CN110942190A - Queuing time prediction method and device, computer equipment and storage medium - Google Patents
Queuing time prediction method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110942190A CN110942190A CN201911156629.4A CN201911156629A CN110942190A CN 110942190 A CN110942190 A CN 110942190A CN 201911156629 A CN201911156629 A CN 201911156629A CN 110942190 A CN110942190 A CN 110942190A
- Authority
- CN
- China
- Prior art keywords
- data
- time prediction
- queuing
- type
- acquiring
- 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
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C11/00—Arrangements, systems or apparatus for checking, e.g. the occurrence of a condition, not provided for elsewhere
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C11/00—Arrangements, systems or apparatus for checking, e.g. the occurrence of a condition, not provided for elsewhere
- G07C2011/04—Arrangements, systems or apparatus for checking, e.g. the occurrence of a condition, not provided for elsewhere related to queuing systems
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of computer technology, in particular to a queuing time prediction method, a queuing time prediction device, computer equipment and a storage medium, wherein the queuing time prediction method comprises the following steps: s10: when a queuing request is obtained, obtaining the type of the service to be transacted from the queuing request; s20: acquiring data of queued personnel according to the type of the service to be handled; s30: inputting the queued personnel data into a preset time prediction model for calculation to obtain a corresponding calculation result; s40: and acquiring a queuing time prediction result corresponding to the type of the service to be managed according to the calculation result. The invention has the advantages that the predicted queuing time is provided for the user when the user gets the ticket, the user knows the waiting time in advance, the time can be freely arranged, and the effect of improving the satisfaction degree of the user in the transaction process is facilitated.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a queuing time prediction method, apparatus, computer device, and storage medium.
Background
At present, when people need to transact related matters, people transact the matters in the corresponding service hall. Meanwhile, at present, the satisfaction degree of users in a business hall is also concerned more and more, and particularly, the service attitude of workers, the business efficiency and the queuing waiting time of the users are reflected.
In the existing office hall, a plurality of office windows are usually opened for people to transact related matters. And a queuing system is usually adopted in the office hall, when people go to the office hall, the number is taken through a number taking machine according to the transaction type, and then queuing is carried out according to the number taking condition. However, when the method is used for queuing, the time required for queuing can be predicted only according to the number of people in the queue, and the time required for queuing is difficult to acquire more accurately, so that the service experience of the user in the queuing is influenced, and therefore, the method has a room for improvement.
Disclosure of Invention
The invention aims to provide a queuing time prediction method, a queuing time prediction device, a computer device and a storage medium, which can provide predicted queuing time for a user when the user gets a ticket, enable the user to know the waiting time in advance, can freely arrange the time and are beneficial to improving the satisfaction degree of the user in the transaction process.
The above object of the present invention is achieved by the following technical solutions:
a queuing time prediction method, the queuing time prediction method comprising:
s10: when a queuing request is obtained, obtaining the type of the service to be transacted from the queuing request;
s20: acquiring data of queued personnel according to the type of the service to be handled;
s30: inputting the queued personnel data into a preset time prediction model for calculation to obtain a corresponding calculation result;
s40: and acquiring a queuing time prediction result corresponding to the type of the service to be managed according to the calculation result.
By adopting the technical scheme, the time required to be queued can be calculated by the service type to be handled of the user and the corresponding queued personnel data when the user enters the service hall and triggers the queuing request through the pre-trained time prediction model, so that the user can accurately know the time required to be queued when queuing, and further can freely arrange own time according to the queuing time prediction result, and the service experience of the user when queuing is improved.
The invention is further configured to: before step S30, the queuing time prediction method further includes:
s31: acquiring historical monitoring data, and acquiring corresponding user behavior data from the historical monitoring data according to the transaction type;
s32: classifying the user behavior data according to the transaction service type to obtain a data set to be trained;
s33: and training the data set to be trained class by class to obtain the time prediction model.
By adopting the technical scheme, the historical monitoring data is used, and training is carried out in the historical monitoring data according to the user behavior data corresponding to the transaction service type, so that the time of queuing for the user to handle the service can be calculated according to the service handled by the user when the obtained time prediction model is used, the pertinence of the time prediction model is improved, and the calculation accuracy of the time prediction model is further improved.
The invention is further configured to: step S31 includes:
s311: acquiring vacancy attribute data from the historical monitoring data;
s312: and correspondingly processing the historical monitoring data according to the number of the vacancy attribute data to obtain user behavior data corresponding to each transacted service type.
By adopting the technical scheme, the vacant attribute data are removed from the historical monitoring data, so that the attribute data in the acquired user behavior data are more complete, the reliability of the user behavior data is improved, and the accuracy of the trained time prediction model is improved.
The invention is further configured to: step S33 includes:
s331: preprocessing the data set to be trained to obtain a training set to be grouped;
s332: grouping the training sets to be grouped to obtain a first feature set and a second feature set and a corresponding first test data set and a second test data set;
s333: training the first feature set by using an Adaboost regression algorithm to obtain a corresponding training result, and performing first precision adjustment by using the second feature set and the training result to obtain a model to be tested;
s334: and inputting the first test data set to the model to be tested to obtain a corresponding test result, and performing second precision adjustment on the test result by using the second test data set to obtain the time prediction model.
By adopting the technical scheme, the feature set and the test set are divided into the first feature set and the second feature set, and the first test data set and the second test data set, so that the first precision adjustment and the second precision adjustment can be carried out during model training and testing, and the precision of the time prediction model obtained by training is further ensured.
The invention is further configured to: step S331 includes:
s3311: acquiring user handling data from the data set to be trained;
s3312: and taking the user handling data as the training set to be grouped.
By adopting the technical scheme, the user transaction data is used as the training set to be grouped, and the time prediction result can be calculated according to the behavior of the user transacting the items before when the time prediction model is used for actual calculation.
The second aim of the invention is realized by the following technical scheme:
a queuing time prediction apparatus, the queuing time prediction apparatus comprising:
the request acquisition module is used for acquiring the type of the service to be handled from the queuing request when the queuing request is acquired;
the data acquisition module is used for acquiring queued personnel data according to the type of the service to be managed;
the calculation module is used for inputting the queued personnel data into a preset time prediction model for calculation to obtain a corresponding calculation result;
and the time prediction module is used for acquiring a queuing time prediction result corresponding to the type of the service to be managed according to the calculation result.
By adopting the technical scheme, the time required to be queued can be calculated by the service type to be handled of the user and the corresponding queued personnel data when the user enters the service hall and triggers the queuing request through the pre-trained time prediction model, so that the user can accurately know the time required to be queued when queuing, and further can freely arrange own time according to the queuing time prediction result, and the service experience of the user when queuing is improved.
The third object of the invention is realized by the following technical scheme:
a computer device comprising a memory, a processor and a computer program stored in said memory and executable on said processor, said processor implementing the steps of the above-mentioned queuing time prediction method when executing said computer program.
The fourth object of the invention is realized by the following technical scheme:
a computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned queuing time prediction method.
In conclusion, the beneficial technical effects of the invention are as follows:
by the pre-trained time prediction model, when a user enters a working hall and triggers the queuing request, the time needing to be queued can be calculated through the service type to be handled of the user and the corresponding queued personnel data, the user can accurately know the time prediction result needing to be queued when queuing, the time of the user can be freely arranged according to the queuing time prediction result, and the service experience of the user when queuing is improved.
Drawings
FIG. 1 is a flow chart of a queuing time prediction method in accordance with one embodiment of the present invention;
FIG. 2 is another flow chart of a method of queue time prediction in an embodiment of the present invention;
FIG. 3 is a flowchart illustrating the implementation of step S31 in the queuing time prediction method according to an embodiment of the present invention;
FIG. 4 is a flowchart illustrating the implementation of step S33 in the queuing time prediction method according to an embodiment of the invention;
FIG. 5 is a flowchart of the implementation of step S331 in the queuing time prediction method according to an embodiment of the present invention;
FIG. 6 is a schematic block diagram of a queuing time prediction apparatus in accordance with an embodiment of the invention;
FIG. 7 is a schematic diagram of a computer device according to an embodiment of the invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
The first embodiment is as follows:
in an embodiment, as shown in fig. 1, the present invention discloses a queuing time prediction method, which specifically includes the following steps:
s10: and when the queuing request is acquired, acquiring the type of the service to be transacted from the queuing request.
In this embodiment, the queuing request refers to a message triggered by a user going to the transaction hall to request queuing and transaction of related matters. The type of the service to be transacted refers to the type of the specific matters to be transacted by the user triggering the queuing request.
Specifically, when a user enters a service hall, after a number taker located in the service hall selects a service type to be handled, the number taker triggers the queuing request according to the service type to be handled, and further, the service type to be handled is obtained from the queuing request.
S20: and acquiring the data of the queued personnel according to the type of the service to be managed.
In this embodiment, the queued personal data refers to the number of users already in a queued state in the to-do business type.
Specifically, when the triggered queuing request is acquired, the number of people queuing to handle the service type to be handled is acquired from the queuing request and is used as the queued personnel data.
S30: and inputting the data of the queued personnel into a preset time prediction model for calculation to obtain a corresponding calculation result.
In this embodiment, the time prediction model refers to a calculation model that is trained in advance and used for predicting the queuing waiting time required by the user.
Specifically, the monitoring device located in the office hall collects behavior data of all users from the beginning of business of the office hall on the day to the time when the queuing request is acquired, and data of the office hall. The behavior data of the user and the data of the service hall comprise data such as the number of windows corresponding to the services, the total waiting number of various services corresponding to the integrated window capable of handling the services, the number of people handling the services corresponding to the integrated window, the average handling time of ticket numbers handled by the services before, the average handling time of ticket numbers handled by the integrated window before, the average handling time of how long the windows capable of handling the services have been handled by the integrated window at the moment, the average call interval of the windows capable of handling the services, and the like.
And further, inputting the behavior data of the user and the data of the queued personnel into the preset time prediction model for calculation to obtain a corresponding result.
S40: and acquiring a queuing time prediction result corresponding to the type of the service to be managed according to the calculation result.
In this embodiment, the queuing time prediction result is the time that the user expects to need to wait in line after being calculated by the time prediction model.
Specifically, when the queuing request is triggered, the calculation result is used as a queuing time prediction result corresponding to the to-be-handled service type.
In the embodiment, through the pre-trained time prediction model, when a user enters the office hall and triggers the queuing request, the time required to be queued can be calculated through the type of the service to be handled of the user and the corresponding queued personnel data, so that the user can accurately know the prediction result of the time required to be queued when queuing, further, the user can freely arrange the time according to the prediction result of the queuing time, and the service experience of the user when queuing is improved.
In one embodiment, as shown in fig. 2, before step S30, the queuing time prediction method further includes:
s31: and acquiring historical monitoring data, and acquiring corresponding user behavior data from the historical monitoring data according to the transaction type.
In this embodiment, the historical monitoring data refers to data obtained by the monitoring device from the behavior of the user and the worker in the office hall over a past period of time. The transaction service type is the type of the items which can be handled in the transaction hall and correspond to the type of the service to be handled. The user behavior data refers to data of the behavior of the user in the historical monitoring data.
Specifically, the monitoring data is photographed by a monitoring device installed in the office hall, and the history monitoring data is composed. The monitoring devices are installed at various positions in the office hall, and the number of the monitoring devices is set according to the shooting capacity of the monitoring devices and the installation angle of the monitoring devices.
Further, in the historical monitoring data, the historical monitoring data is classified according to the transaction type. The specific classification mode may be that when the user transacts the service, the behavior of the user in the transaction hall is used as the user behavior data of the transaction type in the historical monitoring data according to the transaction type selected by the user on the number taker. The mode of acquiring the user behavior data may be to arrange data of the following attributes of users in a certain hall of a month, for example, in a tax hall, according to the user behavior data recorded by the intelligent monitoring device:
| Date | YYYY-MM-DD, recording date of detection time | 2019/9/2 |
| Ticket_id | Ticket number | C051 |
| Take_time | The intelligent monitoring records the time of the taxpayer for getting the ticket at the ticket taking machine, and if not, the time is recorded as null | 9:31:06 |
| Servic_class | Intelligent monitoring and recording transaction business type when taxpayer gets ticket | Receipt acceptance, personal social security service, integrated services, receipt generation, and the like |
| Start_time | The intelligent monitoring records the time that the taxpayer starts to transact in the foreground, and if not, the time is recorded as null | 9:36:06 |
| Count_number | The time when the taxpayer gets the ticket corresponds to the number of windows capable of handling the business | 3 |
| Over_time | The time that the taxpayer finishes transacting in the foreground is intelligently monitored and recorded, and if not, the time is recorded as null | 9:40:06 |
| State | Ticket number status, 1 represents a leave number, 0 represents a normal completion | 1 represents a leave number and 0 represents a normal completion |
S32: and classifying the user behavior data according to the transaction type to obtain a data set to be trained.
In this embodiment, the data set to be trained refers to data that stores user behavior data and is used for training the temporal prediction model.
Specifically, according to the transaction type, the user behavior data are classified, the same user behavior data are classified into one class, and the data set to be trained is obtained.
S33: and training the data set to be trained class by class to obtain a time prediction model.
Specifically, the Adaboost regression algorithm is used for training the data set to be trained class by class to obtain the time prediction model.
In an embodiment, as shown in fig. 3, in step S31, obtaining historical monitoring data, and obtaining corresponding user behavior data from the historical monitoring data according to the transaction type includes the following steps:
s311: and acquiring vacancy attribute data from historical monitoring data.
In the present embodiment, the null attribute data is data recorded as null in the data table in step S31.
Specifically, read _ csv of pandas reads data, and the number of non-empty records per attribute is recorded by info () function.
S312: and according to the number of the vacancy attribute data, performing corresponding processing on the historical monitoring data to obtain user behavior data corresponding to each transacted service type.
Specifically, attribute deletion is directly performed on attributes with the missing value number exceeding 10% of the total record number, if the missing value record number is within 50, the row record is directly deleted, and interpolation is used for replacing the missing value record number between the two.
In an embodiment, as shown in fig. 4, in step S33, in step S33, training a data set to be trained to obtain a temporal prediction model, specifically including the following steps:
s331: and preprocessing the data set to be trained to obtain a training set to be grouped.
In this embodiment, the training set to be grouped needs to be grouped into a data group according to a preset rule.
Specifically, detecting abnormal points in a data set to be trained, preprocessing.scale normalization of all the data sets to be trained, calling cluster.DBSCA density clustering to detect the abnormal points, iteratively adjusting two parameters of a cluster radius eps and a minimum node number min _ samples, performing model fitting by using dbscan.fit (), recording the number of the abnormal points detected by model fitting in each parameter combination and the number of samples of each cluster, finding out an optimal parameter according to the number distribution, continuously performing dbscan.fit (), outputting the abnormal points, and deleting the abnormal points in the data;
further, standardizing the characteristic data in the data set to be trained, performing one-hot compilation OneHotEncoder (spark = False) processing on the service _ class, and performing normalization processing on other characteristics by using MinMaxScaler ();
further, feature selection is performed on the time prediction model. And using a forward step-by-step method, taking R2 as a feature scoring standard, using an adaboost regression model with parameters of max _ depth =36, n _ estimators =50 and learning _ rate =0.8 for the normalized feature data set to be trained, continuously increasing the features with the highest scoring rise amplitude until no features can make the score rise, and taking the corresponding features with the highest scoring in the 100 leave-out method training results as new training features to obtain the training set to be grouped.
S332: and grouping the training sets to be grouped to obtain a first feature set and a second feature set and a corresponding first test data set and a second test data set.
In the present embodiment, the first feature set and the second feature set refer to feature data used for training and testing the temporal prediction model. The first test dataset and the second volume dataset are datasets used to verify the accuracy of the trained temporal prediction model.
Specifically, the first feature set x _ train, the first test data set x _ test, the second feature set y _ train, and the second test data set y _ test are divided by train _ test _ split (test _ size =0.3, random _ state = seed).
S333: and training by using the first feature set of the Adaboost regression algorithm to obtain a corresponding training result, and performing first precision adjustment by using the second feature set and the training result to obtain the model to be tested.
In this embodiment, the Adaboost regression algorithm is an iterative algorithm, and the core idea is to train different classifiers (weak classifiers) for the same training set, and then to assemble these weak classifiers to form a stronger final classifier (strong classifier), i.e., the temporal prediction model in this embodiment. The first accuracy adjustment is a step of adjusting the accuracy of the trained model for the first time. The model to be tested is a model which needs to be further tested after being trained by an Adaboost regression algorithm.
Specifically, before training, the PCA is used for dimensionality reduction on the first training set and the second training set, and the data after PCA dimensionality reduction is returned. Further, the first feature set x _ train is trained by using an AdaBoostRegessor in an Adaboost regression algorithm to obtain a corresponding training result, the second feature set y _ train is compared with the training result, the number of prediction error intervals is counted to serve as an evaluation standard of the model, the model is adjusted step by step until the accuracy requirement standard is met, and the training model is reserved to serve as a model to be tested.
S334: and inputting the first test data set to the model to be tested to obtain a corresponding test result, and performing second precision adjustment on the test result by using the second test data set to obtain a time prediction model.
Specifically, a first test data set x _ test is input to a trained model to be tested for training to obtain a corresponding test result prediction _ test, a second test data set y _ test and the test result prediction _ test are scored, the fitting condition of the model is detected, the model is gradually adjusted until the required accuracy is met, and the adaboost regression prediction model is stored as a time prediction model.
In an embodiment, as shown in fig. 5, in step S331, preprocessing a data set to be trained to obtain a training set to be grouped, specifically includes the following steps:
s3311: and acquiring user handling data from the data set to be trained.
Specifically, the training features and the target set are divided in the to-be-trained set after the outliers are deleted, and corresponding identifiers are set according to the behavior data of the user and the data of the office hall in the data in step S30, for example: [ service _ class, waiting _ numbers, Big _ waiting _ numbers, disabling _ numbers, Big _ disabling _ numbers, Avg _ disable _ time, Big _ Avg _ disable _ time, Avg _ disabling _ time, Avg _ calltime, State ] as training features of the model, i.e., user-managed data, [ Wait _ time ] as the object set of the model.
S3312: and taking the user handling data as a training set to be grouped.
Specifically, the user transaction data is used as a training set to be grouped.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
Example two:
in one embodiment, a queuing time prediction apparatus is provided, and the queuing time prediction apparatus corresponds to the queuing time prediction method in the above embodiment one to one. As shown in fig. 6, the queuing time prediction apparatus includes a request acquisition module 10, a data acquisition module 20, a calculation module 30, and a time prediction module 40. The functional modules are explained in detail as follows:
the request acquisition module 10 is configured to acquire a service type to be handled from the queuing request when the queuing request is acquired;
the data acquisition module 20 is used for acquiring the queued personnel data according to the service type to be managed;
the calculation module 30 is used for inputting the queued personnel data into a preset time prediction model for calculation to obtain a corresponding calculation result;
and the time prediction module 40 is used for obtaining a queuing time prediction result corresponding to the type of the service to be managed according to the calculation result.
Preferably, the queuing time predicting apparatus further includes:
the historical data acquisition module 31 is configured to acquire historical monitoring data and acquire corresponding user behavior data from the historical monitoring data according to the transaction type;
the classification module 32 is used for classifying the user behavior data according to the transaction service types to obtain a data set to be trained;
and the training module 33 is configured to train the data set to be trained class by class to obtain a time prediction model.
Preferably, the historical data acquisition module 31 includes:
a vacancy data acquisition submodule 311, configured to acquire vacancy attribute data from historical monitoring data;
and the vacancy data processing sub-module 312 is configured to perform corresponding processing on the historical monitoring data according to the number of vacancy attribute data, so as to obtain user behavior data corresponding to each transaction type.
Preferably, the training module 33 comprises:
the data preprocessing submodule 331 is configured to preprocess a to-be-trained data set to obtain a to-be-grouped training set;
the grouping submodule 332 is configured to group training sets to be grouped to obtain a first feature set and a second feature set, and a corresponding first test data set and a corresponding second test data set;
the training submodule 333 is configured to perform training using the first feature set of the Adaboost regression algorithm to obtain a corresponding training result, and perform first precision adjustment using the second feature set and the training result to obtain a model to be tested;
the testing submodule 334 is configured to input the first testing data set to the model to be tested to obtain a corresponding testing result, and perform a second precision adjustment on the testing result by using the second testing data set to obtain a time prediction model.
Preferably, the data preprocessing sub-module 331 includes:
a transaction data obtaining unit 3311, configured to obtain user transaction data from the data set to be trained;
a training set obtaining unit 3312, configured to use the user transaction data as a training set to be grouped.
For the specific definition of the queuing time prediction device, reference may be made to the above definition of the queuing time prediction method, which is not described herein again. The modules in the queuing time prediction device can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
Example three:
in one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 7. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing historical monitoring data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a queuing time prediction method.
In one embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
s10: when a queuing request is obtained, obtaining the type of the service to be transacted from the queuing request;
s20: acquiring queued personnel data according to the type of the service to be managed;
s30: inputting the data of the queued personnel into a preset time prediction model for calculation to obtain a corresponding calculation result;
s40: and acquiring a queuing time prediction result corresponding to the type of the service to be managed according to the calculation result.
Example four:
in one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
s10: when a queuing request is obtained, obtaining the type of the service to be transacted from the queuing request;
s20: acquiring queued personnel data according to the type of the service to be managed;
s30: inputting the data of the queued personnel into a preset time prediction model for calculation to obtain a corresponding calculation result;
s40: and acquiring a queuing time prediction result corresponding to the type of the service to be managed according to the calculation result.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (10)
1. A queuing time prediction method, comprising:
s10: when a queuing request is obtained, obtaining the type of the service to be transacted from the queuing request;
s20: acquiring data of queued personnel according to the type of the service to be handled;
s30: inputting the queued personnel data into a preset time prediction model for calculation to obtain a corresponding calculation result;
s40: and acquiring a queuing time prediction result corresponding to the type of the service to be managed according to the calculation result.
2. A queuing time prediction method as claimed in claim 1 wherein prior to step S30, the queuing time prediction method further comprises:
s31: acquiring historical monitoring data, and acquiring corresponding user behavior data from the historical monitoring data according to the transaction type;
s32: classifying the user behavior data according to the transaction service type to obtain a data set to be trained;
s33: and training the data set to be trained class by class to obtain the time prediction model.
3. A queuing time prediction method as claimed in claim 2 wherein step S31 comprises:
s311: acquiring vacancy attribute data from the historical monitoring data;
s312: and correspondingly processing the historical monitoring data according to the number of the vacancy attribute data to obtain user behavior data corresponding to each transacted service type.
4. A queuing time prediction method as claimed in claim 2 wherein step S33 comprises:
s331: preprocessing the data set to be trained to obtain a training set to be grouped;
s332: grouping the training sets to be grouped to obtain a first feature set and a second feature set and a corresponding first test data set and a second test data set;
s333: training the first feature set by using an Adaboost regression algorithm to obtain a corresponding training result, and performing first precision adjustment by using the second feature set and the training result to obtain a model to be tested;
s334: and inputting the first test data set to the model to be tested to obtain a corresponding test result, and performing second precision adjustment on the test result by using the second test data set to obtain the time prediction model.
5. A queuing time prediction method as claimed in claim 4 wherein step S331 comprises:
s3311: acquiring user handling data from the data set to be trained;
s3312: and taking the user handling data as the training set to be grouped.
6. A queuing time prediction apparatus, comprising:
the request acquisition module is used for acquiring the type of the service to be handled from the queuing request when the queuing request is acquired;
the data acquisition module is used for acquiring queued personnel data according to the type of the service to be managed;
the calculation module is used for inputting the queued personnel data into a preset time prediction model for calculation to obtain a corresponding calculation result;
and the time prediction module is used for acquiring a queuing time prediction result corresponding to the type of the service to be managed according to the calculation result.
7. A queuing time prediction apparatus as claimed in claim 6 wherein the queuing time prediction apparatus further comprises:
the historical data acquisition module is used for acquiring historical monitoring data and acquiring corresponding user behavior data from the historical monitoring data according to the transaction type;
the classification module is used for classifying the user behavior data according to the transaction service type to obtain a data set to be trained;
and the training module is used for training the data set to be trained class by class to obtain the time prediction model.
8. A queuing time prediction apparatus as claimed in claim 7 wherein the historical data acquisition module comprises:
the vacancy data acquisition submodule is used for acquiring vacancy attribute data from the historical monitoring data;
and the vacancy data processing submodule is used for correspondingly processing the historical monitoring data according to the number of the vacancy attribute data to obtain user behavior data corresponding to each business handling type.
9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the queuing time prediction method according to any of claims 1 to 5 when executing the computer program.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the queuing time prediction method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911156629.4A CN110942190A (en) | 2019-11-22 | 2019-11-22 | Queuing time prediction method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911156629.4A CN110942190A (en) | 2019-11-22 | 2019-11-22 | Queuing time prediction method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110942190A true CN110942190A (en) | 2020-03-31 |
Family
ID=69907509
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911156629.4A Pending CN110942190A (en) | 2019-11-22 | 2019-11-22 | Queuing time prediction method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110942190A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN111626586A (en) * | 2020-05-21 | 2020-09-04 | 广西电网有限责任公司 | Data quality detection method and device, computer equipment and storage medium |
| CN111696533A (en) * | 2020-06-28 | 2020-09-22 | 中国银行股份有限公司 | Network point robot self-adjusting method and device |
| CN111988478A (en) * | 2020-09-02 | 2020-11-24 | 深圳壹账通智能科技有限公司 | Incoming call management method, device, server and storage medium |
| CN112163686A (en) * | 2020-10-23 | 2021-01-01 | 江西师范大学 | Waiting response time confidence interval prediction method and device for G/G/1 queuing system |
| CN112801372A (en) * | 2021-01-29 | 2021-05-14 | 北京嘀嘀无限科技发展有限公司 | Data processing method and device, electronic equipment and readable storage medium |
| CN115619356A (en) * | 2022-12-16 | 2023-01-17 | 广州明动软件股份有限公司 | Data automatic synchronization convergence and distribution method and system based on event public data |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102521909A (en) * | 2011-12-07 | 2012-06-27 | 广州广电运通金融电子股份有限公司 | Queuing service processing method and system |
| CN102779367A (en) * | 2012-07-13 | 2012-11-14 | 南京信息工程大学 | Scheduling method of queuing processing system and queuing machine for prediction of service processing time |
| CN109087435A (en) * | 2018-08-13 | 2018-12-25 | 中国联合网络通信集团有限公司 | The prediction technique and queuing system of queuing time |
| US20190096010A1 (en) * | 2015-09-23 | 2019-03-28 | International Business Machines Corporation | Real-time wait estimation and prediction via embedded sensors |
| CN109783227A (en) * | 2018-12-13 | 2019-05-21 | 平安科技（深圳）有限公司 | Method for allocating tasks, device, system and computer readable storage medium |
-
2019
- 2019-11-22 CN CN201911156629.4A patent/CN110942190A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102521909A (en) * | 2011-12-07 | 2012-06-27 | 广州广电运通金融电子股份有限公司 | Queuing service processing method and system |
| CN102779367A (en) * | 2012-07-13 | 2012-11-14 | 南京信息工程大学 | Scheduling method of queuing processing system and queuing machine for prediction of service processing time |
| US20190096010A1 (en) * | 2015-09-23 | 2019-03-28 | International Business Machines Corporation | Real-time wait estimation and prediction via embedded sensors |
| CN109087435A (en) * | 2018-08-13 | 2018-12-25 | 中国联合网络通信集团有限公司 | The prediction technique and queuing system of queuing time |
| CN109783227A (en) * | 2018-12-13 | 2019-05-21 | 平安科技（深圳）有限公司 | Method for allocating tasks, device, system and computer readable storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 韦鹏程，冉维，段昂: "《大数据巨量分析与机器学习的整合与开发》", 31 May 2017, 电子科技大学出版社 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN111626586A (en) * | 2020-05-21 | 2020-09-04 | 广西电网有限责任公司 | Data quality detection method and device, computer equipment and storage medium |
| CN111626586B (en) * | 2020-05-21 | 2023-10-31 | 广西电网有限责任公司 | Data quality detection method, device, computer equipment and storage medium |
| CN111696533A (en) * | 2020-06-28 | 2020-09-22 | 中国银行股份有限公司 | Network point robot self-adjusting method and device |
| CN111696533B (en) * | 2020-06-28 | 2023-02-21 | 中国银行股份有限公司 | Network point robot self-adjusting method and device |
| CN111988478A (en) * | 2020-09-02 | 2020-11-24 | 深圳壹账通智能科技有限公司 | Incoming call management method, device, server and storage medium |
| CN112163686A (en) * | 2020-10-23 | 2021-01-01 | 江西师范大学 | Waiting response time confidence interval prediction method and device for G/G/1 queuing system |
| CN112801372A (en) * | 2021-01-29 | 2021-05-14 | 北京嘀嘀无限科技发展有限公司 | Data processing method and device, electronic equipment and readable storage medium |
| CN112801372B (en) * | 2021-01-29 | 2024-04-19 | 北京嘀嘀无限科技发展有限公司 | Data processing method, device, electronic equipment and readable storage medium |
| CN115619356A (en) * | 2022-12-16 | 2023-01-17 | 广州明动软件股份有限公司 | Data automatic synchronization convergence and distribution method and system based on event public data |
| CN115619356B (en) * | 2022-12-16 | 2023-03-21 | 广州明动软件股份有限公司 | Data automatic synchronization convergence and distribution method and system based on event public data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110942190A (en) | Queuing time prediction method and device, computer equipment and storage medium | |
| US10943186B2 (en) | Machine learning model training method and device, and electronic device | |
| US10805151B2 (en) | Method, apparatus, and storage medium for diagnosing failure based on a service monitoring indicator of a server by clustering servers with similar degrees of abnormal fluctuation | |
| CN109446068B (en) | Interface test method, device, computer equipment and storage medium | |
| CN111177714B (en) | Abnormal behavior detection method and device, computer equipment and storage medium | |
| CN109992601B (en) | To-do information pushing method and device and computer equipment | |
| JP6869347B2 (en) | Risk control event automatic processing method and equipment | |
| WO2020062702A9 (en) | Method and device for sending text messages, computer device and storage medium | |
| CN112329843B (en) | Call data processing method, device, equipment and storage medium based on decision tree | |
| CN110570312B (en) | Sample data acquisition method and device, computer equipment and readable storage medium | |
| CN112819631B (en) | Service data processing method, device, computer equipment and storage medium | |
| CN112329811A (en) | Abnormal account identification method and device, computer equipment and storage medium | |
| CN111131290A (en) | Flow data processing method and device | |
| CN108845869B (en) | Concurrent request control method, device, computer equipment and storage medium | |
| CN111163073A (en) | Flow data processing method and device | |
| CN110363381B (en) | Information processing method and device | |
| CN113254250B (en) | Database server abnormal cause detection method, device, equipment and storage medium | |
| CN107871213B (en) | Transaction behavior evaluation method, device, server and storage medium | |
| CN115658620B (en) | Data authorization sharing method and system based on big data | |
| CN111147441A (en) | Method and device for automatically detecting fraud behaviors of online ticket purchasing and readable storage medium | |
| CN116208513A (en) | Gateway health degree prediction method and device | |
| CN110969430B (en) | Suspicious user identification method, suspicious user identification device, computer equipment and storage medium | |
| CN114676422A (en) | Resource access abnormity detection method, device and equipment | |
| CN112395119B (en) | Abnormal data processing method, device, server and storage medium | |
| CN114003339A (en) | Detection method and device for zombie virtual machine, computer equipment and storage medium |
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 |