CN111985646A - Service processing method and device - Google Patents
Service processing method and device Download PDFInfo
- Publication number
- CN111985646A CN111985646A CN202010908152.7A CN202010908152A CN111985646A CN 111985646 A CN111985646 A CN 111985646A CN 202010908152 A CN202010908152 A CN 202010908152A CN 111985646 A CN111985646 A CN 111985646A
- Authority
- CN
- China
- Prior art keywords
- service
- information
- service processing
- processing time
- client
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06316—Sequencing of tasks or work
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Educational Administration (AREA)
- Mathematical Physics (AREA)
- Game Theory and Decision Science (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Development Economics (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a business processing method and a device, which are used for receiving a business processing request sent by a client, wherein the business processing request carries basic information of the client and business information of a business requested to be processed; the service information is used as the input of a service processing time prediction model, the service processing time prediction is carried out on the service information by utilizing the service processing time prediction model, and the predicted service processing time is output; determining the client grade of the client based on the basic information, and determining the arrangement sequence of the service in the service queue according to the client grade, the service information and the service processing time; and acquiring historical service processing information of the client based on the basic information, determining target service processing equipment for processing the service from the service processing equipment in the idle state at present according to the historical service processing information of the client, and sending the service processing request to the target service processing equipment. According to the invention, the service processing time can be reduced, and the time for a client to wait for processing the service can be reduced.
Description
Technical Field
The present invention relates to the field of information processing technologies, and in particular, to a method and an apparatus for processing a service.
Background
At present, a bank background system has a plurality of different types of services to be processed every day, the processed services are large in amount and the types of the services are various, and therefore an operation team realizes management and scheduling of the services by using a task scheduling platform.
At present, a scheduling platform is used to implement management scheduling of a service, specifically, the management platform is used to configure an impact factor and a weight of each impact factor to determine an order of the service in a queue, and when the service is scheduled, service processing devices in an idle state in a service skill set are queried, and a service processing device is randomly selected from the service processing devices to process the service. However, random factors and customer experience are not fully considered when the existing service management scheduling method performs service scheduling, which results in poor service scheduling effect by using the existing service scheduling method, long service processing time, or long service waiting time for a customer to process.
Disclosure of Invention
In view of the above, the present invention provides a service processing method and device, so as to solve the problem in the prior art that the service processing time is long or the service waiting time of a client is long due to a poor service deployment effect.
The first aspect of the present invention discloses a service processing method, which includes:
receiving a service processing request sent by a client, wherein the service processing request carries basic information of the client and service information of a service requested to be processed;
the service information is used as the input of a service processing time prediction model, the service processing time prediction model is used for predicting the service processing time of the service information, the predicted service processing time is output, and the service processing time prediction model is obtained by training a neural network by using historical service information;
determining the customer grade of the customer based on the basic information, and determining the arranging sequence of the business in a business queue according to the customer grade, the business information and the business processing time;
and acquiring historical service processing information of the client based on the basic information, and determining target service processing equipment for processing the service from the service processing equipment in the idle state according to the historical service processing information of the client.
Optionally, the determining an arrangement order of the services in a service queue according to the customer class, the service information, and the service processing time includes:
determining at least one target queuing influence factor corresponding to the customer grade, the service information and the service processing time from at least one preset queuing influence factor;
determining a target queuing influence factor weight matched with the target queuing influence factor based on the corresponding relation between the queuing influence factor and the queuing influence factor weight;
and determining the arrangement sequence of the service in the service queue according to at least one target queuing influence factor weight.
Optionally, the training process of using the historical business information to train the nerve to obtain the business processing time prediction model includes:
acquiring historical service information, and preprocessing the historical service information to obtain target historical service information;
and inputting the target historical service information into a neural network to be trained so that the neural network to be trained can predict service processing time based on the target historical service information, and training the neural network to be trained by taking the predicted service processing time approaching the target service processing time as a training target until the neural network to be trained converges to obtain a service processing time prediction model.
Optionally, the step of using the service information as an input of a service processing time prediction model, performing service processing time prediction on the service information by using the service processing time prediction model, and outputting the predicted service processing time includes:
extracting characteristic data in the service information;
inputting the characteristic data in the service information into a service processing time prediction model;
and the service processing prediction model predicts service processing time based on the characteristic data in the service information to obtain the service processing time of the service.
Optionally, the determining, according to the historical service processing information of the client, a target service processing device for processing the service from service processing devices currently in an idle state includes:
extracting characteristic data in the historical service processing information of the client;
inputting characteristic data in the historical service processing information of the client into a service personnel prediction model, wherein the service personnel prediction model is obtained by training a deep learning model by utilizing service personnel information and historical service processing information corresponding to service processing equipment in a service skill set;
and the service personnel prediction model predicts based on the characteristic data in the historical service processing information of the client to obtain target service processing equipment for processing the service.
Optionally, the training process of training the deep learning model by using the service staff information and the historical service processing information corresponding to the service processing device in the service skill set to obtain the service staff prediction model includes:
acquiring a training sample, wherein the training sample at least comprises service personnel information and historical service processing information corresponding to service processing equipment in a service skill set, and the historical service processing information comprises historical customer information and historical service information of services requested to be processed by the historical customers;
inputting the training sample into a deep learning model to be trained to predict service processing equipment to which the training sample belongs, taking the service processing equipment to which the training sample belongs approaching the service processing equipment indicated by the training sample as a training target, and training the deep learning model to be trained until the deep learning model to be trained converges to obtain a service personnel prediction model.
A second aspect of the present invention discloses a service processing apparatus, which includes:
a receiving unit, configured to receive a service processing request sent by a client, where the service processing request carries basic information of the client and service information of a service requested to be processed;
the first prediction unit is used for taking the service information as the input of a service processing time prediction model, performing service processing time prediction on the service information by using the service processing time prediction model and outputting the predicted service processing time, wherein the service processing time prediction model is obtained by training a neural network by using historical service information through the first construction unit;
a first determining unit, configured to determine a customer class of the customer based on the basic information, and determine an arrangement order of the services in a service queue according to the customer class, the service information, and the service processing time;
a second determining unit, configured to obtain historical service processing information of the client based on the basic information; determining target service processing equipment for processing the service from the service processing equipment in the idle state at present according to the historical service processing information of the client;
and the sending unit is used for sending the service processing request to the target service processing equipment.
Optionally, the first determining unit includes:
a third determining unit, configured to determine at least one target queuing influence factor corresponding to the customer class, the service information, and the service processing time information from at least one preset queuing influence factor;
a fourth determining unit, configured to determine, based on a correspondence between the queuing influence factor and the queuing influence factor weight, a target queuing influence factor weight that matches the target queuing influence factor;
and a fifth determining unit, configured to determine, according to at least one target queuing impact factor weight, an arrangement order of the service in a service queue.
Optionally, the first building unit includes:
the second acquisition unit is used for acquiring historical service information and preprocessing the historical service information to obtain target historical service information;
and the first training unit is used for inputting the historical service information into a neural network to be trained so that the neural network to be trained can predict the service processing time of the historical service information, and the neural network to be trained is trained by taking the predicted service processing time approaching to the target service processing time as a training target until the neural network to be trained converges to obtain a service processing time prediction model.
Optionally, the first prediction unit includes:
the first extraction unit is used for extracting the characteristic data in the service information;
the first input unit is used for inputting the characteristic data in the service information into a service processing time prediction model;
and the second prediction unit is used for predicting the service processing time by the service processing prediction model based on the characteristic data in the service information to obtain the service processing time of the service.
The invention provides a business processing method and a device, after receiving a business processing request sent by a client, determining basic information of the client and business information of a business requested to be processed, which are carried by the business processing request, taking the determined business information as the input of a business processing time prediction model, performing business processing time prediction on the input business information by using the business processing time prediction model, and outputting the predicted business processing time; and determining the client grade of the client by using the basic information of the client so as to reasonably sort the requested services according to the determined client grade, the service information and the service processing information and reduce the time of waiting for processing the services by the client. When the business processing equipment for processing the business is allocated for the requested business, historical business processing information of a client sending the business processing request is combined to allocate the business processing equipment (business personnel) which is most suitable for processing the business requested by the client to the client, and therefore the business processing time of the client is reduced.
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 description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a schematic flow chart of a service processing method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a service processing apparatus according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the 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 invention.
In this application, 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 identical elements in a process, method, article, or apparatus that comprises the element.
As can be seen from the foregoing background art, in the existing service management scheduling method, when performing service scheduling, random factors (for example, task blocking due to too long service processing time) and customer experience are not fully considered, for example, there are task a and task B that enter a queue in sequence, and each impact factor and the weight of each impact factor of the two tasks are the same, but the processing of task a requires 20 minutes and the processing of task B requires 5 minutes. Before any intelligent processing, the client requesting processing task B needs to wait for 20 minutes, so that the client requesting processing task B needs to wait for a long time before starting processing the service requested by the client. In the service processing device for task allocation, the existing service management scheduling method is to query the service processing devices in an idle state in a service skill set, randomly select one service processing device from the service processing devices to process the service, and not comprehensively consider the service processing capability and the customer experience of service personnel corresponding to the service processing devices in the service skill set, which results in long service processing time.
Therefore, the invention provides a service processing method and a service processing device, which can reduce service processing time and can also reduce service waiting time of a client.
Referring to fig. 1, a flow diagram of a service processing method provided in an embodiment of the present invention is shown, where the service processing method specifically includes the following steps:
s101: and receiving a service processing request sent by a client, wherein the service processing request carries basic information of the client and service information of a service requested to be processed.
In an embodiment of the present application, the basic information may include a customer name and an identification number of a customer requesting to transact the business. When a client transacts business at a bank outlet, the client presses a number-taking key to take a number after inputting basic information (name, identification number, and the like) on a number-calling system and selecting the business to be transacted, and when the client presses the number-taking key, the client can be considered to send a business processing request based on the number-calling system, or when the client requests to transact business through a telephone bank, the client can be considered to send a business processing request based on the telephone bank and receive the business processing request sent by the client when inputting the basic information and the business to be selectively processed and pressing a confirmation key, so that the basic information of the client related to the business processing duration of the business processing request and the business information of the business to be processed are obtained.
S102: and taking the service information as the input of a service processing time prediction model, performing service processing time prediction on the service information by using the service processing time prediction model, and outputting the predicted service processing time.
In the embodiment of the application, after a service processing request sent by a client is received, service information of a service carried in the service processing request is obtained, the obtained service information is preprocessed, feature data in the preprocessed service information is extracted, and the extracted feature data in the preprocessed service information is input into a service processing time prediction model, so that the service processing time prediction model carries out service processing time prediction on the basis of the feature data in the preprocessed service information to obtain the service processing time of the service. The service processing time prediction model is obtained by training a neural network by using historical service information; the service information may be preprocessed by null processing, normalization processing, and the like.
In this embodiment of the present application, a training process for obtaining the business processing time prediction model by training a nerve with historical business information may be: acquiring historical service information, and preprocessing the acquired historical service information (for the convenience of distinguishing, information obtained by preprocessing the historical service information is called target historical service information); and inputting the target historical service information into the neural network to be trained so that the application network to be trained can predict the service processing time based on the target historical service information, and training the neural network to be trained by taking the predicted service processing time approach and the target service processing time as training targets until the neural network to be trained converges to obtain a service processing prediction model. The historical service processing information may be preprocessed by null processing, normalization processing, and the like.
S103: and determining the customer grade of the customer based on the basic information, and determining the arrangement sequence of the services in the service queue according to the customer grade, the service information and the service processing time.
In the embodiment of the application, at least one queuing influence factor and the corresponding relation between the queuing influence shadow and the queuing influence factor weight are preset. After receiving a service processing request sent by a client, acquiring basic information of the client and service information of a service requested to be processed by the client, which are carried by the service processing request; determining the client grade of the client according to the acquired basic information of the client, and determining the service grade of the requested service according to the acquired service information; determining at least one target queuing influence factor corresponding to the client grade, the service grade and the service processing time from at least one preset queuing influence factor; and aiming at each target queuing influence factor, determining a target queuing influence factor weight matched with the target queuing influence factor based on the corresponding relation between the queuing influence factor and the queuing influence factor weight, and determining the arrangement sequence of the service in the service queue according to at least one target queuing influence factor weight. The service information comprises the service type of the service requested to be processed and the transaction amount of the service.
In the embodiment of the application, at least one queuing influence factor is preset, and a corresponding relation between the queuing influence factor and the queuing influence factor weight is preset. The preset at least one queuing influence factor can be VPI client (client class), common client (client class), emergency service (service class), common service (service class), service processing time within ten minutes, service processing time from ten minutes to twenty minutes, and service processing time greater than twenty minutes. The queuing influence factor is that the queuing influence factor weight of the VIP customer is greater than that of the common customer; the queuing influence factor is the weight of the queuing influence factor of the emergency service, which is greater than the weight of the queuing influence factor of the common service; the queuing impact factor weight with the service processing time within ten minutes, ten minutes to twenty minutes and more than twenty minutes is arranged from big to small in sequence as follows: queuing impact factor weight with service processing time within ten minutes > ten minutes to twenty minutes of service processing time > queuing impact factor weight with service processing time greater than twenty minutes. The at least one queuing influence factor can be obtained by the staff who are engaged in the bank working experience for many years according to the working experience of the staff.
For example, if the clients entering the service queue successively are client 1 and client 2, receiving a service processing request 1 sent by client 1 and a service processing request 2 sent by client 2, acquiring basic information 1 and service information 1 of client 1 carried by service processing request 1, and acquiring basic information 2 and service information 2 of client 2 carried by service processing request 2; if the service processing time of the client 1 is 15 minutes by using the service processing time prediction model to predict the service processing time of the service information 1, determining that the client grade of the client 1 is a common client according to the basic information 1, and determining that the service grade of the client 1 is a common service according to the service information 1; and predicting the service processing time of the service information 2 by using a service processing time prediction model to obtain that the service processing time of the client 2 is 5 minutes, determining that the client grade of the client 2 is a common client according to the basic information 2, and determining that the service grade of the client 2 is a common service according to the service information 2.
Determining that the target queuing influence factor corresponding to the customer level, the service level and the service processing time of the customer 1 is normal customer, normal service and service processing time from at least one preset queuing influence factor, and determining a target queuing influence factor weight matched with the normal customer, a target queuing influence factor weight matched with the normal service and a target queuing influence factor weight matched with the service processing time from ten minutes to twenty minutes according to the corresponding relation between the queuing influence factor and the queuing influence shadow weight; determining that the target queuing influence factor corresponding to the customer grade, the service grade and the service processing time of the customer 2 is within ten minutes from at least one preset queuing influence factor, and determining the target queuing influence factor weight matched with the common customer, the target queuing influence factor weight matched with the common service and the target queuing influence factor weight matched with the service processing time within ten minutes according to the corresponding relation between the queuing influence factor and the queuing influence shadow weight; and determining that the arrangement sequence of the client 1 and the client 2 in the service queue is the client 2 and the client 1 according to the target queuing influence factor weight matched with the common client of the client 2, the target queuing influence factor weight matched with the common service, the target queuing influence factor weight matched with the common client of the client 1 and the target queuing influence factor weight matched with the common client of the client 1, the target queuing influence factor weight matched with the common service and the target queuing influence factor weight matched with the service processing time of ten minutes to twenty minutes.
The above is only a preferred way to set the queuing affecting factor and the size of the queuing affecting shadow weight corresponding to the queuing affecting factor provided in the embodiment of the present application, and the inventor can set the queuing affecting factor and the queuing affecting factor according to his own requirements, which is not limited in the embodiment of the present application.
S104: and acquiring historical service processing information of the client based on the basic information, and determining target service processing equipment for processing the service from the service processing equipment in the idle state according to the historical service processing information of the client.
In the embodiment of the application, the service personnel prediction model is obtained by training the deep learning model by using service personnel information and historical service processing information corresponding to service processing equipment in a service skill set. The training process of training the deep learning model by using the service personnel information and the historical service processing information corresponding to the service processing equipment in the service skill set to obtain the service personnel prediction model may be as follows: the method comprises the steps of obtaining a training sample, preprocessing the obtained training sample, inputting the preprocessed training sample into a deep learning model to be trained to predict service processing equipment to which the training sample belongs, training the deep learning model to be trained by taking the service processing equipment to which the training sample belongs approaching the service processing equipment indicated by the training sample as a training target until the deep learning model to be trained converges, and obtaining a service staff prediction model. The training sample at least comprises service personnel information and historical service processing information corresponding to service processing equipment in a service skill set, and the historical service processing information comprises historical client information and historical service information of services requested to be processed by historical clients.
In the process of specifically executing step S104, service staff information corresponding to the service processing device in the idle state in the current service skill group may be acquired, and historical service processing information of the client may be acquired according to the basic information of the client that sends the service processing request; extracting the characteristic data in the business personnel information corresponding to the business processing equipment in the idle state and the historical business processing information of the client, and inputting the business personnel information corresponding to the business processing equipment in the idle state and the characteristic data in the historical business processing information of the client into a business personnel prediction model, so that the business personnel prediction model carries out business personnel prediction on the basis of the business personnel information corresponding to the business processing equipment in the idle state and the characteristic data in the historical business processing information of the client to obtain target business processing equipment for processing business.
In the embodiment of the present application, the service staff information corresponding to the service processing device includes a name of a service staff operating the service processing device, a service type which the service staff is skilled in processing, rating information of the service staff, and the like; the historical service processing information of the client comprises the service processed by the historical request of the client, the service processing equipment matched with the service processed by the historical request of the client and the service personnel information corresponding to the service processing equipment. The scoring information of the service personnel can be 5-star high score, 3-star medium score, 1-star poor score and the like.
For example, the service processing devices in the idle state in the current service skill set are the service processing device 1 and the service processing device 2. If the service staff information of the service staff 1 corresponding to the service processing equipment 1 is a service staff A, the service staff A is skilled in processing and modifying the bank card password and opening the mobile phone bank, and the grading information of the service staff A is 5-star good evaluation; the service personnel information of the service personnel 2 corresponding to the service processing equipment 2 is a service personnel B, the service personnel B is good at processing and modifying the password and the withdrawal of the bank card, and the scoring information of the service personnel B is 1 star-poor scoring; according to the basic information of the client sending the service processing request, acquiring the historical service processing information of the client as the service which is processed by the historical request of the client is the modified bank card password, the service processing equipment matched with the historical processing information of the client as the historical request processing modified bank card password is the service processing equipment 2, and the service staff information corresponding to the service processing equipment 2 is the service staff information of the service staff B.
Extracting characteristic data in business personnel information (business personnel information of business personnel A and business personnel information of business personnel B) corresponding to the business processing equipment in an idle state and historical business processing information of a client, inputting the business personnel information (business personnel information of business personnel A and business personnel information of business personnel B) corresponding to the business processing equipment in the idle state and the characteristic data in the historical business processing information of the client into a business personnel prediction model, so that the business personnel prediction model carries out business personnel prediction based on the business personnel information (business personnel information of business personnel A and business personnel information of business personnel B) corresponding to the business processing equipment in the idle state and the characteristic data in the historical business processing information of the client, and obtains target business processing equipment for processing business (modifying bank card passwords) as the business processing equipment 1, further, the service processing request sent by the client may be sent to the service processing device 1 (target service processing device), so that the service person a operates the service processing device 1 (target service processing device) to perform service processing for the client.
S105: and sending the service processing request to the target service processing equipment.
After determining target business processing equipment for processing business from the current idle business processing equipment according to historical business processing information of a client sending a business processing request, sending the business processing request to the target business processing equipment so that business personnel corresponding to the target business processing equipment can handle the business requested to be processed by the client.
The invention provides a business processing method, after receiving a business processing request sent by a client, determining basic information of the client and business information of a business requested to be processed, which are carried by the business processing request, taking the determined business information as the input of a business processing time prediction model, performing business processing time prediction on the input business information by utilizing the business processing time prediction model, and outputting the predicted business processing time; and determining the client grade of the client by using the basic information of the client so as to reasonably sort the requested services according to the determined client grade, the service information and the service processing information and reduce the time of waiting for processing the services by the client. When the business processing equipment for processing the business is allocated for the requested business, historical business processing information of a client sending the business processing request is combined to allocate the business processing equipment (business personnel) which is most suitable for processing the business requested by the client to the client, and therefore the business processing time of the client is reduced.
Corresponding to the service processing method disclosed in the above embodiment of the present invention, an embodiment of the present invention further provides a service processing apparatus, as shown in fig. 2, where the service processing apparatus includes:
a receiving unit 21, configured to receive a service processing request sent by a client, where the service processing request carries basic information of the client and service information of a service requested to be processed;
the first prediction unit 22 is configured to use the service information as an input of a service processing time prediction model, perform service processing time prediction on the service information by using the service processing time prediction model, and output predicted service processing time, where the service processing time prediction model is obtained by training a neural network by using historical service information through the first construction unit;
a first determining unit 23, configured to determine a client class of the client based on the basic information, and determine an arrangement order of the services in the service queue according to the client class, the service information, and the service processing time;
a second determining unit 24, configured to obtain historical service processing information of the client based on the basic information, and determine, from the service processing devices currently in an idle state, a service processing device that processes the service, based on the historical service processing information of the client;
a sending unit 25, configured to send the service processing request to the target service processing device.
The specific principle and the execution process of each unit in the service processing apparatus disclosed in the above embodiment of the present invention are the same as those of the service processing method disclosed in the above embodiment of the present invention, and reference may be made to corresponding parts in the service processing method disclosed in the above embodiment of the present invention, which are not described herein again.
The invention provides a business processing device, after receiving a business processing request sent by a client, determining basic information of the client and business information of a business requested to be processed, which are carried by the business processing request, taking the determined business information as the input of a business processing time prediction model, performing business processing time prediction on the input business information by utilizing the business processing time prediction model, and outputting the predicted business processing time; and determining the client grade of the client by using the basic information of the client so as to reasonably sort the requested services according to the determined client grade, the service information and the service processing information and reduce the time of waiting for processing the services by the client. When the business processing equipment for processing the business is allocated for the requested business, historical business processing information of a client sending the business processing request is combined to allocate the business processing equipment (business personnel) which is most suitable for processing the business requested by the client to the client, and therefore the business processing time of the client is reduced.
Preferably, in an embodiment of the present application, the first determining unit includes:
a third determining unit, configured to determine at least one target queuing influence factor corresponding to the client class, the service information, and the service processing time information from at least one preset queuing influence factor;
a fourth determining unit, configured to determine, based on a correspondence between the queuing influence factor and the queuing influence factor weight, a target queuing influence factor weight that matches the target queuing influence factor;
and the fifth determining unit is used for determining the arrangement sequence of the service in the service queue according to the weight of the at least one target queuing influence factor.
Preferably, in an embodiment of the present application, the first building unit includes:
the second acquisition unit is used for acquiring historical service information and preprocessing the historical service information to obtain target historical service information;
the first training unit is used for inputting the historical service information into the neural network to be trained so that the neural network to be trained can predict the service processing time of the historical service information, the predicted service processing time approaches the target service processing time and serves as a training target, the neural network to be trained is trained until the neural network to be trained converges, and a service processing time prediction model is obtained.
Preferably, in an embodiment of the present application, the first prediction unit includes:
the first extraction unit is used for extracting the characteristic data in the service information;
the first input unit is used for inputting the characteristic data in the service information into the service processing time prediction model;
and the second prediction unit is used for predicting the service processing time based on the characteristic data in the service information by the service processing prediction model to obtain the service processing time of the service.
Preferably, in an embodiment of the present application, the second determining unit includes:
the second extraction unit is used for extracting characteristic data in the historical service processing information of the client;
the second prediction unit is used for inputting the characteristic data in the historical service processing information of the client into the service personnel prediction model, wherein the service personnel prediction model is obtained by training the deep learning model through the second construction unit by utilizing the service personnel information and the historical service processing information corresponding to the service processing equipment in the service skill set;
the service personnel prediction model carries out service personnel prediction based on characteristic data in the historical service processing information of the client to obtain service processing equipment for processing the service.
Preferably, in an embodiment of the present application, the second building unit includes:
a third obtaining unit, configured to obtain a training sample, where the training sample at least includes service staff information and historical service processing information corresponding to service processing devices in a service skill set, and the historical service processing information includes historical client information and historical service information of a service requested to be processed by a historical client;
and the second training unit is used for inputting the training samples into the business processing equipment to which the deep learning model to be trained belongs to predict the training samples, and training the deep learning model to be trained by taking the business processing equipment to which the training samples belong close to the target business processing equipment indicated by the training samples as a training target until the deep learning model to be trained converges to obtain a business personnel prediction model.
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, the system or system embodiments are substantially similar to the method embodiments and therefore are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for related points. The above-described system and system embodiments are only illustrative, wherein the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (10)
1. A method for processing a service, the method comprising:
receiving a service processing request sent by a client, wherein the service processing request carries basic information of the client and service information of a service requested to be processed;
the service information is used as the input of a service processing time prediction model, the service processing time prediction model is used for predicting the service processing time of the service information, the predicted service processing time is output, and the service processing time prediction model is obtained by training a neural network by using historical service information;
determining the customer grade of the customer based on the basic information, and determining the arranging sequence of the business in a business queue according to the customer grade, the business information and the business processing time;
acquiring historical service processing information of the client based on the basic information, and determining target service processing equipment for processing the service from the service processing equipment in the idle state at present according to the historical service processing information of the client;
and sending the service processing request to the target service processing equipment.
2. The method of claim 1, wherein said determining the order of arranging the services in a service queue according to the customer class, the service information and the service processing time comprises:
determining at least one target queuing influence factor corresponding to the customer grade, the service information and the service processing time from at least one preset queuing influence factor;
determining a target queuing influence factor weight matched with the target queuing influence factor based on the corresponding relation between the queuing influence factor and the queuing influence factor weight;
and determining the arrangement sequence of the service in the service queue according to at least one target queuing influence factor weight.
3. The method of claim 1, wherein the training process for training a nerve using historical business information to obtain the business process time prediction model comprises:
acquiring historical service information, and preprocessing the historical service information to obtain target historical service information;
and inputting the target historical service information into a neural network to be trained so that the neural network to be trained can predict service processing time based on the target historical service information, and training the neural network to be trained by taking the predicted service processing time approaching the target service processing time as a training target until the neural network to be trained converges to obtain a service processing time prediction model.
4. The method of claim 1, wherein the using the service information as an input of a service processing time prediction model, performing service processing time prediction on the service information by using the service processing time prediction model, and outputting a predicted service processing time comprises:
extracting characteristic data in the service information;
inputting the characteristic data in the service information into a service processing time prediction model;
and the service processing prediction model predicts service processing time based on the characteristic data in the service information to obtain the service processing time of the service.
5. The method according to claim 1, wherein the determining, from the service processing devices currently in an idle state, a target service processing device for processing the service according to the historical service processing information of the client comprises:
extracting characteristic data in the historical service processing information of the client;
inputting characteristic data in the historical service processing information of the client into a service personnel prediction model, wherein the service personnel prediction model is obtained by training a deep learning model by utilizing service personnel information and historical service processing information corresponding to service processing equipment in a service skill set;
and the service personnel prediction model predicts based on the characteristic data in the historical service processing information of the client to obtain target service processing equipment for processing the service.
6. The method according to claim 5, wherein the training process of training the deep learning model to obtain the service person prediction model by using the service person information and the historical service processing information corresponding to the service processing equipment in the service skill set comprises:
acquiring a training sample, wherein the training sample at least comprises service personnel information and historical service processing information corresponding to service processing equipment in a service skill set, and the historical service processing information comprises historical customer information and historical service information of services requested to be processed by the historical customers;
inputting the training sample into a deep learning model to be trained to predict service processing equipment to which the training sample belongs, taking the service processing equipment to which the training sample belongs approaching the service processing equipment indicated by the training sample as a training target, and training the deep learning model to be trained until the deep learning model to be trained converges to obtain a service personnel prediction model.
7. A traffic processing apparatus, characterized in that the apparatus comprises:
a receiving unit, configured to receive a service processing request sent by a client, where the service processing request carries basic information of the client and service information of a service requested to be processed;
the first prediction unit is used for taking the service information as the input of a service processing time prediction model, performing service processing time prediction on the service information by using the service processing time prediction model and outputting the predicted service processing time, wherein the service processing time prediction model is obtained by training a neural network by using historical service information through the first construction unit;
a first determining unit, configured to determine a customer class of the customer based on the basic information, and determine an arrangement order of the services in a service queue according to the customer class, the service information, and the service processing time;
a second determining unit, configured to obtain historical service processing information of the client based on the basic information; determining target service processing equipment for processing the service from the service processing equipment in the idle state at present according to the historical service processing information of the client;
and the sending unit is used for sending the service processing request to the target service processing equipment.
8. The apparatus of claim 7, wherein the first determining unit comprises:
a third determining unit, configured to determine at least one target queuing influence factor corresponding to the customer class, the service information, and the service processing time information from at least one preset queuing influence factor;
a fourth determining unit, configured to determine, based on a correspondence between the queuing influence factor and the queuing influence factor weight, a target queuing influence factor weight that matches the target queuing influence factor;
and a fifth determining unit, configured to determine, according to at least one target queuing impact factor weight, an arrangement order of the service in a service queue.
9. The apparatus of claim 7, wherein the first building unit comprises:
the second acquisition unit is used for acquiring historical service information and preprocessing the historical service information to obtain target historical service information;
and the first training unit is used for inputting the historical service information into a neural network to be trained so that the neural network to be trained can predict the service processing time of the historical service information, and the neural network to be trained is trained by taking the predicted service processing time approaching to the target service processing time as a training target until the neural network to be trained converges to obtain a service processing time prediction model.
10. The apparatus of claim 7, wherein the first prediction unit comprises:
the first extraction unit is used for extracting the characteristic data in the service information;
the first input unit is used for inputting the characteristic data in the service information into a service processing time prediction model;
and the second prediction unit is used for predicting the service processing time by the service processing prediction model based on the characteristic data in the service information to obtain the service processing time of the service.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010908152.7A CN111985646B (en) | 2020-09-02 | 2020-09-02 | Service processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010908152.7A CN111985646B (en) | 2020-09-02 | 2020-09-02 | Service processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111985646A true CN111985646A (en) | 2020-11-24 |
| CN111985646B CN111985646B (en) | 2023-07-18 |
Family
ID=73448173
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010908152.7A Active CN111985646B (en) | 2020-09-02 | 2020-09-02 | Service processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111985646B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112650571A (en) * | 2020-12-30 | 2021-04-13 | 中国农业银行股份有限公司 | Operation execution method and device |
| CN113537574A (en) * | 2021-06-23 | 2021-10-22 | 北京健康之家科技有限公司 | Service processing timeliness pushing method and device, storage medium and computer equipment |
| CN114973493A (en) * | 2022-05-19 | 2022-08-30 | 中国银行股份有限公司 | Intelligent number-taking machine and method for bank outlets |
| CN115482620A (en) * | 2022-09-29 | 2022-12-16 | 上海浦东发展银行股份有限公司 | Multi-channel intelligent number calling method, device, equipment and medium |
| 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 |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190057475A1 (en) * | 2017-08-16 | 2019-02-21 | Beijing Didi Infinity Technology And Development Co., Ltd. | System and method for predicting wait time |
| CN110910557A (en) * | 2019-11-28 | 2020-03-24 | 中国银行股份有限公司 | Service handling duration prediction method, device, server and storage medium |
| US20200132298A1 (en) * | 2018-10-26 | 2020-04-30 | Robert W. Healey | Gas powered torch |
| CN111489026A (en) * | 2020-04-08 | 2020-08-04 | 中国银行股份有限公司 | Queuing time estimation method, system and device |
-
2020
- 2020-09-02 CN CN202010908152.7A patent/CN111985646B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190057475A1 (en) * | 2017-08-16 | 2019-02-21 | Beijing Didi Infinity Technology And Development Co., Ltd. | System and method for predicting wait time |
| US20200132298A1 (en) * | 2018-10-26 | 2020-04-30 | Robert W. Healey | Gas powered torch |
| CN110910557A (en) * | 2019-11-28 | 2020-03-24 | 中国银行股份有限公司 | Service handling duration prediction method, device, server and storage medium |
| CN111489026A (en) * | 2020-04-08 | 2020-08-04 | 中国银行股份有限公司 | Queuing time estimation method, system and device |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112650571A (en) * | 2020-12-30 | 2021-04-13 | 中国农业银行股份有限公司 | Operation execution method and device |
| CN113537574A (en) * | 2021-06-23 | 2021-10-22 | 北京健康之家科技有限公司 | Service processing timeliness pushing method and device, storage medium and computer equipment |
| CN113537574B (en) * | 2021-06-23 | 2024-03-26 | 北京水滴科技集团有限公司 | Service processing aging pushing method and device, storage medium and computer equipment |
| CN114973493A (en) * | 2022-05-19 | 2022-08-30 | 中国银行股份有限公司 | Intelligent number-taking machine and method for bank outlets |
| CN115482620A (en) * | 2022-09-29 | 2022-12-16 | 上海浦东发展银行股份有限公司 | Multi-channel intelligent number calling method, device, equipment and medium |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111985646B (en) | 2023-07-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111985646A (en) | Service processing method and device | |
| CN105975948B (en) | Cloud service platform framework for recognition of face | |
| CN108874640A (en) | A kind of appraisal procedure and device of clustering performance | |
| CN108830439A (en) | Electricity business hall intelligent Service monitoring method and system based on recognition of face | |
| CN104461704B (en) | A kind of business cloud processing method and system | |
| CN110264039A (en) | A kind of generation method and equipment of working report | |
| CN101221672A (en) | Automatic registration method and system based on network | |
| CN111079557A (en) | Face recognition-based automatic distribution method and system for electric power business hall service terminals | |
| CN111476460A (en) | Method, equipment and medium for intelligent operation scheduling of bank self-service equipment | |
| CN108921391A (en) | A kind of method for distributing business and device | |
| CN112217672B (en) | Service processing system for CDN platform | |
| CN109491733A (en) | Based on visual interface display method and relevant device | |
| CN115099629A (en) | Customer service demand evaluation distribution method and system, electronic device and storage medium | |
| CN112381418A (en) | Case allocation method, device, equipment and storage medium | |
| CN115631064A (en) | Intelligent gas installation management method, internet of things system and storage medium | |
| CN106878347A (en) | Information processing method, system, mobile terminal and server | |
| CN113450002A (en) | Task allocation method and device, electronic equipment and storage medium | |
| CN110189221B (en) | Method, apparatus, device and computer readable storage medium for performing industry-spreading adjustment | |
| CN110910558B (en) | Bank outlet queuing method and device | |
| CN112348507A (en) | Service processing method and device | |
| CN110969440A (en) | Remote authorization method and device | |
| CN111652471A (en) | List distribution control method and device, electronic equipment and storage medium | |
| CN115394003A (en) | Service handling time length estimation method, device, equipment, storage medium and product | |
| CN115578815A (en) | Access control management method, authentication server, access control system and readable storage medium | |
| Olusola et al. | Queue management systems for congestion control: Case study of first bank, Nigeria |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |