CN115760329A - Bank outlet customer distribution method and system based on deep learning - Google Patents
Bank outlet customer distribution method and system based on deep learning Download PDFInfo
- Publication number
- CN115760329A CN115760329A CN202211239194.1A CN202211239194A CN115760329A CN 115760329 A CN115760329 A CN 115760329A CN 202211239194 A CN202211239194 A CN 202211239194A CN 115760329 A CN115760329 A CN 115760329A
- Authority
- CN
- China
- Prior art keywords
- user
- reservation
- deep learning
- model
- historical
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention discloses a bank outlet customer distribution method and system based on deep learning, and relates to the technical field of artificial intelligence, wherein the method comprises the following steps: the client side recommends reservation time for a user according to the service type of a reservation network point selected by the user, the current reservation condition corresponding to the service type and historical data of the service type handled by the user at the reservation network point; receiving the actual appointment time of the user to the service type according to the recommended appointment time; the client distribution server acquires the current user characteristics when receiving the sign-in operation of the user reaching the reservation website at the actual reservation time; determining a window with the least waiting time for the current user to transact the business according to the current user characteristics and a pre-trained user flow distribution model; the user features include: attribute characteristics of the user and characteristics of historical service handling of the user. The invention can efficiently shunt the bank outlets based on deep learning, thereby improving the user experience.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a bank outlet customer distribution method and system based on deep learning.
Background
This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.
At present, when a customer transacts business to a bank, the customer firstly needs to arrive at a network site, then gets a number through a queuing machine at the door and waits in a queuing way, when the flow of people is large, shunting personnel can not complete specific shunting work, so that the waiting time of partial personnel is long, in addition, the customer can not predict the current of people at the network site in the day in advance, the time of the customer is further wasted, and therefore unfriendly business transaction experience is brought to the customer. At present, friendly service experience can be praised by customers, and more customers can be obtained at the same time, so that how to save time of the customers on the whole process of handling business is an important problem.
Disclosure of Invention
The embodiment of the invention provides a banking outlet customer distribution method based on deep learning, which is used for efficiently distributing banking outlet customers based on deep learning and comprises the following steps:
the client side recommends reservation time for a user according to the service type of a reservation network point selected by the user, the current reservation condition corresponding to the service type and historical data of the service type handled by the user at the reservation network point; receiving the actual appointment time of the user to the service type according to the recommended appointment time;
when receiving the sign-in operation of the user at the actual reservation time to a reservation website, the client flow distribution server acquires the current user characteristics; determining a window with the least waiting time for the current user to transact the business according to the current user characteristics and a pre-trained user flow distribution model; the user features include: attribute characteristics of the user and characteristics of historical service handling of the user.
The embodiment of the invention also provides a system for shunting customers at banking outlets based on deep learning, which is used for efficiently shunting the customers at the banking outlets based on the deep learning and comprises the following components:
the client is used for recommending the appointment time for the user according to the service type of the appointment website selected by the user, the current appointment condition corresponding to the service type and historical data of the service type transacted by the user at the appointment website; receiving the actual appointment time of the user to the service type according to the recommended appointment time;
the client distribution server is used for acquiring the current user characteristics when receiving the sign-in operation of the user reaching the reservation website at the actual reservation time; determining a window with the least waiting time for the current user to transact the business according to the current user characteristics and a pre-trained user flow distribution model; the user features include: attribute characteristics of the user and historical service handling characteristics of the user.
The embodiment of the invention also provides computer equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the computer program to realize the deep learning-based banking outlet customer distribution method.
The embodiment of the invention also provides a computer readable storage medium, wherein a computer program is stored in the computer readable storage medium, and when the computer program is executed by a processor, the method for banking outlet customer distribution based on deep learning is realized.
The embodiment of the invention also provides a computer program product, which comprises a computer program, and when the computer program is executed by a processor, the method for banking outlet customer distribution based on deep learning is realized.
The embodiment of the invention provides a banking outlet customer distribution scheme based on deep learning, which comprises the following steps: the client side recommends reservation time for a user according to the service type of a reservation network point selected by the user, the current reservation condition corresponding to the service type and historical data of the service type handled by the user at the reservation network point; receiving the actual appointment time of the user to the service type according to the recommended appointment time; the client distribution server acquires the current user characteristics when receiving the sign-in operation of the user reaching the reservation website at the actual reservation time; determining a window with the least waiting time for the current user to handle the service according to the current user characteristics and a pre-trained user flow distribution model; the user features include: according to the scheme, the customers of the bank outlets can be effectively shunted based on deep learning, and the user experience is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts. In the drawings:
FIG. 1 is a schematic flow chart of a deep learning-based banking outlet customer distribution method in an embodiment of the present invention;
fig. 2 is a schematic diagram of a principle of banking outlet customer distribution based on deep learning in an embodiment of the present invention;
FIG. 3 is a schematic diagram of a user offload model in an embodiment of the present invention;
FIG. 4 is a schematic overall flow chart of banking outlet customer distribution based on deep learning in the embodiment of the present invention;
fig. 5 is a schematic structural diagram of a system for banking outlet customer distribution based on deep learning in an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention.
According to the technical scheme, the data acquisition, storage, use, processing and the like meet relevant regulations of national laws and regulations.
The term "and/or" herein merely describes an associative relationship, meaning that three relationships may exist, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the term "at least one" herein means any one of a plurality or any combination of at least two of a plurality, for example, including at least one of a, B, and C, and may mean including any one or more elements selected from the group consisting of a, B, and C.
In the description of the present specification, the terms "comprising," "including," "having," "containing," and the like are used in an open-ended fashion, i.e., to mean including but not limited to. Reference to the description of the terms "one embodiment," "a particular embodiment," "some embodiments," "for example," etc., means that a particular feature, structure, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. The sequence of steps involved in the embodiments is for illustrative purposes to illustrate the implementation of the present application, and the sequence of steps is not limited and can be adjusted as needed.
At present, a client usually needs to wait for longer time to transact business to a bank website, especially for special business of some websites and business which can be transacted only in some websites, so that the problem of poor experience is brought to the client, and the loss of the client can be caused when the problem appears for many times.
In order to alleviate the situations, most network sites are provided with queuing machines, the problem is solved by queuing numbers when a client arrives at a site, when the user gets the numbers, the user can select the service to be handled, and different number plates are fetched according to different service categories, but in the actual service handling process, window classification is not performed according to the service types, so that category pairing is failed, and the queuing operation is performed in the sequence of arriving at the site. When the traffic is large, the down manager can inquire the people and shunt the people manually.
In order to solve the problem that time is wasted when a customer transacts business queuing, the embodiment of the invention provides a deep learning-based customer distribution scheme of a bank outlet, and the customer cannot make an appointment in advance when transacting business on site, so that the business peak can not be effectively avoided; after a client arrives at a site, although a serial number is selected and printed on a queuing machine at a doorway to wait for business handling, different businesses are not distinguished in the actual business handling process, and the client can only carry out the serial number ordering in sequence; some customer business demands are simple in practice, can handle at modes such as self-service machine and intelligent sales counter, lead to customer experience poor, in order to further improve user's waiting problem, under the prerequisite of user's reservation, can obtain detailed business window information of handling through signing in when the user arrives the website, the system can be with heterogeneous business evenly distributed, and furthest's reduction user's latency promotes user experience. The following describes the scheme of customer distribution of banking outlets based on deep learning in detail.
Fig. 1 is a schematic flowchart of a method for banking outlet customer diversion based on deep learning in an embodiment of the present invention, and as shown in fig. 1, the method includes the following steps:
step 101: the client side recommends the reservation time for the user according to the service type of the reservation network selected by the user, the current reservation condition corresponding to the service type and the historical data of the service type handled by the user at the reservation network; receiving the actual appointment time of the user to the service type according to the recommended appointment time;
step 102: when receiving the sign-in operation of the user at the actual reservation time to a reservation website, the client flow distribution server acquires the current user characteristics; determining a window with the least waiting time for the current user to transact the business according to the current user characteristics and a pre-trained user flow distribution model; the user features include: attribute characteristics of the user and historical service handling characteristics of the user.
The bank branch client shunting method based on deep learning provided by the embodiment of the invention works as follows: the client side recommends the reservation time for the user according to the service type of the reservation network selected by the user, the current reservation condition corresponding to the service type and the historical data of the service type handled by the user at the reservation network; receiving the actual appointment time of the user to the service type according to the recommended appointment time; the client distribution server acquires the current user characteristics when receiving the sign-in operation of the user reaching the reservation website at the actual reservation time; determining a window with the least waiting time for the current user to handle the service according to the current user characteristics and a pre-trained user flow distribution model; the user features include: the method can efficiently shunt the clients of the bank outlets based on deep learning, and improves the user experience.
In one implementation, the method for banking outlet customer diversion based on deep learning may further include pre-constructing the user diversion model according to the following method:
acquiring a plurality of user information of bank outlets and historical business transaction information of users;
extracting historical user attribute characteristic information and historical transaction characteristic information from the plurality of user information and the historical service transaction information of the user, and creating a data set;
and building a deep learning model, and training the deep learning model by using the created data set to obtain the user flow distribution model.
In specific implementation, the step of constructing the user flow distribution model further improves the accuracy of model prediction.
In an embodiment, the method for banking outlet customer diversion based on deep learning may further include: and after a preset time period, re-establishing a data set to train the user shunting model to obtain an updated user shunting model.
When the method is specifically implemented, the model needs to be retrained after the life style and the behavior habit of people are changed along with the lapse of time, so that the prediction accuracy of the model is further improved.
In one embodiment, the user offload model may be a Bi-LSTM and CNN model.
In specific implementation, the user flow distribution model can be a Bi-LSTM model and a CNN model, and the prediction accuracy of the models can be further improved.
To facilitate an understanding of how the present invention may be practiced, reference is now made in detail to fig. 2-4.
In the embodiment of the invention, service personnel card out all current service detailed types and input the detailed types into the system and configure a window or a machine (a client shunting server) of a current network point for handling the current service; further utilizing a deep learning model to learn the characteristics of business handling of historical clients to form a classification model (user shunting model); the method comprises the steps of setting up a system to provide online reservation service, making service reservation before a client reaches a website, signing in by using a tangible medium or other certificates capable of proving identity after the client reaches the site, analyzing user behavior characteristics (transaction types, about stay time and the like) by using a classification model to perform classification judgment, distributing transaction windows for the client, and reducing the waiting time of the client.
As shown in fig. 2, the implementation process of the embodiment of the present invention is as follows:
1. a set of service reservation system is developed, which comprises a service input module, a client reservation module, a reservation condition checking module and a reservation time recommending module, so that the user can know the reservation condition of the current day and make advance reservation before going to a website, and a general direction is provided for the user to arrange the self travel.
2. The method comprises the steps of obtaining client information and historical service handling information, extracting main characteristics such as sex and age of a user, service types supported by website history, handling duration of various services, bearing capacity of each window and the like, and creating a data set (the information is made into a vector, word2vec is used for text, and normalization operation is used for numbers).
3. And (3) building a deep learning model, and training the model by using the data set created in the step 2 to obtain a classification model for completing automatic customer distribution according to the current time field and the historical information of the customer.
4. And embedding the existing model into a queuing machine or other queuing systems for specific application.
5. And after a period of time, performing 2-4 steps again to meet the needs of people for psychological and social changes.
In order to implement the above steps, the embodiment of the present invention may include two modules: a service subscription module and a client offloading module, see fig. 2 in detail.
(1) In the service reservation module, a service input sub-module is required to be developed so that service personnel can conveniently comb all services which can be handled by the website and input the services into a reservation system; the customer reservation submodule can be embedded into channels such as a mobile phone bank, and a user enters the reservation module and can select a business line required to be transacted by himself, and the user is guided to enter specific services required to be transacted layer by layer (the business line is a tree structure diagram of banking services, such as a first class of a deposit part, a customer information part, a bank card part and the like, which is a first layer; after entering a specific service, the system can inquire the current reservation condition, and meanwhile, the system can recommend the time according to the historical service data, such as the age of the user and the current network point condition (firstly, one reservation condition of the current network point service and the time point when the historical non-reservation personnel reach the service, the two are combined to screen out the idle time, secondly, the system carries out the recommendation by combining one historical service time preference of the current user), and finally, the user carries out the service reservation by combining the self condition.
(2) The client distribution module is the core of the invention, firstly, the automatic distribution algorithm is adopted in the module, the automatic distribution algorithm adopts a deep learning method, a classification model is constructed, and the model carries out specific business and specific handling window distribution according to the characteristics of a user so as to achieve the distribution purpose. The constructed classification model is specifically shown in fig. 3:
firstly, a large amount of customer information and historical business transaction information of customers are prepared, user characteristics (the sex and the age of the user, the business types supported by the site history, the transaction duration of various businesses, the bearing capacity of each window and other information) are constructed by combining the business flow of the current site, a data set is created (the information is made into a vector, a word2vec is used as a text, and a normalization operation is used as a number)), meanwhile, the characteristic data of the current user is marked, and the result is marked as a certain transaction window of the site (data which is manually optimized according to time information). The user characteristics are sequentially input into Bi-LSTM and CNN models, abstract characteristics of the user are extracted, finally, a classifier is used for obtaining a window in which the user handles the business, the window is compared with standard data, parameters in the models are optimized through a gradient descent algorithm, and finally a group of classification models with the best parameters can be obtained (the model is input by the user characteristics such as age, gender, name and the like, the business characteristics such as cards, debit cards and the like, and the output is a window with the least time).
After the classification model is obtained, the classification model is integrated into a queuing machine and other systems, when a client arrives at the site, the client signs in through a personal certificate, an automatic shunting algorithm module is activated to predict a current user, and a window with the minimum waiting time for the current user to handle the service is obtained, so that the problem of long queuing time of the user is solved, and the user experience is improved.
Split example: for example, if a user wants to transact a financial transaction, he inputs some features of himself and the features of the current window, and automatically calculates a window which is suitable for him, and the window can transact the financial transaction faster or is good at financial transaction and has less queuing time compared with other windows (for example, if the window is directly allocated to a salesman who does not know financial transaction, the transaction process may not queue up the window of the salesman who is familiar with financial transaction, which is also the purpose of automatic distribution by an algorithm).
For a better understanding of the embodiments of the present invention, reference is now made in its entirety to FIG. 4.
1. Preparing a large amount of customer information and historical business transaction information of customers, constructing user characteristics by combining the business flow of the current network, marking the characteristic data of the current user, and inputting the characteristic data into the model for training to obtain the shunting model.
2. The business personnel comb the business flow which can be handled by the current network point and input the business flow into the reservation system module;
3. the client enters the reservation system through channels such as a mobile phone bank and the like, enters a reservation page of a specific service according to the guidance of the service flow, and performs online reservation according to the recommended time of the system and the time of the client.
4. And the customer signs in after arriving at the network according to the reserved time.
5. And after the sign-in is completed, activating a shunting algorithm to calculate the currently optimal service queuing transaction scheme for the current client, and finally informing the user of waiting at a specific window according to a specific window result.
The bank branch customer distribution method based on deep learning provided by the embodiment of the invention can realize that:
1. through a specific service flow input system, specific service handling can be reserved in the reservation system instead of the large class of service, so that staff at bank outlets can conveniently know the working condition, and meanwhile, the waiting time of clients is saved.
2. Through an automatic shunting algorithm, the problem that the current queuing machine cannot distribute specific windows can be solved, and the aim of shunting is fulfilled.
To sum up, the embodiment of the invention provides a client automatic shunting method and a device based on deep learning aiming at the problems that the current client can not make advance reservation for transacting business to a website and the queuing time is long after the client arrives at the website, the device can complete business transacting reservation before the user arrives at the website, the time can be controlled in a certain range through the reserved user, and the subsequent work of the user can be better arranged; after the terminal further arrives at a network point, a window for transacting the business can be intelligently provided, and the sequencing is not performed in all the sequence numbers, so that the time of the user is further saved, and the user experience is improved.
By implementing the bank outlet customer distribution method based on deep learning in the embodiment of the invention, automatic customer distribution can be realized: after the client arrives at the network site, the client performs sign-in operation and gives a window or a machine for transacting specific services, and the client only needs to queue at the current machine without queuing on the whole link, so that the working efficiency is improved.
The embodiment of the invention also provides a deep learning-based system for banking outlet customer distribution, which is described in the following embodiment. Because the principle of solving the problems of the system is similar to the method for banking outlet customer distribution based on deep learning, the implementation of the system can refer to the implementation of the method for banking outlet customer distribution based on deep learning, and repeated parts are not described again.
Fig. 5 is a schematic structural diagram of a deep learning-based banking outlet customer diversion system in an embodiment of the present invention, and as shown in fig. 5, the system includes:
the client 01 is used for recommending reservation time for a user according to the service type of a reservation network point selected by the user, the current reservation condition corresponding to the service type and historical data of the service type handled by the user at the reservation network point; receiving the actual appointment time of the user to the service type according to the recommended appointment time;
the client distribution server 02 is used for acquiring the characteristics of the current user when receiving the sign-in operation of the user reaching the reservation website at the actual reservation time; determining a window with the least waiting time for the current user to transact the business according to the current user characteristics and a pre-trained user flow distribution model; the user features include: attribute characteristics of the user and historical service handling characteristics of the user.
In an embodiment, the system for banking outlet customer diversion based on deep learning may further include an establishing unit, configured to pre-construct the user diversion model according to the following method:
acquiring a plurality of user information of bank outlets and historical business transaction information of users;
extracting historical user attribute characteristic information and historical transaction characteristic information from the plurality of user information and the historical service transaction information of the user, and creating a data set;
and building a deep learning model, and training the deep learning model by using the created data set to obtain the user flow distribution model.
In one embodiment, the system for banking outlet customer diversion based on deep learning further includes: and the updating unit is used for recreating the data set to train the user shunting model after a preset time period to obtain an updated user shunting model.
In one embodiment, the user traffic model is a Bi-LSTM and CNN model.
The embodiment of the invention also provides computer equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the computer program to realize the deep learning-based banking outlet customer distribution method.
The embodiment of the invention also provides a computer readable storage medium, wherein a computer program is stored in the computer readable storage medium, and when the computer program is executed by a processor, the method for banking outlet customer distribution based on deep learning is realized.
The embodiment of the invention also provides a computer program product, which comprises a computer program, and when the computer program is executed by a processor, the method for banking outlet customer distribution based on deep learning is realized.
The banking outlet customer distribution scheme based on deep learning provided by the embodiment of the invention comprises the following steps: the client side recommends reservation time for a user according to the service type of a reservation network point selected by the user, the current reservation condition corresponding to the service type and historical data of the service type handled by the user at the reservation network point; receiving the actual appointment time of the user to the service type according to the recommended appointment time; the client distribution server acquires the current user characteristics when receiving the sign-in operation of the user reaching the reservation website at the actual reservation time; determining a window with the least waiting time for the current user to handle the service according to the current user characteristics and a pre-trained user flow distribution model; the user features include: according to the scheme, the customers of the bank outlets can be effectively shunted based on deep learning, and the user experience is improved.
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.
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.
The above-mentioned embodiments are provided to further explain the objects, technical solutions and advantages of the present invention in detail, and it should be understood that the above-mentioned embodiments are only examples of the present invention and should not be used to limit the scope of the present invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (11)
1. A banking outlet customer distribution method based on deep learning is characterized by comprising the following steps:
the client side recommends the reservation time for the user according to the service type of the reservation network selected by the user, the current reservation condition corresponding to the service type and the historical data of the service type handled by the user at the reservation network; receiving the actual appointment time of the user to the service type according to the recommended appointment time;
the client distribution server acquires the current user characteristics when receiving the sign-in operation of the user reaching the reservation website at the actual reservation time; determining a window with the least waiting time for the current user to handle the service according to the current user characteristics and a pre-trained user flow distribution model; the user features include: attribute characteristics of the user and historical service handling characteristics of the user.
2. The deep learning-based banking outlet customer diversion method according to claim 1, further comprising pre-constructing the user diversion model according to the following method:
acquiring a plurality of user information of banking outlets and historical business transaction information of the users;
extracting historical user attribute characteristic information and historical transaction characteristic information from the plurality of user information and the historical service transaction information of the user, and creating a data set;
and building a deep learning model, and training the deep learning model by using the created data set to obtain the user flow distribution model.
3. The deep learning-based banking site customer diversion method as claimed in claim 1, further comprising: and after a preset time period, re-establishing a data set to train the user flow distribution model to obtain an updated user flow distribution model.
4. The deep learning-based banking outlet customer diversion method according to claim 1, wherein the customer diversion model is a Bi-LSTM and CNN model.
5. A system for banking outlet customer diversion based on deep learning, comprising:
the system comprises a client, a system and a server, wherein the client is used for recommending reservation time for a user according to the service type of a reservation network point selected by the user, the current reservation condition corresponding to the service type and historical data of the service type handled by the user at the reservation network point; receiving the actual appointment time of the user to the service type according to the recommended appointment time;
the client distribution server is used for acquiring the current user characteristics when receiving the sign-in operation of the user reaching the reservation website at the actual reservation time; determining a window with the least waiting time for the current user to handle the service according to the current user characteristics and a pre-trained user flow distribution model; the user features include: attribute characteristics of the user and characteristics of historical service handling of the user.
6. The deep learning-based banking outlet customer diversion system as claimed in claim 5, further comprising a building unit for pre-building the user diversion model according to the following method:
acquiring a plurality of user information of banking outlets and historical business transaction information of the users;
extracting historical user attribute characteristic information and historical transaction characteristic information from the plurality of user information and the historical service transaction information of the user, and creating a data set;
and building a deep learning model, and training the deep learning model by using the created data set to obtain the user flow distribution model.
7. The deep learning-based banking outlet customer diversion system according to claim 5, further comprising an updating unit for recreating a data set to train the user diversion model after a preset time period, resulting in an updated user diversion model.
8. The deep learning-based banking outlet customer diversion system as claimed in claim 5, wherein said customer diversion models are Bi-LSTM and CNN models.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any one of claims 1 to 4 when executing the computer program.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed by a processor, implements the method of any of claims 1 to 4.
11. A computer program product, characterized in that the computer program product comprises a computer program which, when being executed by a processor, carries out the method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211239194.1A CN115760329A (en) | 2022-10-11 | 2022-10-11 | Bank outlet customer distribution method and system based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211239194.1A CN115760329A (en) | 2022-10-11 | 2022-10-11 | Bank outlet customer distribution method and system based on deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115760329A true CN115760329A (en) | 2023-03-07 |
Family
ID=85351204
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211239194.1A Pending CN115760329A (en) | 2022-10-11 | 2022-10-11 | Bank outlet customer distribution method and system based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115760329A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116757456A (en) * | 2023-08-21 | 2023-09-15 | 上海银行股份有限公司 | BFS-based banking process visual management system and method |
-
2022
- 2022-10-11 CN CN202211239194.1A patent/CN115760329A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116757456A (en) * | 2023-08-21 | 2023-09-15 | 上海银行股份有限公司 | BFS-based banking process visual management system and method |
| CN116757456B (en) * | 2023-08-21 | 2023-11-03 | 上海银行股份有限公司 | BFS-based banking process visual management system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105139505B (en) | The non-timed reservation remote queue method and system that a kind of banking is handled | |
| CN108476230A (en) | The optimal routing acted on behalf of based on the interaction of machine learning to liaison centre | |
| CN107169580B (en) | Queuing reservation method and system based on window acceptance dynamic capacity | |
| CN109919417A (en) | Method for allocating tasks and device, electronic equipment, the storage medium of financial system | |
| CN109816483B (en) | Information recommendation method and device and readable storage medium | |
| CN111476460B (en) | Method, equipment and medium for intelligent operation scheduling of self-service equipment of bank | |
| CN110727875B (en) | Intelligent distribution method and system for legal case agent | |
| CN111489026A (en) | Queuing time estimation method, system and device | |
| WO2020029387A1 (en) | Wechat-based method and system for making appointment for face-to-face signature for loans, and device and storage medium | |
| KR102196536B1 (en) | Method, apparatus and computer program for providing technician matching service | |
| CN111461636A (en) | Virtual robot-based government affair service platform and application | |
| CN108256970A (en) | A kind of method that Products Show is carried out based on shopping need | |
| CN112215448A (en) | Method and device for distributing customer service | |
| CN110969327B (en) | Work order dispatching method, device, system and data processing method | |
| CN110322093A (en) | Information processing method, information display method, device and calculating equipment | |
| CN111309887A (en) | Method and system for training text key content extraction model | |
| CN115760329A (en) | Bank outlet customer distribution method and system based on deep learning | |
| CN107222542A (en) | A kind of construction method of cloud service management system | |
| CN105930245A (en) | Method and system for monitoring service state of transaction terminal | |
| Madasamy et al. | THE EVOLUTION OF CHATBOTS: CLOUD AND AI SYNERGY IN BANKING CUSTOMER INTERACTIONS | |
| US20160034927A1 (en) | Customer Relations Intelligence | |
| US10853763B1 (en) | Onboarding new service providers utilizing portable service provider attributes | |
| JP6328135B2 (en) | Recommended engine for interactive search forms | |
| CN114186024A (en) | Recommendation method and device | |
| CN116542418B (en) | Deep learning-based business handling method and system for office hall |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |