CN112200440A

CN112200440A - Agent allocation method and device, electronic equipment and computer readable storage medium

Info

Publication number: CN112200440A
Application number: CN202011058251.7A
Authority: CN
Inventors: 耿学文; 卢道和; 徐峰; 陈朝亮; 刘沛峰; 芦梦娇; 邓翔; 潘康杰
Original assignee: WeBank Co Ltd
Current assignee: WeBank Co Ltd
Priority date: 2020-09-30
Filing date: 2020-09-30
Publication date: 2021-01-08

Abstract

The embodiment of the application provides a method, a device and equipment for allocating agents and a computer readable storage medium; the method comprises the following steps: acquiring the number of objects to be served in a first queue; under the condition that the number of the objects to be served is greater than or equal to a set threshold value, carrying out value scoring on each object to be served in the first queue based on a value scoring model to obtain a value scoring result; reordering the objects to be served in the first queue based on the value scoring result to obtain an ordering result; and distributing service seats to the various objects to be served based on the sequencing result.

Description

Agent allocation method and device, electronic equipment and computer readable storage medium

Technical Field

The present application relates to the field of intelligent dispatching of financial technology (Fintech), and relates to, but is not limited to, a method, an apparatus, an electronic device, and a computer-readable storage medium for agent allocation.

Background

With the development of computer technology, more and more technologies are applied in the financial field, and the traditional financial industry is gradually changing to financial technology (Fintech), but higher requirements are also put forward on the technologies due to the requirements of the financial industry on safety and real-time performance.

Currently, in the field of financial technology, in order to implement allocation of service agents to users, a first-in first-out method is generally adopted based on a single user queue to automatically assign service work orders to service agents with free service agents; when a plurality of service seats with idle service seats exist, automatic allocation is carried out by adopting a random algorithm, and when all the service seats do not exist with idle service seats, a service work order is received after any service seat is waited to be idle.

According to the scheme for distributing the service seats to the users, the service seats are distributed to the users only on the basis of the time sequence, the service seats cannot be distributed according to business requirements, and therefore the distribution accuracy of the seats is low.

Disclosure of Invention

The embodiment of the application provides a seat allocation method and device, electronic equipment and a computer readable storage medium.

The technical scheme of the embodiment of the application is realized as follows:

the embodiment of the application provides a seat allocation method, which comprises the following steps:

acquiring the number of objects to be served in a first queue;

under the condition that the number of the objects to be served is greater than or equal to a set threshold value, carrying out value scoring on each object to be served in the first queue based on a value scoring model to obtain a value scoring result;

reordering the objects to be served in the first queue based on the value scoring result to obtain an ordering result;

and distributing service seats to the various objects to be served based on the sequencing result.

In some embodiments of the present application, the scoring the value of each object to be served in the first queue based on the value scoring model, and obtaining the value scoring result includes:

acquiring at least one attribute of each object to be served in the first queue;

and based on at least one attribute of each object to be served in the first queue, performing value scoring on each object to be served in the first queue by adopting a value scoring model to obtain a value scoring result.

It can be seen that, in the embodiment of the application, the value scoring can be performed on the object to be served based on at least one attribute of the object to be served, so that the value scoring which accurately reflects the value of the object to be served can be obtained, and further, the subsequent accurate sequencing can be performed, and the service can be preferentially provided for the object to be served with higher value.

In some embodiments of the present application, the scoring a value of each object to be served in the first queue by using a value scoring model based on at least one attribute of each object to be served in the first queue, and obtaining a value scoring result includes:

and under the condition that the at least one attribute comprises multiple attributes, carrying out weighted summation on the scoring values of the multiple attributes of each object to be served in the first queue to obtain the value scoring result.

Therefore, in the embodiment of the application, the value scoring result can be determined based on the scoring values and the weights of various attributes of the object to be served, so that the value scoring which accurately reflects the value of the object to be served can be obtained, the subsequent accurate sequencing can be facilitated, and the service can be preferentially provided for the object to be served with higher value.

In some embodiments of the present application, the allocating a service agent to each object to be served based on the ranking result includes:

according to the sequencing result, at least one object to be served in each object to be served is placed in a second queue;

and distributing service seats to the objects to be served in the second queue.

As can be understood, according to the sorting result, the object to be served with higher value may be placed in the second queue, so as to preferentially allocate a service agent to the object to be served with higher value, thereby facilitating to preferentially provide service for the object to be served with higher value.

In some embodiments of the present application, the allocating a service agent to the object to be served in the second queue includes:

determining a target service seat allocated to the object to be served in the second queue, and when the service queue of the target service seat is not idle, allocating the target service seat to the object to be served in advance; and after the service queue of the target service seat is free, distributing the object to be served to the target service seat.

Therefore, when the service seat runs at full load, the objects to be served in the second queue can be pre-distributed, and after the target service seat is idle, the objects to be served can be directly distributed to the target service seat, so that the problem of intelligent seat distribution in the service seat running at full load can be solved.

In some embodiments of the present application, the determining a target service agent allocated to an object to be served in the second queue includes:

determining a score value of each service agent according to at least one index, wherein the at least one index comprises at least one of the following: the seat service capability index, the seat state index and the seat working strength index are matched with the objects to be served in the second queue, and the seat state index is used for representing the number of the objects being served by the service seat;

and selecting the target service seat from the service seats according to the grade value of each service seat.

Therefore, the service agent suitable for the object to be served can be accurately determined, and the service effect of the service agent is improved.

In some embodiments of the present application, the method further comprises:

and determining the agent service capability index matched with the object to be served in the second queue according to at least one characteristic of the object to be served in the second queue.

It can be seen that, in the embodiment of the present application, by determining the agent service capability index matched with the object to be served in the second queue, it is beneficial to accurately obtain the service capability of each service agent for the object to be served, so as to accurately allocate the service agent to the object to be served.

In some embodiments of the present application, the determining the score value of each service agent according to at least one index includes:

under the condition that the number of the at least one index is greater than 1, acquiring a weight parameter of each index in the at least one index;

and determining the score value of each service agent according to the weight parameter of each index and the at least one index.

Therefore, the method and the device can accurately obtain the score value of each service agent, and are beneficial to accurately selecting the target service agent for the service object.

In some embodiments of the present application, the weight parameters include: the first weight of each index in the at least one index is determined according to an entropy method, and/or the second weight of each index in the at least one index is a preset value.

The service agents can be classified according to the first weight and/or the second weight of each index, and the service agents can be classified according to the classification value of each index.

In some embodiments of the present application, the method further comprises:

standardizing the at least one index to obtain at least one standardized index, wherein the value ranges of different standardized indexes are the same;

determining the proportion of each index in the at least one index after the standardization treatment to each index after the standardization treatment;

and determining a first weight of each index in the at least one index according to the entropy method based on the proportion of each index in the at least one index after the standardization treatment to each index after the standardization treatment.

It can be seen that, in the embodiment of the present application, the specific gravity of each index after the normalization processing can be determined, and then, the first weight of each index can be conveniently determined.

In some embodiments of the present application, the determining the first weight of each of the at least one index based on the weight of each of the at least one index after the normalization process to the respective index after the normalization process according to the entropy method includes:

determining the information entropy redundancy of each index in the at least one index based on the proportion of each index in the at least one index after the standardization treatment to each index after the standardization treatment;

determining a first weight of each index of the at least one index based on the entropy redundancy of the information of each index of the at least one index.

Therefore, the first weight of each index can be accurately determined according to the information entropy redundancy of each index on the basis of determining the specific gravity of each index after the standardization processing.

and when no object which is served exists in any service seat in the service seats, determining the score value of any service seat as a set maximum score value.

It can be seen that when there is no object being served by the service agent, it indicates that the service agent is in a completely idle state, and at this time, the score value of the service agent is set to be the maximum score value, and the corresponding service agent can be determined to be the target service agent, so that the target service agent can be allocated to the object to be served, and the service agent is not in the completely idle state, which is beneficial to improving the service efficiency of the service agent.

The embodiment of the application provides an agent distributor, the device includes:

the acquisition module is used for acquiring the number of the objects to be served in the first queue;

the first processing module is used for scoring the value of each object to be served in the first queue based on a value scoring model under the condition that the number of the objects to be served is greater than or equal to a set threshold value to obtain a value scoring result;

the second processing module is used for reordering the objects to be served in the first queue based on the value scoring result to obtain an ordering result;

and the distribution module is used for distributing service seats to the objects to be served based on the sequencing result.

In some embodiments of the present application, the first processing module is configured to score a value of each object to be served in the first queue based on a value scoring model, and obtaining a value scoring result includes:

In some embodiments of the present application, the first processing module is configured to score a value of each object to be served in the first queue by using a value scoring model based on at least one attribute of each object to be served in the first queue, and obtaining a value scoring result includes:

In some embodiments of the present application, the allocating module, configured to allocate a service agent to each object to be served based on the sorting result, includes:

and distributing service seats to the objects to be served in the second queue.

In some embodiments of the present application, the allocating module, configured to allocate a service agent to an object to be served in the second queue, includes:

In some embodiments of the present application, the allocating module, configured to determine a target service agent allocated to an object to be served in the second queue, includes:

In some embodiments of the present application, the allocating module is further configured to determine, according to at least one characteristic of the objects to be served in the second queue, an agent service capability index matched with the objects to be served in the second queue.

In some embodiments of the present application, the allocating module, configured to determine a score value of each service agent according to at least one index, includes:

In some embodiments of the present application, the assignment module is further configured to:

In some embodiments of the present application, the allocating module, configured to determine the first weight of each of the at least one index according to the entropy method based on a specific gravity of each of the at least one index after the normalization process to each of the at least one index after the normalization process, includes:

An embodiment of the present application provides an electronic device, which includes:

a memory for storing executable instructions;

and the processor is used for realizing any one of the agent allocation methods when executing the executable instructions stored in the memory.

An embodiment of the present application provides a computer-readable storage medium, which stores executable instructions and is configured to, when executed by a processor, implement any one of the agent allocation methods described above.

In the embodiment of the application, the number of objects to be served in a first queue is obtained; under the condition that the number of the objects to be served is greater than or equal to a set threshold value, carrying out value scoring on each object to be served in the first queue based on a value scoring model to obtain a value scoring result; reordering the objects to be served in the first queue based on the value scoring result to obtain an ordering result; and distributing service seats to the various objects to be served based on the sequencing result. It can be seen that, in the embodiment of the application, the queue order of the objects to be served in the first queue can be optimized based on the value of the objects to be served, so that the method is beneficial to providing service for the objects to be served with higher value preferentially; in addition, the value of the object to be served can reflect the actual demand of the object to be served, so that the allocation accuracy of the agent is low due to the fact that the service agent is allocated according to the business demand, the service agent can be allocated to the object to be served according to the actual demand, and the service effect of the service agent is improved.

Drawings

Fig. 1 is an alternative flowchart of an agent allocation method according to an embodiment of the present disclosure;

fig. 2 is a schematic structural diagram of a dispatch service system for implementing the agent allocation method according to an embodiment of the present disclosure;

fig. 3 is another alternative flowchart of an agent allocation method according to an embodiment of the present disclosure;

fig. 4 is a schematic diagram of an alternative configuration of the agent distribution device according to the embodiment of the present application;

fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

In the related art, a first-in first-out method is adopted to automatically dispatch a service work order to a service agent with a free service agent on the basis of a single user queue; the dispatching method is simple and extensive in implementation and cannot optimize the dispatching process based on data driving; further, when the user queue is blocked or long in the user queue, some users with high value may be lost due to too long waiting time; in addition, the dispatching method cannot be combined with the attributes of the users and the capability of the service seat for intelligent matching, so that the service effect of the service seat is poor.

In view of the above technical problems, the technical solutions of the embodiments of the present application are provided.

In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be described in further detail with reference to the attached drawings, the described embodiments should not be considered as limiting the present application, and all other embodiments obtained by a person of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

The embodiment of the application provides a method, a device and equipment for allocating agents and a computer readable storage medium; the agent allocation method provided by the embodiment of the present application may be applied to an electronic device, and an exemplary application of the electronic device provided by the embodiment of the present application is described below, where the electronic device provided by the embodiment of the present application may be implemented as a notebook computer, a tablet computer, a desktop computer, a set-top box, a mobile device (e.g., a mobile phone, a portable music player, a personal digital assistant, a dedicated messaging device, a portable game device), and the like.

The agent allocation method according to the embodiment of the present application is described below by way of example.

Fig. 1 is an optional flowchart of an agent allocation method provided in the embodiment of the present application, and as shown in fig. 1, the flowchart may include:

step 101: and acquiring the number of the objects to be served in the first queue.

In the embodiment of the application, the object to be serviced may represent an object that needs to be subjected to an agent service, and the agent service may be a service provided by at least one agent, for example, the agent service may be a service related to an insurance product; at least two objects to be served may exist in the first queue, and each object to be served may correspond to one user; that is, the first queue may represent a user queuing queue.

In practical application, the number of the objects to be served in the first queue can be counted in real time; every time when one object to be served enters the first queue, the number of the objects to be served in the first queue can be reduced by one; each time an object to be serviced is removed from the first queue, the number of objects to be serviced in the first queue may be incremented by one.

Step 102: and under the condition that the number of the objects to be served is greater than or equal to the set threshold value, carrying out value scoring on each object to be served in the first queue based on the value scoring model to obtain a value scoring result.

In the embodiment of the application, the set threshold is a value greater than or equal to 2, and the set threshold can be set empirically according to actual requirements; when the number of the objects to be served is greater than or equal to the set threshold, the first queue can be considered as a congestion queue.

In the embodiment of the application, the value scoring model represents a model for scoring the value of the object to be served, and the value scoring model can be preset according to actual conditions; the value scoring result comprises the value scoring of each object to be served in the first queue, and the higher the value scoring of the object to be served is, the higher the value of the object to be served is, and the more the object to be served needs to be served preferentially.

In some embodiments, parameters of the value scoring model may be set according to an actual scene, and different value scoring models may be set for different scenes, or different parameters may be set in the value scoring model.

Step 103: and reordering the objects to be served in the first queue based on the value scoring result to obtain a sequencing result.

In the embodiment of the application, the sequencing result indicates the sequence of each object to be served in the first queue.

Step 104: and distributing service seats to the objects to be served based on the sequencing result.

In practical applications, the steps 101 to 104 may be implemented based on a Processor in an electronic Device, where the Processor may be at least one of an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a Central Processing Unit (CPU), a controller, a microcontroller, and a microprocessor. It is understood that the electronic device implementing the above-described processor function may be other electronic devices, and the embodiments of the present application are not limited thereto.

It can be seen that, in the embodiment of the application, the queue order of the objects to be served in the first queue can be optimized based on the value of the objects to be served, so that the method is beneficial to providing service for the objects to be served with higher value preferentially; in addition, the value of the object to be served can reflect the actual demand of the object to be served, so that the allocation accuracy of the agent is low due to the fact that the service agent is allocated according to the business demand, the service agent can be allocated to the object to be served according to the actual demand, and the service effect of the service agent is improved.

For an implementation manner of scoring the value of each object to be served in the first queue based on the value scoring model to obtain a value scoring result, exemplarily, at least one attribute of each object to be served in the first queue may be obtained; and based on at least one attribute of each object to be served in the first queue, performing value scoring on each object to be served in the first queue by adopting a value scoring model to obtain a value scoring result.

In this embodiment, the first queue may include an identifier and an attribute of each object to be served, where the identifier of the object to be served may be a name, an Identity Document (ID), or other information.

Fig. 2 is a schematic structural diagram of a dispatch service system for implementing the agent allocation method according to an embodiment of the present disclosure, and referring to fig. 2, in some embodiments of the present disclosure, an attribute of an object to be serviced may include at least one of the following: age, gender, location, channel from which the product is obtained, product, length of wait in the first queue.

Various attributes of the object to be serviced are exemplarily illustrated by table 1 below.

TABLE 1

In table 1, H5 is an abbreviation of hypertext Markup Language (Hyper Text Markup Language)5.0, and APP is an abbreviation of Application program (Application).

In some embodiments, the attributes of the object to be serviced may be stored in a database, for example, referring to fig. 2, the attributes of the object to be serviced may be stored in a distributed database tdsql (tencent distributed mysql).

For the implementation manner that the value scoring result is obtained by scoring the value of each object to be served in the first queue based on at least one attribute of each object to be served in the first queue by using a value scoring model, exemplarily, the value scoring result may be obtained by performing weighted summation on the score values of the multiple attributes of each object to be served in the first queue under the condition that the at least one attribute includes multiple attributes.

In the embodiment of the present application, each attribute score value and weight of an object to be served may be preset, and a plurality of attribute score values and weights of the object to be served are exemplarily described below by using table 2.

TABLE 2

The value score for each object to be served can be expressed as Q, with reference to table 2, Q ═ wait duration score 50% + (age score 30% + regional score 20% + channel score 20% + product score 30%) 50%.

On the basis of table 1 and table 2, an implementation manner of reordering each object to be served in the first queue is exemplarily illustrated below through table 3 and table 4, where table 3 is a table of correspondence between a queue order and an attribute of the object to be served in the first queue at an initial time (e.g., 11:00), and table 4 is a table of an ordering result obtained by reordering each object to be served in the first queue.

TABLE 3

TABLE 4

In some embodiments of the present application, value scoring may be performed on each object to be served in the first queue every first set time period based on a value scoring model.

Here, the first set time period may be set in advance, and for example, the first set time period may be 4 seconds, 5 seconds, 6 seconds, or the like.

Fig. 3 is another optional flowchart of the agent allocation method provided in the embodiment of the present application, and referring to fig. 2 and fig. 3, value scoring may be performed on each object to be served in the first queue based on a value scoring model at regular time, so as to implement dynamic optimization of the queue order of the first queue.

Therefore, in the embodiment of the application, the queue sequence of the first queue can be optimized at regular time, so that the value score reflecting the value of the object to be served at the current moment can be obtained in time, and the service agent allocation can be accurately realized in real time.

In some embodiments of the present application, an implementation manner of allocating a service agent to each object to be served based on the sorting result may be that, according to the sorting result, at least one object to be served in each object to be served is placed in a second queue; and allocating service seats to the objects to be served in the second queue.

In this embodiment of the application, the second queue may be a level two cache queue, for example, referring to fig. 2, the second queue may be a Redis queue.

In an implementation manner, referring to fig. 3, it may be sequentially determined whether the objects to be served in the first queue may enter the second queue according to the sorting result, that is, it may be first determined whether the first object to be served in the first queue may enter the second queue, and when the first object to be served in the first queue may enter the second queue, the first object to be served in the first queue is placed in the second queue, and the first object to be served in the first queue is removed from the first queue; then, it can be continuously determined whether the first object to be served in the first queue can enter the second queue at the current time.

In an implementation manner, whether the objects to be served in the first queue can enter the second queue or not can be determined and judged according to the number of the objects to be served in the second queue, and when the number of the objects to be served in the second queue is smaller than a preset number, the length of the second queue is smaller, and at the moment, it is determined that the first object to be served in the first queue can enter the second queue; on the contrary, if the number of the objects to be served in the second queue is greater than or equal to the preset number, the length of the second queue is smaller, and at this time, it is determined that the first object to be served in the first queue cannot enter the second queue.

It should be noted that, if the first object to be served in the first queue at the current time may not enter the second queue, it is continuously determined whether the first object to be served in the first queue at the current time may enter the second queue.

For the implementation manner of allocating the service seats to the objects to be served in the second queue, for example, the target service seat allocated to the objects to be served in the second queue may be determined, and when the service queue of the target service seat is not idle, the target service seat is allocated to the objects to be served in advance; and after the service queue of the target service seat is free, distributing the object to be served to the target service seat.

In the embodiment of the application, any service seat can serve K users at most, and the online service queue of any service seat represents an object which is served by the service seat; when the number of the objects which are being served by any service seat is equal to K, the service seat is free; when the number of the objects which are being served by any service seat is equal to K, the service seat is idle, and can provide services for other objects to be served at the same time; wherein K is an integer greater than or equal to 1.

For the implementation of determining the target service agent allocated to the object to be served in the second queue, the scoring value of each service agent may be determined according to at least one index, where the at least one index includes at least one of the following: the agent service capability index, the agent state index and the agent working strength index are matched with the objects to be served in the second queue, and the agent state index is used for representing the number of the objects being served by the service agent; and selecting a target service agent from the service agents according to the grade value of each service agent.

In some embodiments, when K equals 5, the agent status indicator may be 0, 1, 2, 3, 4, or 5; referring to fig. 3, after the service of the service agent to any object is finished, the agent online service queue and the agent status index may be updated in real time.

In some embodiments, the agent working strength index is used to reflect the working strength of the agent in a period of time, for example, the agent working strength index may be determined according to the number of times of day service of the service agent and the effective service duration of each service, and the effective service duration represents the effective communication duration when the service agent person and the user perform one service, that is, the agent working strength index may be the total effective duration of the service on the day; the agent working strength index may be a product of the number of services of the agent on the day and an average effective service duration, which represents an average of effective service durations of services on each day.

In some embodiments, referring to fig. 3, after the service of the service agent to any one object is ended, the agent service record may be updated, and then the score of the agent working strength index may be updated, where the agent service record includes the effective service duration of the service; further, the seat service record includes information such as service satisfaction, product of the user, age of the user, gender of the user, region of the user, and channel of the product acquired by the user.

In some embodiments of the present application, an agent service capability index matching an object to be served in the second queue may be determined according to at least one characteristic of the object to be served in the second queue.

Here, the at least one characteristic of the object to be served may be at least one of: age, gender, region, channel for obtaining the product, and product.

In practical application, referring to fig. 2 and 3, an agent capability model may be obtained, where the agent capability model is used to determine the service capability of each service agent for each object to be served; after the agent capability model is obtained, at least one feature of the object to be served may be input into the agent capability model, and an agent service capability index matched with the object to be served in the second queue is obtained.

In some embodiments, service data of each service agent within a second set time period may be acquired every second set time period, and an agent service capability index and/or an agent working strength index may be updated according to the service data.

Here, the second set time period may be preset according to an actual scene, for example, the second set time period may be 1 day, 2 days, 1 week, or the like.

In some embodiments, referring to fig. 2, after the tth day ends, the seat service record of the tth day may be obtained, where the seat service record of the tth day includes the seat service record of the current service of each service seat of the tth day; then, the seat capability model can be updated based on the seat service record of the Tth day at the zero point of the T +1 th day; t is an integer greater than or equal to 1.

The agent service record for the tth day is exemplarily illustrated by table 5 below.

TABLE 5

In some embodiments, the agent service record of day T may be synchronized to a data warehouse tool when the agent service record of day T is obtained, for example, the data warehouse tool may be Hive, which is a data warehouse tool based on Hadoop and used for data extraction, transformation, and loading.

And synchronizing the seat service records of the Tth day to the data warehouse tool, and performing data cleaning and processing on the seat service records of the Tth day by using the data warehouse tool so as to update the seat capability model. In some embodiments, the agent capability model may also be updated into a database, such as TDSQL, to facilitate subsequent invocations.

It can be seen that the agent service capability index can be updated by updating the agent capability model.

In some embodiments of the present application, the service data of each service agent in the second set duration may include the working strength of each service agent in the second set duration, and thus, based on the service data of each service agent in the second set duration, the agent working strength index in the second set duration may be updated.

Therefore, the service ability index and/or the agent working strength index of the agent are updated at regular time, the score value of each service agent can be accurately obtained, and the service agents can be accurately distributed to the objects to be served.

In some embodiments, the agent capability model may be described by a number of parameters, which are illustratively described below by table 6.

TABLE 6

In table 6, the user satisfaction represents the average satisfaction of the service agent for multiple services, the channel conversion rate represents the probability that the service object of the service agent comes from each channel, the region conversion rate represents the probability that the service object of the service agent comes from each region, the product conversion rate represents the probability that the service object of the service agent selects various products, and the age conversion rate represents the probability that the service object of the service agent is in each age group.

In some embodiments, an agent global satisfaction table, an agent sub-channel conversion rate (seat _ channel _ rate) table, an agent sub-regional conversion rate (seat _ area _ rate) table, an agent sub-product conversion rate (seat _ product _ rate) table, and an agent sub-age conversion rate (seat _ age _ rate) table may be generated based on the parameters of the agent capability model shown in table 6; here, the agent overall satisfaction degree table includes a user satisfaction degree parameter, the agent channel conversion rate table includes a channel conversion rate parameter, the agent region conversion rate table includes a region conversion rate parameter, the agent product conversion rate table includes a product conversion rate parameter, and the agent age conversion rate table includes an age conversion rate parameter.

In some embodiments, a parameter matched with the object to be served in the agent capability model may be selected according to at least one characteristic of the object to be served, and the agent service capability index may include the selected parameter matched with the object to be served; for example, in combination with table 6, information such as a product channel can be obtained according to a product, an age, and a user region of the object to be served, and a product conversion rate, an age conversion rate, a region conversion rate, and a channel conversion rate that are matched with the object to be served are selected.

In some embodiments, a database storing an agent capability model may be used to find an agent service capability indicator matching an object to be serviced using Structured Query Language (SQL) logic, and an exemplary SQL logic code is as follows:

select a.seat_id,b.rate,c.rate,d.date,e.rate

from seat_satisfaction a,seat_channel_rate b,seat_area_rate c,seat_product_r ate d,seat_age_rate e

where a.seat_id＝b.seat_id

and b.seat_id＝c.seat_id

and c.seat_id＝d.seat_id

and d.seat_id＝e.seat_id

and b.channel＝<％user.channel％>

and c.area＝<％user.area％>

and d.product＝<％user.product％>

and e.age＝<％user.age％>

In some embodiments, a dynamic weighting algorithm may be adopted to calculate the at least one index, and a target service seat of an object to be served is determined according to a calculation result; the dynamic weighting algorithm is exemplified below.

In some embodiments, when the number of the at least one index is greater than 1, a weight parameter of each index in the at least one index is obtained; and determining the score value of each service agent according to the weight parameter of each index and at least one index.

In practical application, referring to fig. 3, at least one index may be weighted and summed according to the weight parameter of each index to obtain the score value of each service agent, so that intelligent agent matching may be performed according to the score value of each service agent, that is, a target service agent is determined according to the score value of each service agent; after the target service seat is determined, the object to be served enters an online service queue of the target service seat to receive seat service.

Illustratively, the number of the service agents is m, m is an integer greater than 1, and the m service agents are respectively marked as S₁To S_mEach service seat has n indexes, and the n indexes are respectively marked as X₁To X_nN is an integer greater than 1; thus, n indices X can be targeted₁To X_nAnd respectively obtaining the weight parameters so as to obtain the score value of each service agent.

In some embodiments of the present application, the weight parameter may include: the first weight of each index in the at least one index is determined according to an entropy method, and/or the second weight of each index in the at least one index is a preset value.

Here, entropy is a measure of uncertainty. The larger the information quantity is, the smaller the uncertainty is, and the smaller the entropy is; the smaller the amount of information, the greater the uncertainty and the greater the entropy. According to the characteristics of entropy, the randomness and the disorder degree of an event can be judged by calculating the entropy, or the dispersion degree of a certain index can be judged by using the entropy, and the larger the dispersion degree of the index is, the larger the influence (weight) of the index on comprehensive evaluation is; that is, the first weight of each index in at least one index obtained by using the entropy method is not a weight set subjectively by a user, but a weight reflecting the dispersion degree of the index.

In practical applications, the second weight of each of the at least one index may be set by a user according to actual requirements.

In some embodiments of the present application, determining the score value of each service agent according to the at least one index may be implemented by determining the score value of any one service agent as a set maximum score value when there is no object being served by any one service agent in each service agent.

Here, the set maximum score value represents an upper limit of a preset score value, and the score value of each service agent cannot be greater than the set maximum score value; in some examples, the maximum score value is set to 1.

In one example, the agent service capability index includes 5 indexes, and the 5 indexes are user satisfaction degrees X respectively₁Sub-channel conversion rate X₂Regional conversion rate X₃Conversion rate of product X₄And the age-related ratio X₅Wherein the sub-channel conversion rate X₂Representing the channel conversion rate, regional conversion rate X, matched with the channel of the acquired product of the object to be served₃Expressing the conversion rate of the region matched with the region of the object to be served, the conversion rate of the products by X₄Expressing the conversion rate of products matched with the products of the objects to be served, the differential aging rate X₅Representing an age conversion rate matched with the age of the object to be served; it can be understood that the 5 indexes are all positive indexes, the positive indexes are positively correlated with the score values of the service agents, and the larger the value of the positive indexes is, the higher the score value of the service agents is.

The seat status index is represented as X₆The working strength index of the seat is represented as X₇Understandably, the agent status index X₆And the working strength index X of the seat₇The positive index is negative relative to the service agent scoring value, and the larger the value of the positive index is, the lower the service agent scoring value is.

When the first weight of each index is determined by calculation according to the entropy method, each index needs to be standardized, and the process of the standardization includes: and carrying out forward processing on the reverse indexes, and carrying out normalization processing on the numerical values of all the indexes to enable the value ranges of the numerical values of all the indexes after normalization processing to be the same value range.

For example, the value range of each index after the normalization process is 0 to 1, and the value range of the user satisfaction is 0 to 10, then the user satisfaction X may be calculated₁Divided by 10 to obtain the normalized productDegree of satisfaction of the user y₁(ii) a Sub-channel conversion rate X₂Is in the range of 0 to 1, and at this time, the conversion rate y of the sub-channel after the standardization treatment is₂＝X₂(ii) a Regional conversion rate X₃Is in the range of 0 to 1, and at this time, the regional conversion rate y after the standardization process₃＝X₃(ii) a Conversion ratio of product X₄Is in the range of 0 to 1, at which the conversion of the sub-product after the standardization treatment is y₄＝X₄(ii) a Age-based rate X₅Is in the range of 0 to 1, at which the conversion rate y of the normalized chronological age is₅＝X₅(ii) a Seat state index X₆For reverse direction, the sitting posture index X is required₆Forward processing and normalization processing are carried out, and the seat state index X is considered₆For discrete values, a normalized agent status indicator y may be determined₆＝1/X₆(ii) a Working strength index X of seat₇The working strength index X of the sitting mat is needed as a reverse index₇The normalized processing and the normalization processing are carried out, and the seat working strength index y after the normalization processing can be determined by considering that the possible deviation of the working strength values of different seats is large₇＝1-X₇/X_7max，X_7maxMaximum value of agent working strength index representing service agent, e.g. X_7maxRepresenting the maximum value of the total active duration of the service agent during the time of day.

The indexes after the normalization process are described below in table 7.

TABLE 7

In some embodiments of the present application, the at least one index is standardized to obtain the at least one index after the standardization, wherein the value ranges of different indexes after the standardization are the same;

and determining a first weight of each index in the at least one index according to an entropy method based on the proportion of each index in the at least one index after the standardization treatment to each index after the standardization treatment.

Illustratively, the specific gravity of each index after the normalization process may be according to the following formula (1):

wherein, b_iIndicates the index y after the normalization process_iI is 1 to n.

Index information entropy of each index is calculated according to the following formula (2):

wherein e is_iIndicates the ith index X_iThe index information entropy of (1).

The information entropy redundancy (i.e., difference coefficient) of each index is calculated according to the following formula (3):

d_i＝1-e_i (3)

wherein d is_iIndicates the ith index X_iInformation entropy redundancy of (2).

The first weight of each index is calculated according to the following formula (4):

wherein, W_iIndicates the ith index X_iThe first weight of (1).

Then, a preset second weight of each index may be obtained, and in one example, the first weight and the second weight of each index may be illustrated by table 8.

TABLE 8

After the first weight and the second weight of each index are obtained, the score value of each service agent can be calculated according to the following formula (5):

wherein, f (S)_j) Represents the value of the credit for the jth service agent, j taking 1 to m.

After the score value of each service agent is determined, the service agent with the highest score value can be selected from the service agents to serve as a target service agent, and then the target service agent is distributed to the object to be served.

On the basis of the seat allocation method provided by the embodiment, the embodiment of the application also provides a seat allocation device; fig. 4 is a schematic diagram of an alternative configuration of an agent allocation apparatus according to an embodiment of the present application, and as shown in fig. 4, the agent allocation apparatus 400 may include:

an obtaining module 401, configured to obtain the number of objects to be served in the first queue;

a first processing module 402, configured to score a value of each object to be served in the first queue based on a value scoring model to obtain a value scoring result, when the number of the objects to be served is greater than or equal to a set threshold;

a second processing module 403, configured to reorder, based on the value scoring result, each object to be served in the first queue to obtain a ranking result;

an allocating module 404, configured to allocate a service agent to each object to be served based on the sorting result.

In some embodiments of the present application, the first processing module 402 is configured to score a value of each object to be served in the first queue based on a value scoring model, and obtaining a value scoring result includes:

In some embodiments of the present application, the first processing module 402 is configured to score a value of each object to be served in the first queue by using a value scoring model based on at least one attribute of each object to be served in the first queue, and obtaining a value scoring result includes:

In some embodiments of the present application, the allocating module 404 is configured to allocate a service agent to each object to be served based on the sorting result, and includes:

and distributing service seats to the objects to be served in the second queue.

In some embodiments of the present application, the allocating module 404 is configured to allocate a service agent to an object to be served in the second queue, and includes:

In some embodiments of the present application, the allocating module 404, configured to determine a target service agent allocated to an object to be served in the second queue, includes:

In some embodiments of the present application, the allocating module 404 is further configured to determine, according to at least one characteristic of the objects to be served in the second queue, an agent service capability index matched with the objects to be served in the second queue.

In some embodiments of the present application, the allocating module 404 is configured to determine a score value of each service agent according to at least one index, including:

In some embodiments of the present application, the assignment module 404 is further configured to:

In some embodiments of the present application, the allocating module 404, configured to determine the first weight of each of the at least one index according to the entropy method based on a specific gravity of each of the at least one index after the normalization process to each of the at least one index after the normalization process, includes:

In practical applications, the obtaining module 401, the first processing module 402, the second processing module 403, and the allocating module 404 may be implemented by a processor, and the processor may be at least one of an ASIC, a DSP, a DSPD, a PLD, an FPGA, a CPU, a controller, a microcontroller, and a microprocessor. It is understood that the electronic device implementing the above-described processor function may be other electronic devices, and the embodiments of the present application are not limited thereto.

It should be noted that the above description of the embodiment of the apparatus, similar to the above description of the embodiment of the method, has similar beneficial effects as the embodiment of the method. For technical details not disclosed in the embodiments of the apparatus of the present application, reference is made to the description of the embodiments of the method of the present application for understanding.

It should be noted that, in the embodiment of the present application, if the agent allocation method is implemented in the form of a software functional module and sold or used as a standalone product, the agent allocation method may also be stored in a computer-readable storage medium. Based on such understanding, the technical solutions of the embodiments of the present application may be essentially implemented or portions thereof contributing to the prior art may be embodied in the form of a software product stored in a storage medium, and including several instructions for causing a computer device (which may be a terminal, a server, etc.) to execute all or part of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read Only Memory (ROM), a magnetic disk, or an optical disk. Thus, embodiments of the present application are not limited to any specific combination of hardware and software.

Correspondingly, an embodiment of the present application further provides a computer program product, where the computer program product includes computer-executable instructions, and the computer-executable instructions are used to implement any one of the agent allocation methods provided in the embodiment of the present application.

Accordingly, an embodiment of the present application further provides a computer storage medium, where computer-executable instructions are stored on the computer storage medium, and the computer-executable instructions are used to implement any one of the agent allocation methods provided in the foregoing embodiments.

An embodiment of the present application further provides an electronic device, fig. 5 is an optional schematic structural diagram of the electronic device provided in the embodiment of the present application, and as shown in fig. 5, the electronic device 50 includes:

a memory 501 for storing executable instructions;

the processor 502 is configured to implement any one of the agent allocation methods described above when executing the executable instructions stored in the memory 501.

The processor 502 may be at least one of ASIC, DSP, DSPD, PLD, FPGA, CPU, controller, microcontroller, and microprocessor.

The computer-readable storage medium/Memory may be a Read Only Memory (ROM), a Programmable Read Only Memory (PROM), an Erasable Programmable Read Only Memory (EPROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a magnetic Random Access Memory (FRAM), a Flash Memory (Flash Memory), a magnetic surface Memory, an optical Disc, or a Compact Disc Read-Only Memory (CD-ROM), and the like; but may also be various terminals such as mobile phones, computers, tablet devices, personal digital assistants, etc., that include one or any combination of the above-mentioned memories.

Here, it should be noted that: the above description of the storage medium and device embodiments is similar to the description of the method embodiments above, with similar advantageous effects as the method embodiments. For technical details not disclosed in the embodiments of the storage medium and apparatus of the present application, reference is made to the description of the embodiments of the method of the present application for understanding.

It should be appreciated that reference throughout this specification to "some embodiments" means that a particular feature, structure, or characteristic described in connection with the embodiments is included in at least one embodiment of the present application. Thus, the appearances of the phrase "in some embodiments" appearing in various places throughout the specification are not necessarily all referring to the same embodiments. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. It should be understood that, in the various embodiments of the present application, the sequence numbers of the above-mentioned processes do not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application. The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments.

It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described device embodiments are merely illustrative, for example, the division of the unit is only a logical functional division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms.

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

In addition, all functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may be separately regarded as one unit, or two or more units may be integrated into one unit; the integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.

Alternatively, the integrated units described above in the present application may be stored in a computer-readable storage medium if they are implemented in the form of software functional modules and sold or used as independent products. Based on such understanding, the technical solutions of the embodiments of the present application may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing an automatic test line of a device to perform all or part of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a removable storage device, a ROM, a magnetic or optical disk, or other various media that can store program code.

The methods disclosed in the several method embodiments provided in the present application may be combined arbitrarily without conflict to obtain new method embodiments.

The features disclosed in the several method or apparatus embodiments provided in the present application may be combined arbitrarily, without conflict, to arrive at new method embodiments or apparatus embodiments.

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

Claims

1. A method of agent allocation, the method comprising:

acquiring the number of objects to be served in a first queue;

2. The method of claim 1, wherein the value scoring is performed on each object to be served in the first queue based on a value scoring model, and obtaining a value scoring result comprises:

3. The method of claim 2, wherein scoring a value of each object to be served in the first queue using a value scoring model based on at least one attribute of each object to be served in the first queue comprises:

4. The method according to claim 1, wherein said assigning service agents to the respective objects to be served based on the sorting result comprises:

and distributing service seats to the objects to be served in the second queue.

5. The method of claim 4, wherein the assigning a service agent to the object to be served in the second queue comprises:

6. The method of claim 5, wherein the determining the target service agent allocated to the object to be served in the second queue comprises:

7. The method of claim 6, further comprising:

8. The method of claim 6, wherein determining a score value for each service agent based on at least one indicator comprises:

9. The method of claim 8, wherein the weight parameter comprises: the first weight of each index in the at least one index is determined according to an entropy method, and/or the second weight of each index in the at least one index is a preset value.

10. The method of claim 9, further comprising:

11. The method according to claim 10, wherein the determining the first weight of each of the at least one index based on the weight of each of the at least one index after the normalization process to the respective index after the normalization process according to the entropy method comprises:

12. The method according to any of claims 6-11, wherein determining a score value for each service agent based on at least one indicator comprises:

13. An agent distribution device, characterized in that the device comprises:

14. An electronic device, characterized in that the electronic device comprises: a memory for storing executable instructions; a processor configured to implement the agent allocation method of any one of claims 1 to 12 when executing the executable instructions stored in the memory.

15. A computer-readable storage medium storing executable instructions for implementing the agent allocation method of any one of claims 1 to 12 when executed by a processor.