CN112668936A - Airport guarantee work distribution method and device - Google Patents
Airport guarantee work distribution method and device Download PDFInfo
- Publication number
- CN112668936A CN112668936A CN202110062626.5A CN202110062626A CN112668936A CN 112668936 A CN112668936 A CN 112668936A CN 202110062626 A CN202110062626 A CN 202110062626A CN 112668936 A CN112668936 A CN 112668936A
- Authority
- CN
- China
- Prior art keywords
- guarantee
- support
- task
- information database
- splicing
- 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
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000012545 processing Methods 0.000 claims abstract description 27
- 230000008569 process Effects 0.000 claims abstract description 18
- 238000012549 training Methods 0.000 claims description 35
- 238000011156 evaluation Methods 0.000 claims description 22
- 238000010276 construction Methods 0.000 claims description 17
- 238000012163 sequencing technique Methods 0.000 claims description 13
- 238000013527 convolutional neural network Methods 0.000 claims description 12
- 238000013507 mapping Methods 0.000 claims description 8
- 238000011176 pooling Methods 0.000 claims description 7
- 238000011161 development Methods 0.000 abstract description 5
- 230000010006 flight Effects 0.000 description 7
- 230000006870 function Effects 0.000 description 7
- 238000012360 testing method Methods 0.000 description 7
- 238000013528 artificial neural network Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000012795 verification Methods 0.000 description 5
- 230000009471 action Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000013480 data collection Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an airport security work distribution method and device, wherein the method comprises the following steps: receiving a real-time guarantee task, wherein the real-time guarantee task comprises a guarantee type and a guarantee requirement; inputting the real-time guarantee task into a pre-trained guarantee dispatching model; and outputting the guarantee staff matched with the real-time guarantee task by the guarantee dispatching model based on the guarantee type and the guarantee requirement. According to the implementation scheme, based on a pre-trained guarantee dispatching model, the guarantee type and guarantee requirements of a real-time guarantee task are combined, the guarantee task can be automatically matched with guarantee personnel, and the guarantee personnel matched with the guarantee task are guaranteed to have guarantee skills for processing the guarantee task; due to the full-automatic execution, the realization process is high in efficiency and matching accuracy, and can adapt to the rapid development of the aviation industry and meet the complex requirements of airport guarantee tasks.
Description
Technical Field
The invention relates to an artificial intelligence technology, in particular to an airport security work distribution method and device.
Background
The airport flight release normal rate is an important index for reflecting the comprehensive guarantee capability of the airport ground and is also one of important indexes for the industry governing department to check the airport regularly. The flight normality management is complex system work, is point-wide, needs all the guarantee units of a company to be linked up and down, and continuously explores and researches from internal fine flight management and control to external operation coordination.
Under the condition of ensuring the task determination, the reasonable and accurate division of labor of workers is ensured, and the method has important significance for ensuring that all the guarantee links of the flights are closely connected, improving the guarantee efficiency, avoiding the delay of the subsequent departure flights caused by station-passing guarantee and improving the normal rate of airport release.
At present, the allocation of the guarantee tasks of the airport is mainly completed by manual allocation, the working efficiency is low, and the quick development of the aviation industry and the increasingly complex airport guarantee tasks are difficult to adapt.
Disclosure of Invention
In view of this, the present invention provides the following technical solutions:
an airport security work allocation method comprises the following steps:
receiving a real-time guarantee task, wherein the real-time guarantee task comprises a guarantee type and a guarantee requirement;
inputting the real-time guarantee task into a pre-trained guarantee dispatching model;
and outputting the guarantee staff matched with the real-time guarantee task by the guarantee dispatching model based on the guarantee type and the guarantee requirement.
Optionally, the training process of the guarantee dispatch model includes:
constructing a support personnel information database;
constructing a guarantee task information database;
splicing and mapping the support personnel information database and the support task information database based on a preset rule to obtain a spliced database;
and inputting the data of the spliced database serving as training data into a convolutional neural network, and training to obtain a guarantee dispatching model.
Optionally, the splicing and mapping processing is performed on the support staff information database and the support task information database based on a preset rule to obtain a spliced database, including:
for the support personnel contained in the support personnel information database, performing descending sequencing based on the capability evaluation value;
for the guarantee tasks contained in the guarantee task information database, performing descending sequencing based on the work difficulty evaluation values of the guarantee tasks;
and correspondingly splicing the sequenced support staff information database and the sequenced support task information database to obtain a spliced database.
Optionally, correspondingly splicing the sequenced support staff information database and the sequenced support task information database to obtain a spliced database, including:
and correspondingly splicing the sequenced support staff information database and the sequenced support task information database according to the support type, so that the support staff has support skills required by the support tasks forming a splicing relation with the support staff.
Optionally, a DropOut layer is provided after the pooling layer of the convolutional neural network to ensure the task allocation rate.
Optionally, the loss function used for ensuring the dispatching model is a cross entropy loss function.
An airport security work distribution apparatus comprising:
the task receiving module is used for receiving a real-time guarantee task, and the real-time guarantee task comprises a guarantee type and a guarantee requirement;
the task input module is used for inputting the real-time guarantee task into a pre-trained guarantee dispatching model;
and the guarantee matching module exists in the guarantee dispatching model and is used for outputting guarantee workers matched with the real-time guarantee tasks based on the guarantee types and the guarantee requirements.
Optionally, the guarantee dispatching model is obtained by training a training device, where the training device includes:
the system comprises a first construction module, a second construction module and a third construction module, wherein the first construction module is used for constructing a support personnel information database;
the second construction module is used for constructing a guarantee task information database;
the splicing processing module is used for carrying out splicing mapping processing on the support personnel information database and the support task information database based on a preset rule to obtain a splicing database;
and the model training module is used for inputting the data of the splicing database into a convolutional neural network as training data and training to obtain a guarantee dispatching model.
Optionally, the splicing processing module includes:
the first processing module is used for sequencing the security personnel contained in the security personnel information database in a descending order based on the capability evaluation value;
the second processing module is used for sequencing guarantee tasks contained in the guarantee task information database in a descending order based on the work difficulty evaluation values of the guarantee tasks;
and the splicing processing submodule is used for correspondingly splicing the sequenced support staff information database and the sequenced support task information database to obtain a spliced database.
Optionally, the splicing processing sub-module is specifically configured to: and correspondingly splicing the sequenced support staff information database and the sequenced support task information database according to the support type, so that the support staff has support skills required by the support tasks forming a splicing relation with the support staff.
Compared with the prior art, the embodiment of the invention discloses an airport security work allocation method and device, and the method comprises the following steps: receiving a real-time guarantee task, wherein the real-time guarantee task comprises a guarantee type and a guarantee requirement; inputting the real-time guarantee task into a pre-trained guarantee dispatching model; and outputting the guarantee staff matched with the real-time guarantee task by the guarantee dispatching model based on the guarantee type and the guarantee requirement. According to the implementation scheme, based on a pre-trained guarantee dispatching model, the guarantee type and guarantee requirements of a real-time guarantee task are combined, the guarantee task can be automatically matched with guarantee personnel, and the guarantee personnel matched with the guarantee task are guaranteed to have guarantee skills for processing the guarantee task; due to the full-automatic execution, the realization process is high in efficiency and matching accuracy, and can adapt to the rapid development of the aviation industry and meet the complex requirements of airport guarantee tasks.
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 flowchart of an airport security work allocation method disclosed in an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a process for training a guarantee dispatch model according to an embodiment of the present invention;
FIG. 3 is a diagram of an implementation structure of an airport security work allocation scheme disclosed in an embodiment of the present invention;
FIG. 4 is a schematic diagram of a model structure of a convolutional neural network disclosed in an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an airport security work distribution device disclosed in the embodiment of the present invention.
Detailed Description
For the sake of reference and clarity, the descriptions, abbreviations or abbreviations of the technical terms used hereinafter are summarized as follows:
DropOut: when a complex feedforward neural network is trained on a small data set, overfitting tends to result. To prevent over-fitting, the performance of the neural network can be improved by blocking the co-action of the feature detectors, DropOut being an algorithm that prevents over-fitting.
Full connection layer: fully connected layers (FC) act as "classifiers" throughout the convolutional neural network. If we say that operations such as convolutional layers, pooling layers, and activation function layers map raw data to hidden layer feature space, the fully-connected layer serves to map the learned "distributed feature representation" to the sample label space. In actual use, the fully-connected layer may be implemented by a convolution operation.
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.
The embodiment of the application can be applied to electronic equipment, the product form of the electronic equipment is not limited by the application, and the electronic equipment can include but is not limited to a smart phone, a tablet computer, wearable equipment, a Personal Computer (PC), a netbook and the like, and can be selected according to application requirements.
Fig. 1 is a flowchart of an airport security work allocation method disclosed in an embodiment of the present invention, and referring to fig. 1, the airport security work allocation method may include:
step 101: and receiving a real-time guarantee task, wherein the real-time guarantee task comprises a guarantee type and a guarantee requirement.
In an airport scene, the types and requirements of guarantee tasks of different flights may be different, and the guarantee skills mastered by a plurality of guarantee personnel in the airport are different, so that the guarantee tasks and the guarantee personnel need to be reasonably distributed instead of being randomly distributed, and the conditions that the guarantee results do not reach the standard and the guarantee time delays the flight punctual operation and the like which are possibly caused by unreasonable distribution are avoided.
With the continuous increase of airport passenger flow, the actual demand is difficult to meet by adopting a manual guarantee task allocation mode at present. Therefore, in the process of implementing the technical scheme, the inventor considers how to reasonably classify the flight support personnel according to the arrival time of the flight, the efficiency of the support personnel and the skills of the support personnel, then reasonably arranges the classified support personnel in each support task of each flight in real time, reasonably fits the support personnel and the support tasks, and realizes the high-efficiency automation of support task distribution.
Step 102: and inputting the real-time guarantee task into a pre-trained guarantee dispatching model.
After receiving the real-time guarantee task, directly inputting the real-time guarantee task into a pre-trained guarantee dispatching model, so that the guarantee dispatching model automatically matches proper guarantee personnel for the real-time guarantee task according to the previously excavated data characteristics and the current actual guarantee personnel condition.
The training process for ensuring the dispatching model will be described in detail in the following embodiments, and will not be described in detail herein.
Step 103: and outputting the guarantee staff matched with the real-time guarantee task by the guarantee dispatching model based on the guarantee type and the guarantee requirement.
According to the airport guarantee work distribution method, the guarantee type and the guarantee requirement of the real-time guarantee task are combined based on a pre-trained guarantee dispatching model, the guarantee task can be automatically matched with the guarantee personnel, and the guarantee personnel matched with the guarantee task are guaranteed to have the guarantee skills for processing the guarantee task; due to the full-automatic execution, the realization process is high in efficiency and matching accuracy, and can adapt to the rapid development of the aviation industry and meet the complex requirements of airport guarantee tasks.
Fig. 2 is a flowchart of a training process of a guaranteed dispatch model disclosed in an embodiment of the present invention, and with reference to fig. 2, the training process of the guaranteed dispatch model in the above embodiment may include:
step 201: and constructing a support personnel information database.
In this embodiment, firstly, the working capacity of the support staff is evaluated according to the support skills of the support staff and the support data of the history of the support staff, and a support staff information database is established, and the support skills and the capacity evaluation values of the support staff are respectively used as the characteristics of each support staff sample.
Step 202: and constructing a guarantee task information database.
Besides the construction of the support personnel information database, a support task information database is also required to be constructed. In this embodiment, all the guarantee tasks of the scheduled flight are classified, and a guarantee task information database is established according to the task category and the task difficulty.
Step 203: and performing splicing mapping processing on the support personnel information database and the support task information database based on a preset rule to obtain a splicing database.
Specifically, the method may include: for the support personnel contained in the support personnel information database, performing descending sequencing based on the capability evaluation value; for the guarantee tasks contained in the guarantee task information database, performing descending sequencing based on the work difficulty evaluation values of the guarantee tasks; and correspondingly splicing the sequenced support staff information database and the sequenced support task information database to obtain a spliced database.
And classifying and matching the guarantee skills of the support personnel and the guarantee types of the guarantee tasks, and sequencing the support personnel information database and the support task information database in a descending order according to the capability evaluation value and the work difficulty evaluation value in the same type of guarantee tasks. And then splicing the sequenced support staff information database and support task information database, and finishing the support task with high work difficulty assessment value by support staff with the skills according with and high ability assessment value.
Step 204: and inputting the data of the spliced database serving as training data into a convolutional neural network, and training to obtain a guarantee dispatching model.
In order to ensure the optimization of the dispatching model, data (data actually reported by guarantee personnel, such as guarantee task types, start time, end time and the like) needs to be continuously acquired to train and test the distribution process by means of a neural network, so that the reasonable distribution of the guarantee tasks is continuously improved, the relevant skill training is pertinently carried out on the staff on the basis of the distribution result, and the working efficiency of the staff is improved.
Fig. 3 is a structural diagram of an implementation of an airport security work allocation scheme disclosed in an embodiment of the present invention, and technical content disclosed in the above embodiment can be understood by referring to fig. 3.
In the above embodiment, correspondingly splicing the sequenced support staff information database and the sequenced support task information database to obtain a spliced database may include: and correspondingly splicing the sequenced support staff information database and the sequenced support task information database according to the support type, so that the support staff has support skills required by the support tasks forming a splicing relation with the support staff.
A Dropout layer is arranged behind the pooling layer of the convolutional neural network to ensure the task allocation rate.
And the loss function adopted by the guarantee dispatching model is a cross entropy loss function.
In one specific implementation, the complete construction process of the guarantee dispatch model may be as follows:
1. data collection of support personnel information database
And aiming at each guarantee person, respectively collecting the guarantee data of the working skill and the history of the guarantee person, and establishing a guarantee person information database. According to the principle of fairness, justness and reasonability, guarantee data in at least one past month needs to be collected, and staff are evaluated through an evaluation algorithm and the past guarantee data. The evaluation algorithm is as follows:
start → collect the guarantee task assigned by the support personnel in the past → evaluate the difficulty of the guarantee task → collect the time required for the support personnel to complete the guarantee task → output the level of the support personnel's working ability → end.
And after the database is established, performing descending order arrangement on the information database of the support personnel according to the work capacity evaluation result of the support personnel.
2. Provisioning task information database data collection
Different tasks of flights are the same, the same task of the flights is different, and different tasks of the flights have different difficulties, so that different guarantee tasks of different flights in the past year need to be collected to establish a database, daily guarantee tasks are firstly stored in a guarantee task information database, and if special guarantee tasks occur, the guarantee task database is updated. Taking the difficulty of the guarantee task as the characteristic of a guarantee task database, and evaluating the difficulty of the guarantee task through an evaluation algorithm, wherein the evaluation algorithm is as follows:
start → collect the guarantee task → collect the time needed to complete the guarantee task to the support personnel → establish different guarantee task difficulty levels → output the guarantee task difficulty level → end.
And finally, arranging the constructed guarantee task information database in a descending order according to the guarantee task evaluation result.
3. Database stitching
In order to better fit the training and testing process of the neural network, the sequenced support staff information database and the support task information database are spliced according to different support skills or support types, support tasks with high difficulty are distributed to support staff with the support skills and relatively high working capacity, and the support staff and the support task information database are sequentially arranged downwards.
For testing and training of neural networks, for example, on the same data set, the training set and the test set are divided, and it can be determined that 80% of the training set and 20% of the test set are used for evaluating the performance of the model. The training set is used for debugging model test, so that the model achieves a good effect.
For example, guaranteed personnel and guarantee tasks are in an airport, the workload and the working capacity of each guaranteed personnel are different, and the difficulty of the guarantee tasks is different. After the data are collected, the data are fitted and classified by means of a neural network model, so that the matching of the guarantee capability of the guarantee personnel and the task requirements is more reasonable. By continuously providing the test set, the accuracy of the model training is higher and more reasonable.
In this embodiment, the neural network is used as a technical support for the airport dispatching guarantee model, and the spliced database is used as an input of the convolutional neural network. The method comprises convolution, pooling, convolution and pooling, in order to prevent overfitting and guarantee reduction of the task allocation rate, a Dropout layer is added behind the pooling layer to guarantee the task allocation rate, and finally a full-connection layer is arranged, and the model structure passing through each layer is shown in a figure 4.
In one implementation, the ratio of 6: 2: 2, in order to improve the accuracy of task allocation and minimize loss, the loss function of the method can adopt a cross entropy loss function, and the formula is as follows:
in the implementation, the accuracy, precision and recall rate of the combination of the support personnel and the support tasks are used as the basis of classification evaluation. Wherein True Positive (True, TP): predicting the positive class as a positive class number; true Negative, TN: predicting a negative class as a negative class number; false Positive (FP): predicting the negative class as a positive class number false alarm (Type I error); false Negative (FN): predict positive class as negative class number → false negative (Type II error). Table 1 is a prediction case table.
TABLE 1 prediction cases Table
The accuracy is as follows:
Acc=(TP+TN)/(TP+FP+TN+FN)
the precision ratio is as follows:
Pre=TP/(TP+FP)
the recall ratio is as follows:
Recall=TP/(TP+FN)
and (3) performing effect verification on the model, distributing all guarantee tasks in 30 days of a certain airport by using the obtained model, and verifying the delay rate and the airport release result as shown in a table 2.
TABLE 2 verification results table
Days of validation | Delay rate | Tendency of airport release |
1 < verification days < ═ 5 | 33.5% | Rise up |
5 < verification days < ═ 15 | 32.1% | Rise up |
15 < verification days < ═ 30 | 30.2% | Rise up |
The delay rate is as follows: the ratio of delayed tasks to total number of tasks.
The guarantee dispatching model disclosed by the embodiment of the invention has stronger self-learning capability, the training degree of the model is higher and higher along with the increase of the service time, the generated effect is more and more obvious, the delay rate of the task is ensured to be lower and lower, the airport clearance rate is continuously improved, and better experience is brought to passengers.
While, for purposes of simplicity of explanation, the foregoing method embodiments have been described as a series of acts or combination of acts, it will be appreciated by those skilled in the art that the present invention is not limited by the illustrated ordering of acts, as some steps may occur in other orders or concurrently with other steps in accordance with the invention. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required by the invention.
The method is described in detail in the embodiments disclosed above, and the method of the present invention can be implemented by various types of apparatuses, so that the present invention also discloses an apparatus, and the following detailed description will be given of specific embodiments.
Fig. 5 is a schematic structural diagram of an airport security work distribution apparatus according to an embodiment of the present invention, and referring to fig. 5, the airport security work distribution apparatus 50 may include:
the task receiving module 501 is configured to receive a real-time guarantee task, where the real-time guarantee task includes a guarantee type and a guarantee requirement.
A task input module 502, configured to input the real-time guarantee task into a pre-trained guarantee dispatching model.
And the guarantee matching module 503 exists in the guarantee dispatching model and is used for outputting guarantee workers matched with the real-time guarantee tasks based on the guarantee types and the guarantee requirements.
The airport guarantee work distribution device provided by the embodiment is based on a pre-trained guarantee dispatching model, combines the guarantee type and guarantee requirement of a real-time guarantee task, can automatically realize the matching of the guarantee task to guarantee personnel, and guarantees that the guarantee personnel matched with the guarantee task have the guarantee skill for processing the guarantee task; due to the full-automatic execution, the realization process is high in efficiency and matching accuracy, and can adapt to the rapid development of the aviation industry and meet the complex requirements of airport guarantee tasks.
In one implementation, the guarantee dispatch model is trained by a training device, and the training device includes: the system comprises a first construction module, a second construction module and a third construction module, wherein the first construction module is used for constructing a support personnel information database; the second construction module is used for constructing a guarantee task information database; the splicing processing module is used for carrying out splicing mapping processing on the support personnel information database and the support task information database based on a preset rule to obtain a splicing database; and the model training module is used for inputting the data of the splicing database into a convolutional neural network as training data and training to obtain a guarantee dispatching model.
In one implementation, the splicing processing module includes: the first processing module is used for sequencing the security personnel contained in the security personnel information database in a descending order based on the capability evaluation value; the second processing module is used for sequencing guarantee tasks contained in the guarantee task information database in a descending order based on the work difficulty evaluation values of the guarantee tasks; and the splicing processing submodule is used for correspondingly splicing the sequenced support staff information database and the sequenced support task information database to obtain a spliced database.
In one implementation, the splicing processing sub-module is specifically configured to: and correspondingly splicing the sequenced support staff information database and the sequenced support task information database according to the support type, so that the support staff has support skills required by the support tasks forming a splicing relation with the support staff.
The specific implementation of the above airport security work allocation apparatus and its included or related modules may refer to the content introduction of the related parts in the method embodiments, and will not be described repeatedly herein.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
It is further noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, 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.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
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.
Claims (10)
1. An airport security work allocation method, comprising:
receiving a real-time guarantee task, wherein the real-time guarantee task comprises a guarantee type and a guarantee requirement;
inputting the real-time guarantee task into a pre-trained guarantee dispatching model;
and outputting the guarantee staff matched with the real-time guarantee task by the guarantee dispatching model based on the guarantee type and the guarantee requirement.
2. The airport security work allocation method of claim 1, wherein said training process of the security dispatch model comprises:
constructing a support personnel information database;
constructing a guarantee task information database;
splicing and mapping the support personnel information database and the support task information database based on a preset rule to obtain a spliced database;
and inputting the data of the spliced database serving as training data into a convolutional neural network, and training to obtain a guarantee dispatching model.
3. The airport security work allocation method of claim 2, wherein the splicing mapping processing of the support personnel information database and the security mission information database based on preset rules to obtain a spliced database comprises:
for the support personnel contained in the support personnel information database, performing descending sequencing based on the capability evaluation value;
for the guarantee tasks contained in the guarantee task information database, performing descending sequencing based on the work difficulty evaluation values of the guarantee tasks;
and correspondingly splicing the sequenced support staff information database and the sequenced support task information database to obtain a spliced database.
4. The airport security work allocation method of claim 3, wherein correspondingly splicing the sequenced support personnel information database and the sequenced support task information database to obtain a spliced database comprises:
and correspondingly splicing the sequenced support staff information database and the sequenced support task information database according to the support type, so that the support staff has support skills required by the support tasks forming a splicing relation with the support staff.
5. The airport security work allocation method of any of claims 2-4, wherein said convolutional neural network has a DropOut layer after the pooling layer to ensure mission allocation rate.
6. The airport security work allocation method of claim 1, wherein the loss function employed by the security dispatch model is a cross entropy loss function.
7. An airport security work distribution apparatus, comprising:
the task receiving module is used for receiving a real-time guarantee task, and the real-time guarantee task comprises a guarantee type and a guarantee requirement;
the task input module is used for inputting the real-time guarantee task into a pre-trained guarantee dispatching model;
and the guarantee matching module exists in the guarantee dispatching model and is used for outputting guarantee workers matched with the real-time guarantee tasks based on the guarantee types and the guarantee requirements.
8. The airport security work distribution apparatus of claim 7, wherein the security dispatch model is trained by a training apparatus comprising:
the system comprises a first construction module, a second construction module and a third construction module, wherein the first construction module is used for constructing a support personnel information database;
the second construction module is used for constructing a guarantee task information database;
the splicing processing module is used for carrying out splicing mapping processing on the support personnel information database and the support task information database based on a preset rule to obtain a splicing database;
and the model training module is used for inputting the data of the splicing database into a convolutional neural network as training data and training to obtain a guarantee dispatching model.
9. The airport security work distribution apparatus of claim 8, wherein the stitching processing module comprises:
the first processing module is used for sequencing the security personnel contained in the security personnel information database in a descending order based on the capability evaluation value;
the second processing module is used for sequencing guarantee tasks contained in the guarantee task information database in a descending order based on the work difficulty evaluation values of the guarantee tasks;
and the splicing processing submodule is used for correspondingly splicing the sequenced support staff information database and the sequenced support task information database to obtain a spliced database.
10. The airport security work distribution apparatus of claim 9, wherein the stitching process sub-module is specifically configured to: and correspondingly splicing the sequenced support staff information database and the sequenced support task information database according to the support type, so that the support staff has support skills required by the support tasks forming a splicing relation with the support staff.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110062626.5A CN112668936A (en) | 2021-01-18 | 2021-01-18 | Airport guarantee work distribution method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110062626.5A CN112668936A (en) | 2021-01-18 | 2021-01-18 | Airport guarantee work distribution method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112668936A true CN112668936A (en) | 2021-04-16 |
Family
ID=75415586
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110062626.5A Pending CN112668936A (en) | 2021-01-18 | 2021-01-18 | Airport guarantee work distribution method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112668936A (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6938048B1 (en) * | 2001-11-14 | 2005-08-30 | Qgenisys, Inc. | Universal task management system, method and product for automatically managing remote workers, including automatically training the workers |
CN106022628A (en) * | 2016-05-27 | 2016-10-12 | 内蒙古自治区民航机场集团有限责任公司 | Airport work distributing, monitoring and scheduling system based on mobile terminals, and method thereof |
CN106022629A (en) * | 2016-05-27 | 2016-10-12 | 内蒙古自治区民航机场集团有限责任公司 | Guarantee task automatic generating system and guarantee task automatic generating method |
CN109165782A (en) * | 2018-08-15 | 2019-01-08 | 民航成都信息技术有限公司 | Civil Aviation Airport ground service support personnel dispatching method and its system |
CN110796343A (en) * | 2019-10-10 | 2020-02-14 | 深圳中集智能科技有限公司 | Intelligent dispatching method, device and system |
CN111199354A (en) * | 2019-12-31 | 2020-05-26 | 广东电网有限责任公司 | Hopfield neural network-based power communication network operation and maintenance work order scheduling method |
CN111695747A (en) * | 2019-03-13 | 2020-09-22 | 鸿富锦精密电子(成都)有限公司 | Intelligent dispatching method and device and computer readable storage medium |
CN111950910A (en) * | 2020-08-13 | 2020-11-17 | 青岛民航凯亚***集成有限公司 | Airport guarantee vehicle task scheduling method based on DBSCAN-GA |
-
2021
- 2021-01-18 CN CN202110062626.5A patent/CN112668936A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6938048B1 (en) * | 2001-11-14 | 2005-08-30 | Qgenisys, Inc. | Universal task management system, method and product for automatically managing remote workers, including automatically training the workers |
CN106022628A (en) * | 2016-05-27 | 2016-10-12 | 内蒙古自治区民航机场集团有限责任公司 | Airport work distributing, monitoring and scheduling system based on mobile terminals, and method thereof |
CN106022629A (en) * | 2016-05-27 | 2016-10-12 | 内蒙古自治区民航机场集团有限责任公司 | Guarantee task automatic generating system and guarantee task automatic generating method |
CN109165782A (en) * | 2018-08-15 | 2019-01-08 | 民航成都信息技术有限公司 | Civil Aviation Airport ground service support personnel dispatching method and its system |
CN111695747A (en) * | 2019-03-13 | 2020-09-22 | 鸿富锦精密电子(成都)有限公司 | Intelligent dispatching method and device and computer readable storage medium |
CN110796343A (en) * | 2019-10-10 | 2020-02-14 | 深圳中集智能科技有限公司 | Intelligent dispatching method, device and system |
CN111199354A (en) * | 2019-12-31 | 2020-05-26 | 广东电网有限责任公司 | Hopfield neural network-based power communication network operation and maintenance work order scheduling method |
CN111950910A (en) * | 2020-08-13 | 2020-11-17 | 青岛民航凯亚***集成有限公司 | Airport guarantee vehicle task scheduling method based on DBSCAN-GA |
Non-Patent Citations (1)
Title |
---|
冯霞,唐菱,卢敏: ""面向层次资质的机场外航服务人员排班研究"", 《交通运输***工程与信息》, vol. 19, no. 02, 30 April 2019 (2019-04-30), pages 231 - 237 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Karaşan et al. | Location selection of electric vehicles charging stations by using a fuzzy MCDM method: a case study in Turkey | |
KR102026304B1 (en) | Esg based enterprise assessment device and operating method thereof | |
Solis et al. | Perspectives to predict dropout in university students with machine learning | |
Calleja et al. | Methodological approaches to supply chain design | |
CN107766929B (en) | Model analysis method and device | |
CN110852881B (en) | Risk account identification method and device, electronic equipment and medium | |
CN104766144A (en) | Order forecasting method and system | |
CN104050361A (en) | Intelligent analysis early warning method for dangerousness tendency of prison persons serving sentences | |
CN108564423A (en) | Malice occupy-place recognition methods, system, equipment and the storage medium of ticketing service order | |
CN116205355B (en) | Power load prediction method, device and storage medium | |
CN110147389A (en) | Account number treating method and apparatus, storage medium and electronic device | |
CN111986027A (en) | Abnormal transaction processing method and device based on artificial intelligence | |
CN109508807A (en) | Lottery user liveness prediction technique, system and terminal device, storage medium | |
Feng et al. | Civil aircraft spare parts prediction and configuration management techniques: review and prospect | |
Wang et al. | RETRACTED ARTICLE: Efficiency optimization and simulation to manufacturing and service systems based on manufacturing technology Just-In-Time | |
US20220156862A1 (en) | System and method for analyzing grantability of a legal filing | |
Yang et al. | Developing a rough set based approach for group decision making based on determining weights of decision makers with interval numbers | |
CN113421168A (en) | Intelligent machining system for mechanical basic parts | |
Dotoli et al. | Integrated network design of agile resource-efficient supply chains under uncertainty | |
CN112668936A (en) | Airport guarantee work distribution method and device | |
Triantis | Fuzzy non-radial data envelopment analysis (DEA) measures of technical efficiency in support of an integrated performance measurement system | |
CN116187675A (en) | Task allocation method, device, equipment and storage medium | |
CN114418450A (en) | Data processing method and device | |
CN109146549A (en) | Lottery user product participation prediction technique, system and equipment, storage medium | |
Goode et al. | Prioritization of species status assessments for decision support |
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 |