algorithms based on logistic regression.

In yet another embodiment of the present disclosure, the method further comprises: setting the weight of each accepting factor, wherein the setting of the weight of each accepting factor comprises the following steps: according to the business data, acquiring role information which each service party acts in the circulation process of each historical object, business experience parameters of each service party and service party information for assisting logistics conversion success of each historical object; acquiring a plurality of groups of carrying factors of each service party aiming at each historical object respectively according to the role information and the business experience parameters, wherein one group of carrying factors corresponds to one service party and one historical object, and one group of carrying factors comprises a plurality of carrying factors for measuring the success of converting the logistics of one historical object by one service party; acquiring a plurality of groups of weights by utilizing a multi-target particle swarm algorithm according to the plurality of groups of carrying factors and the server information for assisting the logistics conversion success of each historical object; wherein, a set of weights includes: the weight value corresponding to each adapting factor; and selecting a group of weights from the multiple groups of weights according to a preset service target and a preset observation target, wherein the weights are used as weights corresponding to the carrying factors.

In another embodiment of the present disclosure, the obtaining, according to the role information and the service experience parameter, a plurality of sets of carrying factors of each service party for each historical object includes: and acquiring multiple groups of carrying factors of each service party aiming at each historical object respectively according to the role information, the service experience parameters and the excitation information of each service party.

In another embodiment of the present disclosure, the selecting at least one service candidate for the to-be-transferred target object from the to-be-distributed service providers according to the plurality of groups of probabilities includes: obtaining a group of ranks corresponding to each service party to be distributed according to the probability corresponding to each service party to be distributed in the plurality of groups of probabilities; performing ranking fusion processing on a group of rankings corresponding to each service party to be distributed to obtain a final ranking of each service party to be distributed; and selecting at least one service candidate party for the to-be-transferred target according to the final ranking of each to-be-distributed service party.

In another embodiment of the present disclosure, the performing rank fusion processing on a group of ranks corresponding to each service party to be allocated to obtain a final rank of each service party to be allocated includes: for any one to-be-distributed service party, determining the weight of each probability corresponding to the to-be-distributed service party in the plurality of groups of probabilities according to a group of ranks corresponding to the to-be-distributed service party, and calculating the fusion probability of the to-be-distributed service party according to each probability corresponding to the to-be-distributed service party and the weight of each probability; and obtaining the final ranking of each service party to be distributed according to the fusion probability of each service party to be distributed.

In another embodiment of the present disclosure, the determining, according to a set of ranks corresponding to the service provider to be allocated, a weight of each probability corresponding to the service provider to be allocated in the plurality of sets of probabilities includes: and aiming at any rank in a group of ranks corresponding to the service party to be distributed, determining the weight of the corresponding probability corresponding to the service party to be distributed according to the difference between the reverse ranking digit number corresponding to the rank and a preset value and the ratio of the number of the service parties to be distributed participating in the ranking to the difference between the preset value and the number of the service parties to be distributed.

According to another aspect of the embodiments of the present disclosure, there is provided a computer-implemented apparatus for assisting a subject logistics turn, the apparatus including: the information acquisition module is used for acquiring role information of each to-be-allocated service party in the circulation process of the to-be-circulated standard object and service experience parameters of each to-be-allocated service party according to the service data; the obtaining factor module is used for obtaining a plurality of groups of carrying factors of each service party to be distributed aiming at the object to be transferred according to the role information and the business experience parameters, wherein one group of carrying factors correspond to the service party to be distributed, and one group of carrying factors comprises a plurality of carrying factors used for measuring the success transfer of the object to be transferred by the service party to be distributed; the probability obtaining module is used for respectively predicting the probability of each service party to be distributed for successfully circulating the object to be circulated according to the plurality of groups of carrying factors by utilizing a plurality of preset prediction algorithms to obtain a plurality of groups of probabilities; the group of probabilities corresponds to a prediction algorithm, and the group of probabilities comprises the probabilities corresponding to the service parties to be distributed respectively; and the candidate party selecting module is used for selecting at least one service candidate party for the to-be-transferred standard object from the to-be-distributed service parties according to the plurality of groups of probabilities.

In an embodiment of the present disclosure, the information obtaining module includes: the first sub-module is used for inquiring the role information corresponding to the to-be-circulated target object in the service data, and obtaining at least one of the information entry role information of the to-be-circulated target object, the field investigation role information of the to-be-circulated target object, the maintenance role information of the to-be-circulated target object and the accessory owned role information of the to-be-circulated target object.

In another embodiment of the present disclosure, the information obtaining module includes: the second submodule is used for inquiring the information related to the to-be-distributed service party in the business data aiming at any to-be-distributed service party, and obtaining at least one of the information of the to-be-distributed service party accompanying and checking the to-be-distributed standard object, the successful circulation information of the historical standard object received by the to-be-distributed service party, the commodity and business opportunity conversion information of the to-be-distributed service party, the business credit information of the to-be-distributed service party and the successful circulation information of the historical standard object received by a group where the to-be-distributed service party is located.

In yet another embodiment of the present disclosure, the obtaining factor module is further configured to: generating a plurality of groups of carrying factors of the service parties to be distributed aiming at the standard objects to be transferred respectively according to the role information, the service experience parameters and the excitation information of the service parties to be distributed; wherein the incentive information of the service party to be distributed represents compensation for the service party to be distributed belonging to a predetermined group.

In yet another embodiment of the present disclosure, the obtaining factor module includes: the third sub-module is used for respectively carrying out standardized processing on the role information, the service experience parameters and the excitation information to obtain the standard values of the role information, the service experience parameters and the excitation information; the fourth sub-module is used for generating a carrying factor matrix data table of each service party to be allocated for the object to be transferred according to the standard value of the role information, the standard value of the service experience parameter and the standard value of the excitation information; wherein, one table entry in the adapting factor matrix data table comprises a group of adapting factors.

In yet another embodiment of the present disclosure, the apparatus further includes: a receiving factor weight setting module, wherein the receiving factor weight setting module is used for: according to the business data, acquiring role information which each service party acts in the circulation process of each historical object, business experience parameters of each service party and service party information for assisting logistics conversion success of each historical object; acquiring a plurality of groups of carrying factors of each service party aiming at each historical object respectively according to the role information and the business experience parameters, wherein one group of carrying factors corresponds to one service party and one historical object, and one group of carrying factors comprises a plurality of carrying factors for measuring the success of converting the logistics of one historical object by one service party; acquiring a plurality of groups of weights by utilizing a multi-target particle swarm algorithm according to the plurality of groups of carrying factors and the server information for assisting the logistics conversion success of each historical object; wherein, a set of weights includes: the weight value corresponding to each adapting factor; and selecting a group of weights from the multiple groups of weights according to a preset service target and a preset observation target, wherein the weights are used as weights corresponding to the carrying factors.

In yet another embodiment of the present disclosure, the adapting factor weight setting module is further configured to: and acquiring multiple groups of carrying factors of each service party aiming at each historical object respectively according to the role information, the service experience parameters and the excitation information of each service party.

In another embodiment of the present disclosure, the selecting the candidate block module includes: a fifth sub-module, configured to obtain, according to a probability corresponding to each service party to be allocated in the multiple groups of probabilities, a group of ranks corresponding to each service party to be allocated; the sixth submodule is used for carrying out ranking fusion processing on a group of rankings corresponding to each service party to be distributed to obtain the final ranking of each service party to be distributed; and the seventh submodule is used for selecting at least one service candidate party for the objects to be transferred to the flow target according to the final ranking of each service party to be distributed.

In yet another embodiment of the present disclosure, the sixth sub-module includes: a first unit, configured to determine, for any one to-be-allocated service provider, a weight of each probability corresponding to the to-be-allocated service provider in the multiple groups of probabilities according to a group of ranks corresponding to the to-be-allocated service provider, and calculate a fusion probability of the to-be-allocated service provider according to each probability corresponding to the to-be-allocated service provider and the weight of each probability thereof; and the second unit is used for obtaining the final ranking of each service party to be distributed according to the fusion probability of each service party to be distributed.

In yet another embodiment of the present disclosure, the first unit is further configured to: and aiming at any rank in a group of ranks corresponding to the service party to be distributed, determining the weight of the corresponding probability corresponding to the service party to be distributed according to the difference between the reverse ranking digit number corresponding to the rank and a preset value and the ratio of the number of the service parties to be distributed participating in the ranking to the difference between the preset value and the number of the service parties to be distributed.

According to still another aspect of the embodiments of the present disclosure, there is provided a computer-readable storage medium storing a computer program for executing the above computer-implemented method for assisting a targeted logistics turn.

According to still another aspect of the embodiments of the present disclosure, there is provided an electronic apparatus including: a processor; a memory for storing the processor-executable instructions; the processor is used for reading the executable instructions from the memory and executing the instructions to realize the computer-implemented method for assisting the objective logistics.

Based on the method and the device for assisting the logistics transfer of the target provided by the above embodiment of the present disclosure, since the role information of the to-be-allocated service provider in the transfer process of the to-be-transferred target object can indicate the relationship between the to-be-allocated service provider and the to-be-transferred target object, and the business experience parameter of the to-be-allocated service provider can indicate the business capability of the to-be-allocated service provider; therefore, the method and the system have the advantages that the role information of the to-be-distributed server in the circulation process of the to-be-circulated standard object and the business experience parameters of the to-be-distributed server are utilized to obtain a plurality of receiving factors of the to-be-distributed server for receiving the to-be-circulated standard object, and the plurality of receiving factors can objectively represent the value of the to-be-distributed server for receiving the to-be-circulated standard object from different angles; the method and the device have the advantages that the multiple groups of carrying factors are respectively subjected to prediction processing by utilizing the multiple preset prediction algorithms, and the service candidate party is selected from the service parties to be distributed by utilizing the multiple groups of obtained probabilities, so that the phenomenon that probability prediction is biased due to the fact that single prediction algorithm has the emphasis is avoided, and the determined service candidate party is the service party to be distributed, which is most beneficial to promoting successful circulation of the targets to be circulated as soon as possible. Therefore, the technical scheme provided by the disclosure is beneficial to improving the circulation efficiency of the to-be-circulated target object.

The technical solution of the present disclosure is further described in detail by the accompanying drawings and examples.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description, serve to explain the principles of the disclosure.

The present disclosure may be more clearly understood from the following detailed description, taken with reference to the accompanying drawings, in which:

FIG. 1 is a schematic diagram of one embodiment of a suitable scenario for use with the present disclosure;

FIG. 2 is a flow diagram of one embodiment of a computer-implemented method for assisting a targeted logistics turn of the present disclosure;

FIG. 3 is a flowchart of an embodiment of setting weights of each of the carrying factors by simulation according to the present disclosure;

FIG. 4 is a flowchart of one embodiment of the present disclosure for selecting at least one service candidate from a plurality of to-be-streamed targets;

FIG. 5 is a schematic diagram illustrating an embodiment of a computer-implemented apparatus for facilitating a targeted logistics turn in accordance with the present disclosure;

fig. 6 is a block diagram of an electronic device according to an exemplary embodiment of the present disclosure.

Detailed Description

Example embodiments according to the present disclosure will be described in detail below with reference to the accompanying drawings. It is to be understood that the described embodiments are merely a subset of the embodiments of the present disclosure and not all embodiments of the present disclosure, with the understanding that the present disclosure is not limited to the example embodiments described herein.

It should be noted that: the relative arrangement of the components and steps, the numerical expressions, and numerical values set forth in these embodiments do not limit the scope of the present disclosure unless specifically stated otherwise.

It will be understood by those of skill in the art that the terms "first," "second," and the like in the embodiments of the present disclosure are used merely to distinguish one element from another, and are not intended to imply any particular technical meaning, nor is the necessary logical order between them.

It is also understood that in embodiments of the present disclosure, "a plurality" may refer to two or more than two and "at least one" may refer to one, two or more than two.

It is also to be understood that any reference to any component, data, or structure in the embodiments of the disclosure, may be generally understood as one or more, unless explicitly defined otherwise or stated otherwise.

In addition, the term "and/or" in the present disclosure is only one kind of association relationship describing the associated object, and means that there may be three kinds of relationships, such as a and/or B, and may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" in the present disclosure generally indicates that the former and latter associated objects are in an "or" relationship.

It should also be understood that the description of the various embodiments of the present disclosure emphasizes the differences between the various embodiments, and the same or similar parts may be referred to each other, so that the descriptions thereof are omitted for brevity.

Meanwhile, it should be understood that the sizes of the respective portions shown in the drawings are not drawn in an actual proportional relationship for the convenience of description.

The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the disclosure, its application, or uses.

Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate.

It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.

Embodiments of the present disclosure may be implemented in electronic devices such as terminal devices, computer systems, servers, etc., which are operational with numerous other general purpose or special purpose computing system environments or configurations. Examples of well known terminal devices, computing systems, environments, and/or configurations that may be suitable for use with an electronic device, such as a terminal device, computer system, or server, include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, hand-held or laptop devices, microprocessor-based systems, set top boxes, programmable consumer electronics, network pcs, minicomputer systems, mainframe computer systems, distributed cloud computing environments that include any of the above, and the like.

Electronic devices such as terminal devices, computer systems, servers, etc. may be described in the general context of computer system-executable instructions, such as program modules, being executed by a computer system. Generally, program modules may include routines, programs, objects, components, logic, data structures, etc. that perform particular tasks or implement particular abstract data types. The computer system/server may be implemented in a distributed cloud computing environment. In a distributed cloud computing environment, tasks may be performed by remote processing devices that are linked through a communications network. In a distributed cloud computing environment, program modules may be located in both local and remote computer system storage media including memory storage devices.

Summary of the disclosure

In the process of implementing the present disclosure, the inventor finds that, when an object to be streamed has a chance of obtaining a business opportunity, the chance of obtaining the business opportunity at this time is generally allocated to a server in the front of the ranking according to the ranking of a plurality of servers to be allocated, which is set for the object to be streamed in advance, for processing. Due to the accuracy and reasonableness of the sequencing of the plurality of service parties to be distributed, the reasonable distribution of the opportunity of obtaining business opportunities is determined, and therefore the accuracy and reasonableness of the sequencing can influence the successful circulation of the objects of the circulation to be diverted.

Brief description of the drawings

The present disclosure provides an example of an application scenario of a computer-implemented technique for assisting a targeted logistics turn, as shown in fig. 1.

In fig. 1, it is assumed that a user 100 requests access to a website for house rental and sale through a computer 101, and a server 102 of the website pushes a main page of the website to the computer 101. For example, the server 102 pushes a page containing house condition options to the computer 101.

After the user 100 sets the corresponding house condition option on the currently displayed page of the computer 101 according to the requirement of the user, the server 102 performs house source search according to the house condition option set by the user 100, and pushes a web page containing a house source search result to the computer 101. For example, server 102 pushes a page containing pictures and text profiles of multiple sets of house sources to computer 101.

When the user 100 clicks one set of house resources in the page currently displayed by the computer 101, the server 102 will generally select one house broker as a recommender of the house resources according to the rankings of a plurality of house brokers preset for the house resources; if the server 102 cannot obtain the ranking due to access abnormality and other factors, a bottom-of-the-book strategy may be initiated, a bottom-of-the-book house broker may be determined, and the bottom-of-the-book house broker may be used as a recommender of the house source. Then, the server 102 may push a page including the detailed description information of the suite source and the recommender information to the computer 101, and the computer 101 displays the detailed description information of the suite source and the recommender information to the user 100 by displaying the page.

After the user 100 clicks the recommender information in the page currently displayed by the computer 101, a business opportunity is generated, and the recommender obtains the business opportunity, the recommender should make the conversion of the business opportunity as much as possible, for example, the recommender should obtain the contact information of the user 100 (such as the telephone number of the user 100 or the number of the instant messaging tool) as much as possible; as another example, the recommender should try to help the user 100 obtain ownership or usage rights of the premises in which the user is interested.

Exemplary method

FIG. 2 is a flow diagram of one embodiment of a computer-implemented method for assisting a targeted logistics turn of the present disclosure. As shown in fig. 2, the method of this embodiment includes the steps of: s200, S201, S202, and S203. The following describes each step.

S200, according to the service data, role information of each service party to be distributed in the circulation process of the subject matter to be circulated and service experience parameters of each service party to be distributed are obtained.

The to-be-circulated subject matter in the present disclosure is generally a more specific subject matter, for example, the to-be-circulated subject matter in the present disclosure may refer to a subject matter which needs to be registered for ownership transfer at the time of ownership transfer (for example, ownership transfer, etc.) thereof. The to-be-circulated subject matter in the present disclosure includes, but is not limited to: immovable objects, objects with higher value, or objects with larger volumes, etc. Specifically, the object to be transferred of the present disclosure may be: houses, vehicles, large production line equipment and the like.

The service in this disclosure may be an indexed logistics service. The target logistics transfer can be the transfer of ownership of the target object or ownership such as right of use, and the like. For example, the service in the present disclosure may be a house rental service, a house selling service, a vehicle (such as a vehicle, an aircraft, or a ship, etc.) rental service, a vehicle selling service, a large production line equipment rental service, a large production line selling service, and the like.

Business data in this disclosure may refer to data maintained for a server as well as data maintained for a subject matter. The subject matter herein may include: the objects that have been successfully circulated and the objects to be circulated. The subject matter in which the flow has been successful may refer to subject matter in which ownership or usage rights have currently been successfully changed. The object to be circulated may be an object whose ownership or right of use is required to be changed at present. The service data in the present disclosure may include: all information related to the objects and the service is sequentially recorded during the circulation of the objects, such as the objects which have been successfully circulated and the objects to be circulated. For example, the service data may include self-attribute information of the subject matter and information of a service party to which the subject matter relates, and the like. The self-attribute information of the subject matter may include: identification of the subject matter, and information characterizing the subject matter (e.g., information such as location of origin, area, orientation, year, house type, etc.), etc. The information of the service party to which the subject matter relates may indicate an association relationship between the subject matter and the service party (e.g., a service that the service party has currently provided for the subject matter), and the like. For example, in the real estate domain, information about the service party to which the subject matter relates may indicate an association between a house broker and a house source. Business data in the present disclosure may be stored in a data repository.

The server in the present disclosure may refer to a party that provides a service in order to assist the object to be transferred to successfully transfer, for example, the server may be a house broker or the like. The to-be-allocated service party may refer to a party waiting to allocate the to-be-circulated subject matter thereto (for example, waiting for an opportunity of a business opportunity to obtain the to-be-circulated subject matter) so as to provide a service for circulation of the corresponding to-be-circulated subject matter. For example, for the house field, the role information played by a service to be allocated in the circulation process of a to-be-circulated object may indicate the service type of the to-be-circulated object currently provided by a house broker currently provided by the to-be-circulated house source.

The service experience parameter of the service party to be allocated in the present disclosure may refer to: and the parameter is used for measuring the business capability of the service party to be distributed. The service experience parameters of the service party to be allocated in the present disclosure may include: and (3) counting relevant indexes in a plurality of service data formed by services provided by the to-be-circulated target objects and/or the successfully circulated target objects by the to-be-distributed service party at present to obtain parameters. The service experience parameters may be set according to actual service requirements. The number of parameters included in the service experience parameter may be large, and the number of parameters included in the service experience parameter is not limited by the present disclosure.

S201, acquiring multiple groups of carrying factors of each service party to be distributed aiming at the to-be-transferred standard object according to the role information and the business experience parameters.

In the present disclosure, a group of receiving factors corresponds to a to-be-allocated server, and a group of receiving factors may include a plurality of receiving factors, and all receiving factors included in a group of receiving factors may measure, from different angles, a possibility that a to-be-allocated server successfully converts a to-be-converted logistics. That is, the receiving factor in the present disclosure may be a parameter for measuring a receiving value of the to-be-allocated server for receiving the transfer service of the to-be-transferred standard object, and one to-be-allocated server may embody a receiving value of the to-be-allocated server for receiving the transfer service of the to-be-transferred standard object from different angles for a plurality of receiving factors of one to-be-transferred standard object.

In one example, a set of conjunctive factors in this disclosure may be referred to as a set of algorithmic factors. All the padding factors in a set of padding factors may be referred to as algorithmic factors. The connection factor can be considered as a factor influencing the service to be allocated to connect the successful flow of the object of the auxiliary flow target, and the service is the service.

All the adapting factors included in a set of adapting factors in the present disclosure may be combined according to the specific situation of the actual service, and the number of the adapting factors included in a set of adapting factors may be large (e.g., tens or tens, etc.), and the present disclosure does not limit the number of the adapting factors included in a set of adapting factors.

S202, according to the multiple groups of carrying factors, the probability that each service party to be distributed enables the object to be transferred to be successfully transferred is respectively predicted by utilizing multiple preset prediction algorithms, and multiple groups of probabilities are obtained.

The method can predict a group of probabilities by utilizing a prediction algorithm, wherein the group of probabilities comprises a plurality of probabilities, each probability corresponds to one service party to be distributed, and the number of the probabilities included in the group of probabilities is the same as that of the service parties to be distributed. That is, a set of probabilities includes: and predicting the probability of each service party to be distributed by utilizing a prediction algorithm. Each group of the adapting factors in the disclosure is respectively used as the input of a plurality of preset prediction algorithms, so that each prediction algorithm can perform prediction processing on the input of the prediction algorithm, and the result of the prediction processing is a probability. When all groups (such as N groups) of the adapting factors are respectively used as the input of a prediction algorithm, the prediction algorithm outputs N probabilities, and the N probabilities form a group of probabilities, so that a plurality of groups of probabilities can be obtained by utilizing multiple preset prediction algorithms.

S203, selecting at least one service candidate party for the to-be-transferred standard object from each to-be-distributed service party according to the plurality of groups of probabilities.

The method can obtain a final group of probabilities by combining a plurality of groups of probabilities, and the number of the probabilities included in the final group of probabilities can be the number of all the service parties to be distributed, so that the method can sort all the probabilities included in the final group of probabilities from large to small, and select at least one service candidate for the target object to be circulated from the service parties to be distributed according to the sorting. For example, the service to be allocated corresponding to the top probability is taken as the service candidate.

The role information of the to-be-allocated service party in the circulation process of the to-be-circulated standard object can represent the relationship between the to-be-allocated service party and the to-be-circulated standard object, and the business experience parameter of the to-be-allocated service party can represent the business capability of the to-be-allocated service party; therefore, the method and the system have the advantages that the role information of the to-be-distributed server in the circulation process of the to-be-circulated standard object and the business experience parameters of the to-be-distributed server are utilized to obtain a plurality of receiving factors of the to-be-distributed server for receiving the to-be-circulated standard object, and the plurality of receiving factors can objectively represent the value of the to-be-distributed server for receiving the to-be-circulated standard object from different angles; the method and the device have the advantages that the multiple groups of carrying factors are respectively subjected to prediction processing by utilizing the multiple preset prediction algorithms, and the service candidate party is selected from the service parties to be distributed by utilizing the multiple groups of obtained probabilities, so that the phenomenon that probability prediction is biased due to the fact that single prediction algorithm has the emphasis is avoided, and the determined service candidate party is the service party to be distributed, which is most beneficial to promoting successful circulation of the targets to be circulated as soon as possible. Therefore, the technical scheme provided by the disclosure is beneficial to improving the circulation efficiency of the to-be-circulated target object.

In an optional example, the role information in the present disclosure may be set according to an actual service situation of the subject matter circulation service. For example, the role information may include: at least one of information entry role information of the to-be-circulated subject matter, field investigation role information of the to-be-circulated subject matter, maintenance role information of the to-be-circulated subject matter, and accessory holding role information of the to-be-circulated subject matter.

Optionally, the information of the information entry role of the to-be-transferred subject matter may refer to a service party entering the relevant information of the to-be-transferred subject matter into a corresponding system. For example, for the real estate field, the information entry role information of the object to be streamed may be: and inputting the related information of the house source to be rented and sold into the information of the service party in the house source database.

Optionally, the information of the role of the object to be transferred in the field survey may be information of a service party performing the field survey at the location of the object to be transferred. For example, for the real estate domain, the information of the role of the live exploration of the target object to be circulated may be: and surveying the information of the service side of the house source to be rented and sold on the spot.

Optionally, the maintenance role information of the to-be-transferred target object may refer to information of a service provider that maintains the entity of the to-be-transferred target object and data in the system thereof. For example, for the real estate domain, the maintenance role information of the to-be-circulated target object may include: the system is responsible for updating the state information of the house source in the system, for contacting with the owner of the house source, for answering the question of the house broker for the house source and for accompanying the house broker or the client with the maintenance person to check the information of the service party of the house source.

Optionally, the affiliate-holding role information of the to-be-transferred subject matter may refer to service party information of the affiliate holding the to-be-transferred subject matter. For example, for the property area, the appendage may be a key of the property source. For another example, for the vehicle art, the accessory herein may be a key of the vehicle. For another example, in the case of a large production line device, the accessory may be a key for starting the production line device or a pass into the area where the production line device is located. The key in the present disclosure may be an electronic key or a physical key. The key in this disclosure may be a password or the like.

Optionally, for any object to be transferred, the present disclosure may obtain information entry role information of the object to be transferred, field investigation role information of the object to be transferred, maintenance role information of the object to be transferred, and accessory holding role information of the object to be transferred by querying role information corresponding to the object to be transferred in the service data. For example, the present disclosure may use the identifier of the service to be allocated as a key word, and perform matching search in various role information fields in the service data, thereby obtaining specific role information that the service to be allocated serves in the process of transferring the different objects to be transferred.

The information of multiple roles is set, so that the relation between the server to be distributed and the object to be transferred can be explained in multiple aspects, the relation between the server to be distributed and the object to be transferred can be fully embodied through corresponding receiving factors, and the value of the server to be distributed to receive the object to be transferred can be embodied in multiple angles and layers by the receiving factors.

In an alternative example, the service experience parameter of the service to be distributed in the present disclosure may be set according to the flow involved by the actual service. For example, the business experience parameters of the service to be allocated may include: the to-be-distributed service party accompanies at least one of information of the to-be-distributed subject matter, successful circulation information of the historical subject matter received by the to-be-distributed service party, subject matter business opportunity conversion information of the to-be-distributed service party, business credit information of the to-be-distributed service party and successful circulation information of the historical subject matter received by a group where the to-be-distributed service party is located. Historical subject matter in this disclosure may refer to subject matter that has been currently successfully circulated. The community where the service party to be distributed is located can be determined by the actual business situation. For example, the group in which the service to be distributed is located may be a storefront in which the service to be distributed is located, or may be a group in the storefront in which the service to be distributed is located.

Optionally, the information that the to-be-distributed service provider accompanies to view the to-be-transferred target object in the present disclosure may refer to at least one of information that the to-be-distributed service provider accompanies to other parties (e.g., a customer or other service providers, etc.) to view the to-be-transferred target object, information that the to-be-distributed service provider is accompanied (e.g., accompanied by other service providers, etc.) to view the to-be-transferred target object, and the like. The information that the to-be-allocated service party accompanies other parties to see the to-be-transferred target object may include: the server to be distributed accompanies the client belonging to the group where the server to be distributed or other servers belonging to the group where the server to be distributed views the object to be transferred, the server to be distributed accompanies the client belonging to other groups or servers belonging to other groups views the object to be transferred, and the server to be distributed accompanies the object to be transferred by the identity of the maintainer. The information that the to-be-allocated service provider is accompanied with viewing the to-be-transferred target object may include: the number of times that the maintainer accompanies the service to be distributed to check the to-be-transferred target object and the like.

Optionally, the information about successful circulation of the history object accepted by the to-be-allocated service provider in the present disclosure may refer to information about time and number of successful circulation of the history object when the history object is accepted by the to-be-allocated service provider. Specifically, the successful information of the transfer of the history subject matter received by the service party to be allocated may be further subdivided into: the service party to be allocated receives the successful times of the circulation of the historical subject matter belonging to the group in which the service party is positioned, the service party to be allocated receives the successful times of the circulation of the historical subject matter not belonging to the group in which the service party is positioned, the service party to be allocated follows the historical subject matter with the identity of the maintainer to see the successful times of the circulation, and the like.

Alternatively, the commodity business opportunity conversion information of the service party to be distributed in the present disclosure may refer to information that is advantageous for causing the business opportunity of the target to change. For example, information that facilitates the subject matter to generate a business opportunity and information that facilitates the conversion of the business opportunity of the subject matter into a successful circulation. Specifically, the target commodity-business opportunity conversion information of the service party to be allocated may include: the number of times of answering a call of the client (e.g., 400 calls) to the number of times of making a business opportunity, the number of times of answering a call of the client for more than a predetermined time to the number of times of answering a call of the client, and the number of times of obtaining a business opportunity.

Optionally, the service credit information of the to-be-allocated service party in the present disclosure may be information capable of embodying the service comprehensive strength of the to-be-allocated service party. For example, the present disclosure may set business credit information of a service party to be distributed according to various aspects such as business level test achievement, personal performance, customer evaluation, and customer complaint.

Optionally, the information about successful circulation of the history subject matter accepted by the group where the service party to be distributed is located in the present disclosure may refer to: and in a specified time range, the successful circulation information of the historical subject matters accepted by all the service parties to be distributed in the group where the service parties to be distributed are located. For example, in a specified time range, the ratio of the number of successful circulation times of the historical subject accepted by all the servers to be distributed in the group where the servers to be distributed are located to the number of the servers to be distributed in the group.

Optionally, for any service party to be distributed, the disclosure may query, in the service data, information related to the service party to be distributed, so as to obtain information that the service party to be distributed accompanies to view the to-be-distributed standard object, successful information of the distribution of the historical standard object received by the service party to be distributed, conversion information of the standard object and business opportunity of the service party to be distributed, service credit information of the service party to be distributed, and successful information of the distribution of the historical standard object received by the group in which the service party to be distributed is located. The service data in the present disclosure may include various logs, and may also include service records formed after performing statistical sorting on the various logs.

For example, the present disclosure may use the identifier of the service provider to be allocated as a keyword, perform matching search in the accompanying and viewing field and the like in the corresponding service data, thereby obtaining records related to the object of the accompanying and viewing target of the service provider to be allocated, and obtain the times of accompanying and viewing in different forms by performing statistics on related data in all records.

For another example, the present disclosure may use the group identifier, the identifier of the service party to be allocated, the transaction status, and the like as keywords to perform matching search in a plurality of corresponding fields in corresponding business data, so as to obtain records of successful circulation of the historical subject matter received by the service party to be allocated, and perform statistical processing on corresponding data in all records, so as to obtain the number of successful circulation in different forms, and the ratio of the number of successful circulation of the historical subject matter received by all service parties to be allocated in the group where the service party to be allocated is located to the number of people of all service parties to be allocated in the group.

As another example, the present disclosure may use the identifier of the service party to be allocated as a key to search log information related to the service party to be allocated in corresponding logs (such as a telephone answering log and an interactive window log) in the service data, and perform judgment and classification processing on information such as duration in the log information, so as to obtain basic data related to the target physical and mechanical transformation information of the service party to be allocated, and perform statistical processing on the basic data, so as to obtain the times, ratios, and the like in different forms.

As another example, the present disclosure may search in the service credit set in the service data with the identifier of the service party to be allocated as a key word, so as to obtain the service credit information of the service party to be allocated. The service credit information in the service credit set may be updated by periodic maintenance.

The business experience parameters of the service parties to be distributed in various forms are set, so that the business capability of the service parties to be distributed can be explained from multiple aspects, the business capability of the service parties to be distributed can be fully embodied through corresponding carrying factors, and the effect that the carrying factors can reflect the service parties to be distributed in multiple angles and layers and can carry objects to be circulated can be realized.

In an optional example, the method and the system can obtain multiple groups of carrying factors of each service party respectively aiming at each object to be transferred to the standard on the basis of using role information and business experience parameters; and acquiring multiple groups of carrying factors of each service party to be distributed aiming at the standard object to be transferred respectively on the basis of using the role information, the service experience parameter and the excitation information of each service party to be distributed. Incentive information of a to-be-distributed service provider in the present disclosure represents compensation for a to-be-distributed service provider belonging to a predetermined group. For example, incentive information for the to-be-allocated service in the present disclosure may be used to compensate for the to-be-allocated service belonging to the new entry group. Specifically, the method and the device can set different pieces of incentive information for different to-be-distributed service sides with different entry times according to the entry time of the to-be-distributed service side. I.e. the size of the incentive information may be associated with the service to be allocated.

The incentive information of the service parties is set, so that the phenomenon that the service parties to be distributed, belonging to a predetermined group, cannot obtain the receiving opportunity is avoided, the circulation efficiency of the objects to be circulated is guaranteed, and meanwhile, the service parties of different types can obtain the opportunity of providing services for the circulation of the objects to be circulated.

In an optional example, after the role information, the business experience parameter and the incentive information of each to-be-allocated service party are obtained by processing business data through querying, counting and the like, the role information, the business experience parameter and the incentive information of each to-be-allocated service party can be respectively subjected to normalization processing, so that a normalization value of the role information, a normalization value of the business experience parameter and a normalization value of the incentive information of each to-be-allocated service party are obtained; then, the method and the system can generate a receiving factor matrix data table of each service to be distributed aiming at each standard object to be circulated according to the standard value of the role information, the standard value of the service experience parameter and the standard value of the excitation information. Wherein, one table entry in the adapting factor matrix data table comprises a group of adapting factors.

Optionally, the mapping function is set for each type of role information, service experience parameter, and excitation information, so as to perform normalization processing on different types of role information, service experience parameter, and excitation information. For example, the mapping function may be used to set a parameter value smaller than a first predetermined value to 0 and a parameter value larger than a second predetermined value to a highest predetermined value (e.g., full score), and parameter values between the first predetermined value and the second predetermined value may use the original parameter value or may be mapped to a value between 0 and full score. As another example, a mapping function may be used to convert a parameter value to a value in the interval 0-1.

Optionally, the present disclosure may set a corresponding mapping function for each parameter according to a data distribution condition (e.g., a normal distribution condition) of each parameter included in the service experience parameter. For example, for the service credit information in the service experience parameter, in the case that the service credit information of each service party is a specific service credit value, the present disclosure may obtain the distribution of the service credit values of a plurality of service parties, and in general, the distribution of the service credit values of the service parties conforms to a normal distribution, and the present disclosure may set a mapping function for the service credit information, map all data at the head in the normal distribution to a minimum value (e.g., 0), map all data at the tail in the normal distribution to a maximum value (e.g., 100), and map all intermediate values between the head and the tail to a value between the minimum value and the maximum value uniformly.

Optionally, the receiving factor matrix data table in the present disclosure is a table set for a to-be-allocated service provider and a to-be-transferred standard, each table entry corresponds to one to-be-allocated service provider and one to-be-transferred standard, each table entry is a group of receiving factors, and the group of receiving factors includes: and the service party to be distributed corresponding to the table entry aims at all the carrying factors of the object to be transferred and converted corresponding to the table entry. The form of the acceptor matrix data table may take the form of a Dataframe (a tabular data structure).

According to the method and the device, the role information, the service experience parameters and the excitation information are subjected to normalized processing, and the carrying factor matrix data table is generated, so that the subsequent step of determining the service candidate party can be smoothly executed.

It should be particularly noted that the excitation information is only one optional information in the technical solution of the present disclosure, and in the technical solution described above, the excitation information and information related to the excitation information (such as a mapping function of the excitation information) are removed, and the technical effects of the present disclosure can also be achieved. For example, when generating multiple sets of carrying factors of each to-be-allocated service party respectively for a to-be-transferred standard object, the present disclosure may respectively perform normalization processing on only role information and business experience parameters, so as to obtain a normative value of the role information and a normative value of the business experience parameters; then, the method and the system can generate the data table of the carrying factor matrix of each service to be allocated according to the standard value of the role information and the standard value of the business experience parameter without considering the incentive information.

In an alternative example, the various predictive algorithms contemplated by the present disclosure may include: at least one of a prediction algorithm for performing weighted average calculation on the carrying factor based on a preset weight value, a prediction algorithm based on a neural network, a prediction algorithm based on a decision tree, a prediction algorithm based on a Support Vector Machine (SVM), and a prediction algorithm based on a Logistic Regression (LR).

Optionally, the prediction algorithm for performing weighted average calculation on the carrying factor based on the preset weight in the present disclosure may refer to: and an algorithm for performing weighted calculation on all the carrying factors contained in the group of carrying factors by using the weight values corresponding to the carrying factors contained in the group of carrying factors. For example, the present disclosure may calculate the probability Q that each service to be allocated successfully converts the logistics of the to-be-converted stream using the following formula (1):

in the above formula (1), f_iRepresenting the ith insertion factor in a set of insertion factors; w is a_iRepresenting the weight corresponding to the ith carrying factor, namely the weight of the ith carrying factor; n represents the total number of all the insertion factors comprised by a set of insertion factors.

According to the method and the device, probability calculation is carried out by utilizing each group of carrying factors and corresponding weights, so that the influence of different carrying factors on a to-be-distributed service party on the successful transfer of the to-be-transferred standard object is balanced; therefore, the probability value obtained by calculation can objectively and comprehensively reflect the possibility that the service party to be distributed makes the object to be transferred successfully transferred.

Optionally, the present disclosure may refer to the following description for fig. 3 for a process of setting weights for each adapting factor respectively.

Optionally, the present disclosure may provide a set of connected factors as input to a neural network for predicting probability, so as to perform probability prediction processing via the neural network, and the neural network outputs a probability prediction result for each input set of connected factors. The network structure of the neural network in the present disclosure includes, but is not limited to, a network structure of RNN (Recurrent neural network). In the process of training the neural network by using the sample data in the training set, the method can perform loss calculation on the difference between the prediction result of the neural network and the labeling information of the sample data by using the corresponding loss function, and adjust the network parameters (such as a weight matrix) of the neural network according to the loss calculation result. And then, when the neural network is tested by using the sample data in the test set, the number of layers of the hidden layer of the neural network can be adjusted according to the test result, after the number of layers of the hidden layer of the neural network is adjusted, the neural network is trained by using the sample data in the training set again, and the neural network with the best test result can be used as the final neural network for predicting the probability by training the neural network and repeatedly iterating the test process.

Optionally, the present disclosure may provide a set of connected factors as input to a decision tree for predicting probability so as to perform probability prediction processing through the decision tree, where the decision tree outputs a probability prediction result for each input set of connected factors. Decision trees in the present disclosure may include, but are not limited to: RF (Random Forest) Decision trees, GBDT (Gradient Boosting Decision Tree), and the like.

Optionally, when the RF decision tree is constructed, the number of tree particles and the depth of the tree should be determined, and forest algorithm parameters such as the maximum number of leaf nodes, partition criteria (such as kini coefficients) of the nodes, the minimum value of the sum of weights of all samples of the leaf nodes, and the minimum number of separable samples of the nodes are set. The method and the system can train the RF decision tree by using the sample data in the training set so as to continuously adjust the number of the RF decision tree, the depth of the RF decision tree, forest algorithm parameters and the like. The method can utilize the sample data in the test set to test the RF decision tree, adjust the parameters of the RF decision tree according to the test result (such as the size of the predetermined service target, the conversion rate of the predetermined service target and the like), and train the RF decision tree by utilizing the sample data in the training set again after adjusting the parameters of the RF decision tree, and can use the RF decision tree with the best test result as the final RF decision tree for predicting the probability by training the RF decision tree and repeatedly iterating the test process.

Optionally, in the present disclosure, when constructing the GBDT decision tree, the maximum iteration number of the weak learners of the GBDT decision tree, the weight reduction coefficient of each weak learner, and the algorithm parameters of the weak learners during initialization should be determined. The present disclosure may train the GBDT decision tree with sample data in a training set to determine algorithm parameters of the GBDT decision tree (e.g., gradually adjust the algorithm parameters of the GBDT decision tree with corresponding penalty functions). The GBDT decision tree can be tested by using the sample data in the test set, the algorithm parameters of the GBDT decision tree are adjusted according to the test result (such as the size of the predetermined service target, the conversion rate of the predetermined service target and the like), the GBDT decision tree is trained by using the sample data in the training set again after the algorithm parameters of the GBDT decision tree are adjusted, and the GBDT decision tree with the best test result can be used as the final GBDT decision tree for predicting the probability by training the GBDT decision tree and repeatedly iterating the test process.

Optionally, the present disclosure may provide a set of connected factors as input to the SVM to perform probability prediction processing by the SVM, and the SVM outputs a probability prediction result for each set of connected factors. The present disclosure may train the SVM using the sample data in the training set to continuously adjust the algorithm parameters of the SVM, where the algorithm parameters may include but are not limited to: sample feature set, sample result, sample proportion, random number seed and the like. The SVM can be tested by using the sample data in the test set, parameters of the SVM are adjusted according to test results (such as the size of a preset service target, the conversion rate of the preset service target and the like), the SVM is trained by using the sample data in the training set again after the parameters of the SVM are adjusted, and the SVM with the best test result can be used as the final SVM for predicting the probability by training the SVM and repeatedly iterating the test process.

Optionally, the disclosure may provide a set of the carry-over factors as input to the LR model to perform the probability prediction processing through the LR model, and the LR model outputs a probability prediction result for each input set of the carry-over factors. The LR model can be trained by using the sample data in the training set, so that the model parameters of the LR model can be continuously adjusted by using the corresponding loss function and adopting an optimized gradient iterative algorithm such as a least square method or a gradient descent method. The LR model can be tested by using the sample data in the test set, whether the LR model is trained by using the sample data in the training set again is determined according to the test result (such as the size of the predetermined service target, the conversion rate of the predetermined service target and the like), and the LR model with the best test result can be used as the final LR model for predicting the probability by training the LR model and repeatedly iterating the test process.

Due to the fact that various preset prediction algorithms, particularly various prediction algorithms belonging to different types, have different characteristics, for example, an overfitting phenomenon is easy to occur on the classification or regression problem of an RF decision tree with high noise, and an overfitting phenomenon is not easy to occur on a GBDT decision tree; therefore, the present disclosure is advantageous to weaken the influence of the deficiency of different prediction algorithms on the subsequent steps by performing the subsequent steps using the plurality of probability values obtained by the plurality of prediction algorithms (particularly, using the plurality of prediction algorithms belonging to different types).

In one optional example, the plurality of prediction algorithms in the present disclosure include: under the condition of a prediction algorithm for performing weighted average calculation on the carrying factors based on preset weights, each carrying factor corresponds to a corresponding weight, and the weight corresponding to each carrying factor can be set by utilizing a simulation mode. An example of setting the weight of each adapting factor by simulation is shown in fig. 3.

In fig. 3, S300, according to the service data, role information that each service party acts in the circulation process of each history object, service experience parameters of each service party, and service party information that assists in successfully transferring each history object.

Optionally, the business data used to implement the simulation should include business data related to the subject matter that has been successfully streamed so far. The object that has been successfully circulated so far, i.e., the object whose ownership or usage right has been successfully changed so far, may be referred to as a history object. Likewise, the business data used to implement the simulation may include: data maintained for the server and data maintained for the historical subject matter.

Optionally, the service party involved in the simulation process may include: the server assisting the successful conversion of the logistics of each history target and the server not assisting the successful logistics of each history target.

Optionally, the role information of a server in the circulation process of a history object may indicate the service type that the server provided the service for the history object, for example, for the real estate domain, the role information of a server in the circulation process of a history object may indicate the service type that a house broker provided the service for the history object.

Optionally, the service experience parameter of the service side may refer to: a parameter for measuring the service capability of the service party. The business experience parameters of the server in the present disclosure may include: and (3) carrying out statistics on relevant indexes in a plurality of pieces of business data formed by services provided by the server aiming at the circulation of each historical object to obtain parameters. The service experience parameters may be set according to actual service requirements. The number of parameters included in the service experience parameter may be large, and the number of parameters included in the service experience parameter is not limited by the present disclosure.

S301, acquiring multiple groups of carrying factors of each service party aiming at each historical object respectively according to the role information and the business experience parameters.

Optionally, a group of adapting factors in the simulation process corresponds to a server and a history object, the group of adapting factors may include a plurality of adapting factors, and all adapting factors included in the group of adapting factors may measure, from different angles, a possibility that a server makes logistics of a history object succeed. That is, the carrying factor in the simulation process may be a parameter for measuring the carrying value of the server for carrying the streaming service of the historical target object, and one server may embody the carrying value of the streaming service of the historical target object carried by the server from different angles for a plurality of carrying factors of the historical target object.

Optionally, all the padding factors included in the set of padding factors in the simulation process are identical to all the padding factors included in the set of padding factors described above with respect to fig. 2.

Optionally, in consideration of the excitation information of the service party, the disclosure may obtain multiple sets of carrying factors of each service party for each history object according to the role information, the service experience parameter, and the excitation information of each service party. Namely, the set of connection factors includes the connection factor corresponding to the incentive information of the service provider.

Optionally, the obtaining of multiple sets of adapting factors of each service party for each history object according to the present disclosure may refer to the description of the above method embodiment, and a description thereof is not repeated here.

S302, obtaining a plurality of groups of weights by utilizing a multi-target particle swarm optimization (MOPSO) algorithm according to the plurality of groups of carrying factors and the server information for assisting the logistics conversion success of each historical target.

Optionally, a set of weights in this disclosure may include: a plurality of weights, i.e. the weights corresponding to the receiving factors. The multi-target particle swarm optimization algorithm can substitute multiple groups of carrying factors into the multi-target particle swarm optimization algorithm respectively, and set the value of the corresponding item in the algorithm according to the server information assisting the successful circulation of each historical target object, for example, when a server assists the successful conversion of the logistics of one historical target object, the value of the corresponding item in the algorithm can be set to be 1, and when a server does not assist the successful conversion of the logistics of one historical target object, the value of the corresponding item in the algorithm can be set to be 0.

Optionally, the parameters such as the number of iterations, the number of particles, the number of non-inferior solution sets and the like in the multi-target particle swarm algorithm are preset in the disclosure. And multiple groups of weights can be obtained by solving the multi-target particle swarm algorithm. The specific solving process is not described in detail herein.

S303, selecting a group of weights from the multiple groups of weights according to a preset service target and a preset observation target, wherein the weights are used as weights corresponding to all the carrying factors.

Optionally, both the predetermined service objective and the predetermined observation objective in the present disclosure may be set according to an actual service situation. For example, for the real estate domain, the predetermined business objectives may include, but are not limited to: and converting the target by the historical house source business opportunity. The historical house source business transformation goals may include: the historical house source business machine is converted into a transfer target, the historical house source business machine is converted into a partner client to check a corresponding house source target, the historical house source business machine is converted into a successful transfer target of a historical object, and the like.

Optionally, the predetermined observation targets in the present disclosure may include, but are not limited to: the system comprises the targets of house source recall rate, a keny coefficient, low-efficiency server occupation ratio, high-efficiency server occupation ratio and the like. The number of targets included in the predetermined observation targets in the present disclosure may be large (e.g., tens, hundreds, etc.) to ensure reasonableness of the finally selected weights.

According to the method and the device, on the basis of the information related to each historical object in the service data, the weight of each receiving factor is obtained in a simulation mode, so that the setting of each weight is favorably and closely attached to the actual service, and the accuracy of setting the weight is favorably improved.

In an optional example, each service to be allocated in the present disclosure has multiple probabilities, and any probability of each service to be allocated has a probability ranking, that is, for a probability of a service to be allocated, the probability has a ranking in the group in which the service to be allocated belongs. The method and the device can synthesize the ranking of each probability of each service party to be distributed, so as to form the final ranking of all the service parties to be distributed. Specifically, the method for selecting at least one service candidate from the to-be-allocated service parties for the to-be-transferred standard object by using multiple groups of probabilities may be a process as shown in fig. 4.

In fig. 4, S400, a set of ranks corresponding to each service party to be allocated is obtained according to the probability corresponding to each service party to be allocated in the multiple sets of probabilities.

Optionally, each group of probabilities includes probabilities corresponding to all the service parties to be allocated, and each group of probabilities may be arranged in an order from the highest probability to the lowest probability, so that for any service party to be allocated, in all the group probabilities, the service party to be allocated has a rank, and all the ranks of the service party to be allocated form a group of ranks for the service party to be allocated.

For example, assume that there are three service parties to be allocated, namely a service party to be allocated a, b and c. Assuming that there are three predictive algorithms, the set of probabilities obtained using the first predictive algorithm is: probability a1, probability b1, and probability c1, and probability a1> probability b1> probability c 1; the set of probabilities obtained using the second prediction algorithm is: probability a2, probability b2, and probability c2, and probability a2> probability c2> probability b 2; the set of probabilities obtained using the third prediction algorithm is: probability a3, probability b3, and probability c3, and probability b3> probability a3> probability c 3. In the above case, the group of the ranking names corresponding to the service party a to be allocated is: first, first and second; the group of row names corresponding to the service party b to be distributed is as follows: second, third and first; the group of row names corresponding to the service party c to be distributed is as follows: third, second and third.

S401, ranking and fusing a group of rankings corresponding to each service party to be distributed to obtain the final ranking of each service party to be distributed.

Optionally, the present disclosure may utilize a group of ranks corresponding to each service to be allocated to form a corresponding weight, perform weight calculation by using the weight and the probability corresponding to each service to be allocated, and rank each service to be allocated by using the calculation result to obtain a final rank. Specifically, the present disclosure may obtain the final ranking of each service to be allocated by the following steps:

and step A, for any service party to be distributed, determining the weight of each probability corresponding to the service party to be distributed in the plurality of groups of probabilities according to a group of ranks corresponding to the service party to be distributed.

Specifically, for any service party to be allocated, the present disclosure may determine, for any ranking in a group of rankings corresponding to the service party to be allocated, a weight of a corresponding probability corresponding to the service party to be allocated according to a difference between a reverse ranking digit corresponding to the ranking and a predetermined value, and a ratio between a number of each service party to be allocated participating in the ranking and the difference between the predetermined value and the number of the service parties to be allocated. Wherein the predetermined value may be 1. In the case where the predetermined value is 1, the present disclosure may calculate a weight of a probability using the following equation (2):

w ═ (i-1)/(n-1) formula (2)

In the above formula (2), i represents the reverse ranking digit number of the probability; n represents the number of service parties to be allocated; w represents the weight obtained by calculation.

For the previous example, for the probability a1, the number of reverse ranking bits is 3, and therefore, the weight of the probability a1 is 1; for the probability b1, the number of reverse ranking bits is 2, so the weight of the probability b1 is 0.5; for the probability c1, the number of reverse ranking bits is 1, and therefore the weight of the probability c1 is 0. For the probability a2, the number of reverse ranking bits is 3, and therefore, the weight of the probability a2 is 1; for the probability b2, the number of reverse ranking bits is 1, so the weight of the probability b2 is 0; for the probability c2, the number of reverse ranking bits is 2, so the weight of the probability c1 is 0.5. Similarly, for the probability a3, the number of reverse ranking bits is 2, and therefore, the weight of the probability a3 is 0.5; for the probability b3, the number of reverse ranking bits is 3, so the weight of the probability b3 is 1; for the probability c3, the number of reverse ranking bits is 1, and therefore the weight of the probability c1 is 0.

And B, calculating the fusion probability of the distribution service party according to the probabilities corresponding to the service party to be distributed and the weights of the probabilities.

Specifically, the present disclosure may perform weighted average calculation on all probabilities and weights of the to-be-allocated service provider, and use a result of the weighted average calculation as the fusion probability of the to-be-allocated service provider. In the previous example, the fusion probability of the server a to be allocated is: probability a1 × 1+ probability a2 × 1+ probability a3 × 0.5. The fusion probability of the server b to be distributed is as follows: probability b1 × 0.5+ probability b2 × 0+ probability b3 × 1.

And step C, the final ranking of each service party to be distributed can be obtained according to the fusion probability of each service party to be distributed.

Optionally, the present disclosure may regard the fusion probability of each service party to be allocated as: and (4) the probability that each service party to be distributed makes the logistics of each logistics successful. The method and the device can sequence the fusion probabilities obtained through calculation according to the sequence from big to small, so that the final ranking of the service parties to be distributed is obtained. In addition, all probability values calculated by each prediction algorithm in the present disclosure and the finally obtained fusion probability may also take the form of Dataframe.

S402, selecting at least one service candidate party for the to-be-transferred target according to the final ranking of each to-be-distributed service party.

Optionally, the present disclosure may use the service to be allocated that is ranked the top in the final ranking as the selected service candidate. The service candidate in the disclosure may be directly used as a server for assisting the object to be streamed to perform ownership streaming, or after considering factors in terms of workload balance and the like, the disclosure may select one service candidate from a plurality of service candidates as a server for assisting the object to be streamed to perform ownership streaming. For example, for the real estate domain, a server assisting the ownership transfer of the object to be transferred may be considered as a house source recommender.

In an alternative example, the present disclosure may combine the form of the carrier matrix data table and all the calculated probability values and/or fusion probabilities to form a combined matrix data table (which may also be referred to as a full-size matrix data table), which may also be in the form of a Dataframe. The method and the device can process the comprehensive matrix data table according to the actual requirement of display loading while storing the comprehensive matrix data table (such as storing the comprehensive matrix data table in a data warehouse), and store the processed matrix data table, thereby being beneficial to conveniently displaying the comprehensive matrix data table. For example, the present disclosure may store some or all of the data in the consolidated matrix data table into corresponding Json (a lightweight data interchange format) strings.

Exemplary devices

Fig. 5 is a schematic structural diagram of an embodiment of a computer-implemented apparatus for assisting a target logistics turn according to the present disclosure. The apparatus of this embodiment may be used to implement the method embodiments of the present disclosure described above.

As shown in fig. 5, the apparatus of the present embodiment may include: an information obtaining module 500, an obtaining factor module 501, a probability obtaining module 502, and a candidate selecting module 503. In addition, the apparatus of the present disclosure may further optionally include: a weight for the reception factor module 504 is set.

The information obtaining module 500 is configured to obtain, according to the service data, role information that each service to be allocated serves in the process of transferring the to-be-transferred standard object and service experience parameters of each service to be allocated.

Optionally, the information obtaining module 500 may include: a first sub-module 5001 and a second sub-module 5002. The first sub-module 5001 is configured to query role information corresponding to the to-be-circulated object in the service data, and obtain at least one of information entry role information of the to-be-circulated object, field investigation role information of the to-be-circulated object, maintenance role information of the to-be-circulated object, and accessory holding role information of the to-be-circulated object. The second sub-module 5002 is configured to, for any one to-be-allocated service party, query information related to the to-be-allocated service party in the service data, and obtain at least one of information that the to-be-allocated service party accompanies to view a to-be-allocated standard object, information about successful flow of a history standard object received by the to-be-allocated service party, conversion information about the standard object and business opportunity of the to-be-allocated service party, information about business credit of the to-be-allocated service party, and information about successful flow of the history standard object received by a group in which the to-be-allocated service party is located.

The obtaining factor module 501 is configured to obtain multiple sets of carrying factors of each to-be-allocated service provider for the to-be-transferred target object according to the role information and the service experience parameter obtained by the obtaining information module 500. For example, the obtaining factor module 501 may generate multiple sets of carrying factors for the target object to be transferred by each service to be distributed according to the role information, the service experience parameter, and the excitation information of each service to be distributed; wherein the incentive information of the service to be distributed represents compensation for the service to be distributed belonging to the predetermined group. The group of carrying factors corresponds to a to-be-distributed server, and the group of carrying factors comprises a plurality of carrying factors for measuring the success of the to-be-distributed server in the object transfer of the to-be-transferred standard.

Optionally, the obtaining factor module 501 may include: a third submodule 5011 and a fourth submodule 5012. The third submodule 5011 is configured to perform normalization processing on the role information, the service experience parameter, and the incentive information, respectively, to obtain a normative value of the role information, a normative value of the service experience parameter, and a normative value of the incentive information. The fourth submodule 5012 is configured to generate a reception factor matrix data table of each service to be allocated for the object to be forwarded according to the specification value of the role information, the specification value of the service experience parameter, and the specification value of the incentive information. One table entry in the form of the padding factor matrix data table includes a set of padding factors.

The probability obtaining module 502 is configured to respectively predict, according to the multiple sets of carrying factors obtained by the factor obtaining module 501, the probability that each service to be allocated successfully circulates the object to be circulated by using multiple preset prediction algorithms, so as to obtain multiple sets of probabilities. The set of probabilities corresponds to a prediction algorithm, and the set of probabilities includes probabilities corresponding to the service parties to be allocated.

Optionally, the multiple prediction algorithms employed by the obtain probability module 502 may include: at least one of a prediction algorithm for performing weighted average calculation on the carrying factors based on preset weights, a prediction algorithm based on a neural network, a prediction algorithm based on a decision tree, a prediction algorithm based on a support vector machine and a prediction algorithm based on logistic regression. In addition, the weight values corresponding to the carrying factors involved in the prediction algorithm for performing weighted average calculation on the carrying factors based on the preset weight values may be set by the carrying factor weight setting module 504.

The candidate selecting module 503 is configured to select at least one candidate service party for the to-be-transferred target from the to-be-distributed service parties according to the plurality of groups of probabilities obtained by the probability obtaining module 502.

Optionally, the candidate selecting module 503 may include: a fifth sub-module 5031, a sixth sub-module 5032 and a seventh sub-module 5033. The fifth sub-module 5031 is configured to obtain a group of ranks corresponding to each service party to be allocated according to the probability corresponding to each service party to be allocated in the multiple groups of probabilities. The sixth sub-module 5032 is configured to perform rank fusion processing on a group of ranks corresponding to each service party to be allocated, so as to obtain a final rank of each service party to be allocated. For example, the sixth sub-module 5032 may include: a first unit and a second unit. The first unit is used for determining the weight of each probability corresponding to the service party to be distributed in a plurality of groups of probabilities according to a group of ranks corresponding to the service party to be distributed aiming at any service party to be distributed, and calculating the fusion probability of the service party to be distributed according to each probability corresponding to the service party to be distributed and the weight of each probability. For example, the first unit may determine, for any ranking in a group of rankings corresponding to the service to be allocated, a weight of a corresponding probability corresponding to the service to be allocated according to a difference between a number of reverse ranking bits corresponding to the ranking and a predetermined value and a ratio between a number of the service to be allocated participating in the ranking and the predetermined value. The second unit is used for obtaining the final ranking of each service party to be distributed according to the fusion probability of each service party to be distributed. The seventh sub-module 5033 is configured to select at least one service candidate for the to-be-transferred target according to the final ranking of each to-be-distributed service party.

The receiving factor weight setting module 504 may first obtain, according to the service data, role information that each service provider serves in the circulation process of each history object, service experience parameters of each service provider, and service provider information that assists in successfully converting each history object into a logistics. Then, the receiving factor setting weight module 504 may obtain multiple sets of receiving factors of each service party respectively for each history object according to the role information and the service experience parameter, for example, the receiving factor setting weight module 504 may obtain multiple sets of receiving factors of each service party respectively for each history object according to the role information, the service experience parameter, and the excitation information of each service party. The group of adapting factors comprises a plurality of adapting factors used for measuring success of converting logistics of a historical object by a service party; then, the receiving factor weight setting module 504 obtains a plurality of groups of weights by using a multi-target particle swarm algorithm according to the plurality of groups of receiving factors and the server information for assisting the logistics conversion success of each historical target; wherein, a set of weights includes: the weight value corresponding to each adapting factor; finally, the weight setting module 504 for the receiving factors can select a set of weights from the sets of weights as the respective corresponding weights of the receiving factors according to the predetermined service objective and the predetermined observation objective.

The operations specifically executed by the modules and the sub-modules and units included in the modules may be referred to in the description of the method embodiments with reference to fig. 2 to 4, and are not described in detail here.

Exemplary electronic device

An electronic device according to an embodiment of the present disclosure is described below with reference to fig. 6. FIG. 6 shows a block diagram of an electronic device in accordance with an embodiment of the disclosure. As shown in fig. 6, the electronic device 61 includes one or more processors 611 and a memory 612.

The processor 611 may be a Central Processing Unit (CPU) or other form of processing unit having computer-implemented capabilities for facilitating subject matter flow and/or instruction execution capabilities, and may control other components in the electronic device 61 to perform desired functions.

The memory 612 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory, for example, may include: random Access Memory (RAM) and/or cache memory (cache), etc. The nonvolatile memory, for example, may include: read Only Memory (ROM), hard disk, flash memory, and the like. One or more computer program instructions may be stored on the computer-readable storage medium and executed by processor 611 to implement the computer-implemented methods for facilitating subject matter logistics, and/or other desired functionality, of the various embodiments of the present disclosure described above. Various contents such as an input signal, a signal component, a noise component, etc. may also be stored in the computer-readable storage medium.

In one example, the electronic device 61 may further include: an input device 613, an output device 614, etc., which are interconnected by a bus system and/or other form of connection mechanism (not shown). The input device 613 may also include, for example, a keyboard, a mouse, and the like. The output device 614 can output various information to the outside. The output devices 614 may include, for example, a display, speakers, printer, and communication network and remote output devices connected thereto, among others.

Of course, for simplicity, only some of the components of the electronic device 61 relevant to the present disclosure are shown in fig. 6, omitting components such as buses, input/output interfaces, and the like. In addition, the electronic device 61 may include any other suitable components, depending on the particular application.

Exemplary computer program product and computer-readable storage Medium

In addition to the above-described methods and apparatus, embodiments of the present disclosure may also be a computer program product comprising computer program instructions that, when executed by a processor, cause the processor to perform the steps in a computer-implemented method for assisting a subject logistics, in accordance with various embodiments of the present disclosure described in the "exemplary methods" section of this specification above.

The computer program product may write program code for carrying out operations for embodiments of the present disclosure in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server.

Furthermore, embodiments of the present disclosure may also be a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, cause the processor to perform the steps in a computer-implemented method for assisting a subject logistics described in the "exemplary methods" section of this specification above, in accordance with various embodiments of the present disclosure.

The computer-readable storage medium may take any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may include, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium may include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

The foregoing describes the general principles of the present disclosure in conjunction with specific embodiments, however, it is noted that the advantages, effects, etc. mentioned in the present disclosure are merely examples and are not limiting, and they should not be considered essential to the various embodiments of the present disclosure. Furthermore, the foregoing disclosure of specific details is for the purpose of illustration and description and is not intended to be limiting, since the disclosure is not intended to be limited to the specific details so described.

In the present specification, the embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts in the embodiments are referred to each other. For the system embodiment, since it basically corresponds to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

The block diagrams of devices, apparatuses, systems referred to in this disclosure are only given as illustrative examples and are not intended to require or imply that the connections, arrangements, configurations, etc. must be made in the manner shown in the block diagrams. These devices, apparatuses, devices, and systems may be connected, arranged, configured in any manner, as will be appreciated by those skilled in the art. Words such as "including," comprising, "having," and the like are open-ended words that mean "including, but not limited to," and are used interchangeably therewith. The words "or" and "as used herein mean, and are used interchangeably with, the word" and/or, "unless the context clearly dictates otherwise. The word "such as" is used herein to mean, and is used interchangeably with, the phrase "such as but not limited to".

The methods and apparatus of the present disclosure may be implemented in a number of ways. For example, the methods and apparatus of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order for the steps of the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above unless specifically stated otherwise. Further, in some embodiments, the present disclosure may also be embodied as programs recorded in a recording medium, the programs including machine-readable instructions for implementing the methods according to the present disclosure. Thus, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.

It is also noted that in the devices, apparatuses, and methods of the present disclosure, each component or step can be decomposed and/or recombined. These decompositions and/or recombinations are to be considered equivalents of the present disclosure.

The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects, and the like, will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the disclosure. Thus, the present disclosure is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

The foregoing description has been presented for purposes of illustration and description. Furthermore, the description is not intended to limit embodiments of the disclosure to the form disclosed herein. While a number of example aspects and embodiments have been discussed above, those of skill in the art will recognize certain variations, modifications, alterations, additions and sub-combinations thereof.

Claims

1. A computer-implemented method for assisting in a targeted logistics turn, comprising:

according to the service data, role information which each service party to be allocated acts in the circulation process of the subject matter to be circulated and service experience parameters of each service party to be allocated are obtained;

acquiring multiple groups of carrying factors of each service party to be distributed aiming at the object to be transferred according to the role information and the business experience parameters, wherein one group of carrying factors corresponds to the service party to be distributed, and one group of carrying factors comprises multiple carrying factors used for measuring the success transfer of the object to be transferred by the service party to be distributed;

according to the multiple groups of carrying factors, utilizing multiple preset prediction algorithms to respectively predict the probability of successful circulation of the to-be-circulated standard objects of each to-be-distributed service provider, and obtaining multiple groups of probabilities; the group of probabilities corresponds to a prediction algorithm, and the group of probabilities comprises the probabilities corresponding to the service parties to be distributed respectively;

and selecting at least one service candidate party for the to-be-transferred standard object from each to-be-distributed service party according to the plurality of groups of probabilities.

2. The method according to claim 1, wherein the obtaining, according to the service data, role information that each service to be allocated acts in a transfer process of a transfer subject to be transferred and service experience parameters of each service to be allocated includes:

inquiring the role information corresponding to the to-be-circulated object in business data, and obtaining at least one of information entry role information of the to-be-circulated object, field investigation role information of the to-be-circulated object, maintenance role information of the to-be-circulated object and accessory holding role information of the to-be-circulated object.

3. The method according to claim 1 or 2, wherein the obtaining, according to the service data, role information that each service to be allocated acts in the process of transferring the to-be-transferred standard object and service experience parameters of each service to be allocated includes:

and for any service party to be distributed, inquiring information related to the service party to be distributed in the business data, and obtaining at least one of information of the service party to be distributed accompanying with checking the object to be transferred, successful transfer information of the historical object carried by the service party to be distributed, conversion information of the business opportunity of the object of the service party to be distributed, business credit information of the service party to be distributed and successful transfer information of the historical object carried by a group where the service party to be distributed is located.

4. The method according to any one of claims 1 to 3, wherein the obtaining, according to the role information and the business experience parameter, a plurality of sets of carrying factors of each to-be-allocated service provider for the to-be-transferred standard object includes:

generating a plurality of groups of carrying factors of the service parties to be distributed aiming at the standard objects to be transferred respectively according to the role information, the service experience parameters and the excitation information of the service parties to be distributed;

wherein the incentive information of the service party to be distributed represents compensation for the service party to be distributed belonging to a predetermined group.

5. The method according to claim 4, wherein the generating, according to the role information, the business experience parameter, and the incentive information of each to-be-allocated service provider, a plurality of sets of carrying factors of each to-be-allocated service provider for the to-be-allocated-flow-tagged object includes:

respectively carrying out standardization processing on the role information, the service experience parameters and the excitation information to obtain the standard value of the role information, the standard value of the service experience parameters and the standard value of the excitation information;

generating a receiving factor matrix data table of each service to be distributed for the to-be-circulated standard object according to the standard value of the role information, the standard value of the service experience parameter and the standard value of the excitation information;

wherein, one table entry in the adapting factor matrix data table comprises a group of adapting factors.

6. The method of any one of claims 1 to 5, wherein the predetermined plurality of prediction algorithms comprises at least one of:

a prediction algorithm for performing weighted average calculation on the carrying factors based on a preset weight value;

a neural network based prediction algorithm;

a prediction algorithm based on a decision tree;

a prediction algorithm based on a support vector machine;

prediction algorithms based on logistic regression.

7. The method of claim 6, wherein the method further comprises: setting the weight of each accepting factor, wherein the setting of the weight of each accepting factor comprises the following steps:

according to the business data, acquiring role information which each service party acts in the circulation process of each historical object, business experience parameters of each service party and service party information for assisting logistics conversion success of each historical object;

acquiring a plurality of groups of carrying factors of each service party aiming at each historical object respectively according to the role information and the business experience parameters, wherein one group of carrying factors corresponds to one service party and one historical object, and one group of carrying factors comprises a plurality of carrying factors for measuring the success of converting the logistics of one historical object by one service party;

acquiring a plurality of groups of weights by utilizing a multi-target particle swarm algorithm according to the plurality of groups of carrying factors and the server information for assisting the logistics conversion success of each historical object; wherein, a set of weights includes: the weight value corresponding to each adapting factor;

and selecting a group of weights from the multiple groups of weights according to a preset service target and a preset observation target, wherein the weights are used as weights corresponding to the carrying factors.

8. A computer-implemented apparatus for assisting a targeted logistics turn, wherein the apparatus comprises:

the information acquisition module is used for acquiring role information of each to-be-allocated service party in the circulation process of the to-be-circulated standard object and service experience parameters of each to-be-allocated service party according to the service data;

the obtaining factor module is used for obtaining a plurality of groups of carrying factors of each service party to be distributed aiming at the object to be transferred according to the role information and the business experience parameters, wherein one group of carrying factors correspond to the service party to be distributed, and one group of carrying factors comprises a plurality of carrying factors used for measuring the success transfer of the object to be transferred by the service party to be distributed;

the probability obtaining module is used for respectively predicting the probability of each service party to be distributed for successfully circulating the object to be circulated according to the plurality of groups of carrying factors by utilizing a plurality of preset prediction algorithms to obtain a plurality of groups of probabilities; the group of probabilities corresponds to a prediction algorithm, and the group of probabilities comprises the probabilities corresponding to the service parties to be distributed respectively;

and the candidate party selecting module is used for selecting at least one service candidate party for the to-be-transferred standard object from the to-be-distributed service parties according to the plurality of groups of probabilities.

9. A computer-readable storage medium, the storage medium storing a computer program for performing the method of any of the preceding claims 1-7.

10. An electronic device, the electronic device comprising:

a processor;

a memory for storing the processor-executable instructions;

the processor is configured to read the executable instructions from the memory and execute the instructions to implement the method of any one of claims 1-7.