CN111738582A

CN111738582A - Bank outlet task dynamic allocation method, device and equipment based on community

Info

Publication number: CN111738582A
Application number: CN202010541628.8A
Authority: CN
Inventors: 岑昆; 李青; 张锴; 陈渝
Original assignee: Industrial and Commercial Bank of China Ltd ICBC
Current assignee: Industrial and Commercial Bank of China Ltd ICBC
Priority date: 2020-06-15
Filing date: 2020-06-15
Publication date: 2020-10-02
Anticipated expiration: 2040-06-15
Also published as: CN111738582B

Abstract

The invention provides a dynamic bank branch task allocation method, a device and equipment based on community, wherein the method comprises the following steps: predicting the task condition of each bank outlet according to the business data of each bank outlet; monitoring the current task condition to be processed of each bank outlet; dynamically allocating tasks to all personnel in the community in the corresponding community according to the predicted task condition of each bank branch in each community, the current task condition to be processed and the pre-acquired average consumed time for processing each task; wherein, a community includes a plurality of banking outlets, and personnel of each banking outlet belong to corresponding communities. The method has the advantages that a plurality of bank outlets form a community outlet, personnel of the community outlet are subjected to centralized dynamic allocation management, the outlets to which the personnel belong are dynamically adjusted and tasks are allocated according to the current task condition to be processed, the task prediction condition and the processing capacity of the bank outlets in a community, reasonable allocation of the personnel is achieved, and the operation management efficiency of the bank outlets is improved.

Description

Bank outlet task dynamic allocation method, device and equipment based on community

Technical Field

The invention relates to the technical field of artificial intelligence, in particular to a dynamic task allocation method, device and equipment for bank outlets based on community.

Background

The bank branch is a place where a bank is in business, and is generally divided into a branch, a branch treatment, a deposit station and the like, the bank branch usually adopts fixed configuration for a customer service manager, the customer service manager has strong membership with a physical bank branch, a bank system adopts a sign-in and sign-out processing mechanism for the customer service manager, the customer service manager signs in the bank system before working every day, the bank system records the current sign-in branch of the customer service manager, and after logging in, the customer service manager can only process the work tasks in the sign-in branch and cannot process the tasks of other branches across the branches.

However, the business volume of the bank outlets is dynamically changed, the tasks to be processed of different banks in different periods and different time periods are different, and the distribution mode of the existing customer service manager cannot effectively adapt to the situation of dynamic change of the business volume, so that the situation that the hands of a part of bank outlets are insufficient in a period with large business volume and the situation that the bank outlets are idle and waste manpower occurs in a period with small business volume is caused.

Disclosure of Invention

Aiming at the problems in the prior art, the invention provides a dynamic task allocation method, device and equipment for bank outlets based on community, which can at least partially solve the problems in the prior art.

In order to achieve the purpose, the invention adopts the following technical scheme:

in a first aspect, a dynamic banking outlet task allocation method based on community is provided, which includes:

predicting the task condition of each bank outlet according to the business data of each bank outlet;

monitoring the current task condition to be processed of each bank outlet;

dynamically allocating tasks to all personnel in the community in the corresponding community according to the predicted task condition of each bank branch in each community, the current task condition to be processed and the pre-acquired average consumed time for processing each task;

wherein, a community includes a plurality of banking outlets, and personnel of each banking outlet belong to corresponding communities.

Further, the dynamic banking outlet task allocation method based on the community further comprises the following steps:

dividing the bank outlets into a plurality of communities according to the characteristics of the bank outlets;

and modifying the personnel authority of the network points according to the community division result.

Further, the dividing of the bank outlets into a plurality of communities according to the characteristics thereof includes:

acquiring characteristic data of each bank outlet;

and clustering the characteristic data of each bank outlet by adopting a K-means clustering algorithm.

Further, the feature data includes: historical business data, business hours data, and location data.

Further, the task condition prediction according to the business data of each bank branch comprises the following steps:

acquiring service data of each bank outlet;

inputting the business data into a pre-trained LSTM neural network model for task prediction.

acquiring historical service data of each bank outlet;

and counting the historical service data to obtain the average consumed time for processing each task by the corresponding bank outlets.

Further, the dynamically allocating tasks to all the people in the community within the corresponding community according to the predicted task conditions of the banking outlets within the community, the current task conditions to be processed and the pre-acquired average consumed time for processing the tasks includes:

acquiring the time consumption required by the current task to be processed of the corresponding bank outlets according to the average time consumption of each task processed by each bank outlet in each community and the condition of the current task to be processed;

and dynamically allocating tasks to all the personnel in the community in the corresponding community according to the time consumption required by the current tasks to be processed of each bank branch and the predicted task conditions of each bank branch.

In a second aspect, a dynamic banking outlet task allocation device based on community is provided, which includes:

the prediction module predicts the task condition of each bank outlet according to the service data of each bank outlet;

the monitoring module is used for monitoring the current task condition to be processed of each bank outlet;

the dynamic allocation module is used for dynamically allocating tasks to all the personnel in the community in the corresponding community according to the predicted task condition of each bank branch in each community, the current task condition to be processed and the pre-acquired average consumed time for processing each task;

In a third aspect, an electronic device is provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the processor implements the steps of the above-mentioned dynamic assignment method for banking site tasks based on community.

In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the above-mentioned dynamic banking-site task allocation method based on community.

The invention provides a dynamic bank branch task allocation method, a device and equipment based on community, wherein the method comprises the following steps: predicting the task condition of each bank outlet according to the business data of each bank outlet; monitoring the current task condition to be processed of each bank outlet; dynamically allocating tasks to all personnel in the community in the corresponding community according to the predicted task condition of each bank branch in each community, the current task condition to be processed and the pre-acquired average consumed time for processing each task; wherein, a community includes a plurality of banking outlets, and personnel of each banking outlet belong to corresponding communities. By adopting the technical scheme, a plurality of bank outlets form a community outlet, personnel of the community outlet are subjected to centralized dynamic allocation management, the outlets to which the personnel belong are dynamically adjusted and the tasks are allocated according to the current task condition to be processed, the task prediction condition and the processing capacity of the bank outlets in the community, reasonable allocation of the personnel is realized, the operation management efficiency of the bank outlets is improved, the dynamic change condition of the business volume is effectively adapted, and the situation that the personnel is insufficient in the time period with large business volume and the manpower is idle and wasted in the time period with small business volume of the bank outlets is prevented.

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

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts. In the drawings:

FIG. 1 is a first schematic flowchart of a dynamic assignment method for banking outlets tasks based on a community in an embodiment of the present invention;

FIG. 2 illustrates a bank outlet community in an embodiment of the invention;

FIG. 3 is a schematic flow chart of a dynamic banking outlet task allocation method based on a community in an embodiment of the present invention;

FIG. 4 shows the detailed steps of step S400 in FIG. 3;

fig. 5 shows the specific steps of step S100 in fig. 1 or 3;

FIG. 6 is a third schematic flowchart of a dynamic banking outlet task allocation method based on a community in an embodiment of the present invention;

fig. 7 shows the specific steps of step S300 in fig. 1 or fig. 3 or fig. 6;

FIG. 8 is a structural diagram of a dynamic banking outlet task allocation system based on a community in an embodiment of the present invention;

fig. 9 is a schematic diagram of an internal structure of the community banking outlet partitioning module 1 in fig. 8;

fig. 10 is a schematic diagram of the internal structure of the network traffic statistics prediction module 2 in fig. 8;

fig. 11 is a schematic diagram of an internal structure of the pending transaction monitoring module 3 of the banking outlet in fig. 8;

FIG. 12 is a schematic diagram of the internal structure of the dynamic task allocation module 4 of the website customer service manager in FIG. 8;

FIG. 13 is a flowchart illustrating the operation of a dynamic banking outlet task allocation system based on a community in an embodiment of the present invention;

FIG. 14 shows traffic data for a banking outlet;

FIG. 15 shows a comparison of real traffic data at a banking outlet with predicted traffic data before model optimization;

FIG. 16 shows a comparison of real traffic data at a banking outlet with model-optimized predicted traffic data;

FIG. 17 is a block diagram of a dynamic banking outlet task allocation apparatus based on a community in an embodiment of the present invention;

fig. 18 is a block diagram of an electronic device according to an embodiment of the present invention.

Detailed Description

In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

It should be noted that the terms "comprises" and "comprising," and any variations thereof, in the description and claims of this application and the above-described drawings, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.

FIG. 1 is a first schematic flowchart of a dynamic assignment method for banking outlets tasks based on a community in an embodiment of the present invention; as shown in fig. 1, the dynamic assignment method for banking outlet tasks based on the community may include the following steps:

step S100: predicting the task condition of each bank outlet according to the business data of each bank outlet;

specifically, the business of banking outlets generally has a certain regularity, and the daily business fluctuation condition of each banking outlet has periodicity, such as: the business of holidays, the business of loan repayment days and the business of paying days of large customers at bank outlets, therefore, a certain regularity can be obtained according to historical business data, and then the task conditions of the next period, the next day, the next week and the like can be predicted according to the current business data.

Step S200: monitoring the current task condition to be processed of each bank outlet;

specifically, the current task condition to be processed of each bank outlet can be polled at regular time by setting a timer.

Step S300: dynamically allocating tasks to all personnel in the community in the corresponding community according to the predicted task condition of each bank branch in each community, the current task condition to be processed and the pre-acquired average consumed time for processing each task;

the community comprises a plurality of bank outlets, and the personnel of each bank outlet belongs to the corresponding community, as shown in fig. 2, the communities from the B001 to the B003 are G001, the communities from the B004 to the B007 are G002, at this time, the personnel from the B001 to the B003 are G001, and the communities from the B004 to the B007 are G002.

Specifically, all the personnel (such as business managers) of the banking nodes in the community are used as a pool, task allocation is carried out according to the current task situation to be processed of each banking node in the community and the predicted task situation in a future period of time, in addition, the processing speed (represented by average consumed time) of each banking node to each task needs to be combined when the tasks are allocated, and even the tasks can be accurately allocated according to the consumed time of the individual task processing.

It should be noted that, when allocating tasks, the method is not limited to the inside of banking outlets, and although personnel belongs to a specific physical outlet in terms of administrative management, when allocating tasks, the method breaks the outlet limit, and achieves flexible allocation of personnel by targeting community.

Through adopting above-mentioned technical scheme, carry out the community division to bank outlets, carry out the overall management to personnel (for example customer service manager) in with the community, according to pending traffic condition, the check-in site of dynamic adjustment site personnel, realize task dynamic allocation, accelerate task processing efficiency, in addition, through the mode of community management, realize bank outlet personnel's dynamic sharing, the place of physical bank site has been broken through, equipment, personnel's limitation, make full use of manpower resources, improve service quality, the problem that the customer ability who receives treatment daily that has avoided every bank outlet to be limited to the factor in the aspects such as place, equipment, station seat leads to is limited, task processing ability is limited.

In an optional embodiment, referring to fig. 3, the dynamic assignment method for banking outlet tasks based on the community may further include:

step S400: dividing the bank outlets into a plurality of communities according to the characteristics of the bank outlets;

specifically, the characteristics of the banking outlets may be geographical locations (for example, dividing a district into a community), service characteristics (for example, dividing a distribution point with more public services into a community, and then, for example, complementarily dividing a distribution point with more public services and a distribution point with less public services into a community), and the technical means used for the division may be various manners such as clustering and machine learning.

Step S500: and modifying the personnel authority of the network points according to the community division result.

Specifically, according to the division result, the personnel parameter authority is modified, so that the personnel belong to the community.

In a further embodiment, referring to fig. 4, this step S400 may include the following:

step S410: acquiring characteristic data of each bank outlet;

specifically, the feature data includes: historical business data, business hours data, location data, and the like.

Step S420: and clustering the characteristic data of each bank outlet by adopting a K-means clustering algorithm.

The K-means clustering algorithm is a vector quantization method from signal processing, and the purpose of K-means clustering is to divide n points into K clusters, so that each point belongs to a cluster corresponding to the nearest mean (namely a cluster center) to the point, and the cluster is used as a clustering standard.

By modeling the characteristics of the bank outlets, the bank outlets can be divided into bank outlet communities with specific similar characteristics (such as annual service type distribution, high coincidence of business hours, adjacent regions and the like) by using a K-means clustering algorithm.

It is worth noting that the K-means clustering algorithm can be called in Python.

In an alternative embodiment, referring to fig. 5, this step S100 may include the following:

step S110: acquiring service data of each bank outlet;

the business data can be workload flow data, holiday data, salary data and the like.

Step S120: and inputting the service data into a pre-trained LSTM neural network model for task prediction.

In a further embodiment, the dynamic assignment method for banking outlet tasks based on the community may further include the following steps:

step I: acquiring historical service data of a bank outlet;

step II: extracting characteristics according to historical service data to obtain historical characteristic data;

step IV: and taking the historical characteristic data as a training sample and a testing sample, training and testing the pre-established LSTM neural network model until the testing result meets the preset requirement, and obtaining the trained LSTM neural network model for the task prediction of the bank outlets.

The training process is as follows: inputting a training sample into a pre-established LSTM neural network model, comparing an output result of the LSTM neural network model with a label of the training sample, reversely adjusting parameters such as time step in the LSTM function, the number of neurons in a DENSE layer and a hidden layer and the like based on a comparison result, optimizing the function for multiple times, and realizing model training.

The test process comprises the following steps: inputting a test sample into the trained LSTM neural network model, comparing the label of the test sample with the output of the model, judging whether the label meets the preset requirement, if so, successfully training, and if not, optimizing the current model and/or applying the updated training sample set to perform model training again.

As can be understood by those skilled in the art, the dynamic assignment method for banking outlet tasks based on community can further include: and constructing the LSTM neural network model.

It is worth noting that the LSTM neural network model can be invoked directly in Python.

In an optional embodiment, referring to fig. 6, the dynamic assignment method for banking outlet tasks based on a community may further include:

step 600: acquiring historical service data of each bank outlet;

specifically, the historical service data includes service types, service processing time consumption, service processing website numbers and service processing personnel numbers.

Step 700: and counting the historical service data to obtain the average consumed time for processing each task by the corresponding bank outlets.

The average time consumption of the bank outlets for processing each task is obtained through a statistical method, and even the average time consumption of individuals for processing each task can be obtained.

It is worth noting that prior to processing the data, the historical traffic data may be preprocessed, such as filtering noise data, etc., to improve data accuracy.

In an alternative embodiment, referring to fig. 7, this step S300 may include the following:

step S310: acquiring the time consumption required by the current task to be processed of the corresponding bank outlets according to the average time consumption of each task processed by each bank outlet in each community and the condition of the current task to be processed;

step S320: and dynamically allocating tasks to all the personnel in the community in the corresponding community according to the time consumption required by the current tasks to be processed of each bank branch and the predicted task conditions of each bank branch.

For example, according to the current task situation data to be processed of each bank branch in the community and the average consumed time of each task, the expected total consumed time of processing the tasks to be processed of each branch (the number of the tasks to be processed) is calculated, and then, the average consumed time of the tasks to be processed of each branch is calculatedThe task waiting for processing is time-consuming for each website, and the formula is as follows:

finding out the network point (called A network point for short) with the longest time consumption of the per-person task to be processed, finding the network point (called B network point for short) with the least predicted task number and the least time consumption of the per-person task to be processed in the next period of the community, adjusting the current network point of the customer service staff of the network point, dynamically adjusting the network point of the customer service manager (called C for short) of the B network point to the A network point, namely dynamically distributing the tasks of the A network point to the B network point.

Of course, the above is merely an exemplary illustration, and the allocation manner may also be dynamically adjusted according to other manners, which is not limited in this embodiment of the present invention.

In order to make the present invention better understood by those skilled in the art, the following detailed description will be made by taking fig. 8 to fig. 13 as an example:

FIG. 8 is a structural diagram of a dynamic banking outlet task allocation system based on a community in an embodiment of the present invention; the dynamic bank outlet task allocation system based on the community mainly comprises the following working steps:

the method comprises the following steps: according to the characteristics of the bank outlets, the bank outlets are divided into a plurality of (bank outlet) communities, so that the community centralized management of the personnel at the outlets is realized.

Step two: and predicting the task condition of each time period in the day according to the historical task processing condition of each time period in each day of the banking outlets in the community, and counting the historical average time consumption condition of each service of the outlets.

Step three: and monitoring the condition of the tasks to be processed of the bank outlets in the community in real time.

Step four: and dynamically adjusting a customer service manager of the network point and distributing tasks according to the task condition to be processed of the bank network point in the community by combining task prediction of the network point in the next time period and historical average time consumption condition of each service of the network point.

Specifically, the dynamic banking outlet task allocation system based on the community may include: the system comprises a community bank outlet dividing module 1, a outlet traffic statistic and prediction module 2, a bank outlet pending business monitoring module 3 and a outlet customer service manager task dynamic allocation module 4.

Fig. 9 is a schematic diagram of an internal structure of the community banking outlet partitioning module 1 in fig. 8. As shown in fig. 9, the community banking outlet dividing module 1 includes: a community network point dividing unit 11 and a network point customer service manager authority setting unit 12.

The community bank outlets dividing unit 11 is used for carrying out community division on bank outlets to form different bank outlet communities.

The authority setting unit 12 of the customer service manager of the website is used for setting the home website of the customer service manager of the website, namely, the customer service manager of the website is assigned to the community customer service manager pool of the bank website by setting the website to which the customer service manager belongs.

Fig. 10 is a schematic diagram of the internal structure of the network traffic statistics prediction module 2 in fig. 8. As shown in fig. 10, the mesh point traffic statistics prediction module 2 includes: a node daily each time interval traffic statistic unit 21, a node daily each time interval traffic prediction unit 22 and a node each traffic average time consumption statistic unit 23.

The statistical unit 21 of the daily traffic of each time interval of the bank outlets is used for historically counting the traffic of each time interval of the bank outlets.

The service volume prediction unit 22 of each time interval of each day of the branch predicts the service volume of each time interval of each day of the future according to the service volume distribution condition of each time interval of the service volume of the bank branch.

The average consumed time counting unit 23 of each service of the network node counts the consumed time of the service processing of each service type, counts the average consumed time of each service type, and is used as a basis for dynamically adjusting the customer service manager task of the network node subsequently.

Fig. 11 is a schematic diagram of an internal structure of the pending transaction monitoring module 3 of the banking outlet in fig. 8. As shown in fig. 11, the pending transaction monitoring module 3 of the banking outlet includes: a node to-be-processed service timing query unit 31 and a node current to-be-processed task sending unit 32. Wherein:

the node to-be-processed service timing query unit 31 is a timing processing program, and the program can periodically and circularly query the current to-be-processed tasks of each node.

The website current to-be-processed task sending unit 32 is configured to send a website current to-be-processed task condition to the website customer service manager task dynamic allocation module 4.

FIG. 12 is a schematic diagram of the internal structure of the dynamic task allocation module 4 of the website customer service manager in FIG. 8; as shown in fig. 12, the intelligent scheduling apparatus 4 for a community banking outlet includes: a network customer service manager parameter adjusting unit 41 and a network customer service manager task distributing unit 42. Wherein:

the website customer service manager parameter adjusting unit 41 is used for dynamically adjusting the current working website parameter setting of the website customer service manager, so that the website customer service manager can process tasks among different websites in a bank website community.

The task allocation unit 42 of the customer service manager allocates the task to be processed of the current customer service manager in the current website to the customer service manager for processing.

Fig. 13 is an operation procedure of the dynamic banking outlet task allocation system based on the community in the embodiment of the present invention, where the operation procedure is as follows:

step S101: the banking outlets are subjected to community division so as to be divided into different outlet communities, and the community division unit 11 performs the community division. The system collects and counts the characteristics of the bank outlets such as the traffic, the business hours, the regions and the like.

For example:

the method is characterized in that: the 2019 year traffic statistics of the banking outlets are shown in table 1:

TABLE 1

And (2) feature: business hours, as shown in table 2:

TABLE 2

And (3) feature: the area, as shown in table 3:

TABLE 3

By modeling the characteristics of the bank outlets and using a K-means clustering algorithm, the bank outlets can be divided into bank outlet communities with specific similar characteristics (such as annual service type distribution, high coincidence of business hours, adjacent regions and the like). The classification results are shown in fig. 2.

Through system classification, the community allocation results of each bank branch are shown in table 4:

TABLE 4

Bank branch	Community of bank outlets
		B001 mesh point	G001 dot community
B002 mesh point	G001 dot community
		B003 mesh point	G001 dot community
B004 dot	G002 dot community
		B005 net point	G002 dot community
......	......

Step S102: the parameters of the customer service manager of the bank network are set and executed by the parameter setting unit 12 of the customer service manager of the bank network, and the parameter setting result is shown in table 5:

TABLE 5

Customer service manager	Network site to which personnel belong
		T001	B001 mesh point
T002	B002 mesh point
		T003	B002 mesh point
T004	B003 mesh point
		T005	B003 mesh point
T006	B003 mesh point
		......	......

Step S201: counting the historical daily traffic of each time interval of a network point;

specifically, the method collects the traffic (history) data of each time period of each day of the banking outlet, and uses the data as the traffic prediction basis of each time period of the banking outlet in the future. Such as: the results of the historical traffic data collected by the B001 mesh point are shown in table 6:

TABLE 6

Step S202: predicting the historical daily traffic of the network nodes in each time interval; is executed by the traffic prediction unit 22 at each time of day.

According to the business volume (history) data of each time period of each day of the banking outlet, the business volume of each time period of each day in the future of the banking outlet is predicted by a machine learning method. The business prediction needs to establish a prediction analysis mathematical model for prediction, and mainly comprises the following steps:

1) collecting sample data and processing: date information in the collected data is processed to obtain time distribution characteristics of different time periods (by hours). Through trend analysis of the time distribution characteristics respectively, the daily traffic fluctuation situation of each network point has periodicity, which is shown in fig. 14.

Due to the fact that the range of the traffic is too large, in order to avoid the problem that machine learning cannot be converged due to the occurrence of abnormal data, the machine learning speed is increased, and the result data needs to be processed by using a normalization function.

2) Establishing a model: as can be seen from the data processing in the step 1, the data has periodicity, is dependent on the sequence of time occurrence, belongs to the problem of time sequence, and meanwhile, the traffic volume in each time period of each day is not very stable, so that the LSTM neural network model is selected, and the prediction can be carried out without carrying out multiple smooth processing on the data.

The data are loaded first, and by setting a time point, the data before the time point are divided into a training set train ═ df.loc [: time ] and a data division test set test ═ df.loc [ time: ] after the time point. Next, calling a function train predict (LSTM _ MODEL) to perform model training, and a comparison graph of a real value and a predicted value under a test set is shown in fig. 15, so that a deviation ratio between a predicted result and the real value is large, at this time, the function is optimized for multiple times by adjusting parameters such as time steps in the LSTM function, the number of neurons in a DENSE layer and a hidden layer until an experimental result reaches a better value shown in fig. 16, and finally, the result is adjusted to normal traffic data through an inverse normalization function.

3) And (3) predicting: if the traffic of a certain network point in T month needs to be predicted, the data files from the network point in T-13 month to T-1 month are used as the training data of the model to be input, the date file of the T month is used as the test set of the model to be input, and the output is the daily traffic of the network point in T month. The output results are shown in table 7:

TABLE 7

Step S203: and counting the average time consumption of each service of the network points. Is executed by the average time consumption statistical unit 23 of each service of the network point.

The average processing time of each service is calculated by summarizing and counting the time consumed by the historical service processing of each network point, and the average processing time is used as a basis for the dynamic allocation of a subsequent customer manager. The average time consumption of each service is shown in table 8:

TABLE 8

Step S301: and inquiring the current tasks to be processed of each bank outlet. Is executed by the node pending service timing query unit 21.

The current task condition to be processed of each bank outlet is inquired by setting a timer.

Step S302: and sending the current task to be processed of the bank outlet. Is executed by the current task sending unit 22 of the mesh point.

Specifically, the current task condition data to be processed of the network is sent to a network customer service manager task dynamic allocation module for task allocation processing. The current task situation of the B001 mesh point to be processed is shown in table 9:

TABLE 9

Step S401: calculating the total time consumption of the estimated processing of the tasks to be processed of each network point;

according to the data of the current tasks to be processed of each bank branch in the community, the estimated total processing time (the number of the tasks to be processed) × the average task time) of the tasks to be processed of each branch is calculated, and the calculation result of the B001 branch is shown in table 10:

watch 10

Step S402: finding out the network points with the longest time consumption of the per-person task to be processed;

calculating the time consumption of the task to be processed of each website, wherein the formula is as follows:

find out the network point (hereinafter referred to as the "A" network point, for example, the B002 network point in Table 11) that takes the longest time for the per-capita task.

TABLE 11

Step S403: searching a network point which predicts the number of tasks in the next time period and consumes the least time for the tasks to be processed by people;

specifically, the mesh point (hereinafter referred to as the B003 mesh point in table 12) in which the predicted task number (prediction from step S202) in the next period within the community is the smallest and the task time consumed by everyone is the smallest is searched.

TABLE 12

Step S404: adjusting system parameters, and adjusting a customer service manager C of the A site to be a B site person;

specifically, the current check-in point of the customer service manager of the website is adjusted, and the check-in point of a customer service manager (hereinafter referred to as C, for example, T012 in table 13) of the website B is dynamically adjusted to the website a.

Watch 13

Customer service manager	Check-in net point
		T002	B003 mesh point
T003	B003 mesh point
		T010	B003 mesh point
T011	B003 mesh point
		T012	B003 mesh point
......	......

The adjusted results are shown in table 14:

TABLE 14

Customer service manager	Check-in net point
		T002	B003 mesh point
T003	B003 mesh point
		T010	B003 mesh point
T011	B003 mesh point
		T012	B001 mesh point
......	......

Step S405: and distributing the tasks to a customer service manager C from the A site. The process returns to S401 to continue the processing.

Based on the same inventive concept, the embodiment of the present application further provides a dynamic banking outlet task allocation device based on the community, which can be used for implementing the method described in the foregoing embodiment, as described in the following embodiment. Because the principle of solving the problems of the dynamic bank branch task allocation device based on the community is similar to that of the method, the implementation of the dynamic bank branch task allocation device based on the community can refer to the implementation of the method, and repeated parts are not described again. As used hereinafter, the term "unit" or "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.

Fig. 17 is a first structural block diagram of a dynamic banking outlet task allocation device based on a community in an embodiment of the present invention. As shown in fig. 17, the dynamic banking outlet task allocation device based on the community specifically includes: a prediction module 10, a monitoring module 20, and a dynamic allocation module 30.

The prediction module 10 predicts the task condition according to the business data of each bank outlet;

the monitoring module 20 monitors the current task condition to be processed of each bank outlet;

the dynamic allocation module 30 dynamically allocates tasks to all the persons in the community within the corresponding community according to the predicted task conditions of each bank branch in each community, the current task conditions to be processed and the pre-acquired average consumed time for processing each task;

The apparatuses, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or implemented by a product with certain functions. A typical implementation device is an electronic device, which may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

In a typical example, the electronic device specifically includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the processor implements the steps of the dynamic assignment method based on the clustered banking site task.

Referring now to FIG. 18, shown is a schematic diagram of an electronic device 600 suitable for use in implementing embodiments of the present application.

As shown in fig. 18, the electronic apparatus 600 includes a Central Processing Unit (CPU)601 that can perform various appropriate works and processes according to a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage section 608 into a Random Access Memory (RAM)) 603. In the RAM603, various programs and data necessary for the operation of the system 600 are also stored. The CPU601, ROM602, and RAM603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.

The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, a mouse, and the like; an output portion 607 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The driver 610 is also connected to the I/O interface 605 as needed. A removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 610 as necessary, so that a computer program read out therefrom is mounted as necessary on the storage section 608.

In particular, according to an embodiment of the present invention, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, an embodiment of the present invention includes a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps of the above-mentioned dynamic assignment method for tasks based on a clustered banking outlet.

In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 609, and/or installed from the removable medium 611.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functionality of the units may be implemented in one or more software and/or hardware when implementing the present application.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

It should also be noted that 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.

As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

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

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

The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A dynamic bank outlet task allocation method based on community is characterized by comprising the following steps:

monitoring the current task condition to be processed of each bank outlet;

2. The dynamic banking outlet task allocation method based on community-based according to claim 1, further comprising:

3. The dynamic banking outlet task allocation method based on community according to claim 2, wherein the dividing of banking outlets into a plurality of communities according to their characteristics comprises:

acquiring characteristic data of each bank outlet;

4. The dynamic banking outlet task allocation method based on community-based according to claim 3, wherein the characteristic data includes: historical business data, business hours data, and location data.

5. The dynamic banking branch task allocation method based on community according to claim 1, wherein the step of predicting the task situation of each banking branch according to the business data of each banking branch comprises:

acquiring service data of each bank outlet;

and inputting the service data into a pre-trained LSTM neural network model for task prediction.

6. The dynamic banking outlet task allocation method based on community-based according to claim 1, further comprising:

acquiring historical service data of each bank outlet;

7. The dynamic banking branch task allocation method based on community according to claim 1, wherein the dynamic allocation of tasks to all people in a community within a corresponding community according to the predicted task conditions of banking branches within each community, the current task conditions to be processed, and the pre-obtained average consumed time for processing each task comprises:

8. The utility model provides a dynamic allocation device of bank outlet task based on community ization which characterized in that includes:

9. An electronic device comprising a memory, a processor and a computer program stored on the memory and operable on the processor, wherein the processor implements the steps of the dynamic assignment method for tasks based on a clustered banking site according to any one of claims 1 to 7 when executing the program.

10. A computer-readable storage medium, on which a computer program is stored, wherein the computer program, when being executed by a processor, implements the steps of the dynamic assignment method for tasks based on a clustered banking outlet according to any one of claims 1 to 7.