CN113610356A - Airport core risk prediction method and system - Google Patents
Airport core risk prediction method and system Download PDFInfo
- Publication number
- CN113610356A CN113610356A CN202110805418.XA CN202110805418A CN113610356A CN 113610356 A CN113610356 A CN 113610356A CN 202110805418 A CN202110805418 A CN 202110805418A CN 113610356 A CN113610356 A CN 113610356A
- Authority
- CN
- China
- Prior art keywords
- unsafe
- event information
- prediction
- event
- airport
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Abstract
The invention discloses an airport core risk prediction method and system, belonging to the technical field of airport security service, wherein the method comprises the following steps: acquiring unsafe event information of an airport, wherein the unsafe event information is event information which is uploaded by each system and threatens the operation of the airport; extracting keywords of the unsafe event information, and splitting the unsafe event information according to five parameters of time, place, type, severity level and processing measure, wherein the splitting is used for refining the event information, so that each parameter is used as a prediction factor, and the prediction factor is used as the input of a prediction model; and carrying out reason positioning and prediction on the split unsafe time information, and displaying a prediction result. By splitting the unsafe event information of the airport into five parameters, each parameter is used as a prediction factor of a prediction model, and prediction results are accurately output through different weights of the prediction factors, so that the prediction is more accurate.
Description
Technical Field
The invention relates to the technical field of airport security service, in particular to an airport core risk prediction method and system.
Background
Under the requirements of ICAO, CAAC, local supervision and the requirements of airport corresponding to self security and quality fine management, the airport AOC can timely acquire various events which occur and are found on each business line of the airport, namely the events which are found on duty and the events which occur in field operation. With the development of safety management ideas and big data technologies, airports have realized that event data actively contributes to the assessment of airport operation situations and the identification of important safety management work, and efforts are made to explore data analysis modes suitable for the airports to further develop the value of unsafe events.
The traditional airport risk prediction mode only stays in macroscopic prediction, one factor generated according to unsafe events is used as a prediction factor of a prediction model, so that the accuracy of the prediction result is poor, the two unsafe events are similar in result but different in generation reason, the prediction results output by the prediction model are consistent, and the prediction mode is not beneficial to safety control of an airport and is inconvenient to handle risks caused by the unsafe events.
Disclosure of Invention
The invention aims to solve the problems that the conventional airport risk prediction mode has a single prediction factor and the prediction result is not accurate enough, and provides an airport core risk prediction method and system, which have the advantages of more accurate prediction result, high sensitivity, convenience in timely positioning of the reason for generating unsafe events and convenience in later-stage safety management.
In a first aspect, the present invention provides a method for predicting risk of an airport core, including the steps of:
acquiring unsafe event information of an airport, wherein the unsafe event information is event information which is uploaded by each system and threatens the operation of the airport;
extracting keywords of the unsafe event information, and splitting the unsafe event information according to five parameters of time, place, type, severity level and processing measure, wherein the splitting is used for refining the event information, so that each parameter is used as a prediction factor, and the prediction factor is used as the input of a prediction model;
and carrying out reason positioning and prediction on the split unsafe time information, and displaying a prediction result.
Preferably, the unsafe event information is obtained by collecting a manual system, an equipment system and an environment system, the manual system is used for providing the manual unsafe event information, the equipment system is used for providing the equipment unsafe event information, and the environment system is used for providing the environment unsafe event information.
Preferably, the method for locating and predicting the reason of the split unsafe time information includes the following steps:
acquiring unsafe event information, and splitting parameters by extracting keywords of the unsafe event;
the split parameters are used to:
weighting the event parameters including time, place, type, severity level and treatment measure, and calculating an overall score;
the reason of the event is layered to obtain the generation reason of the unsafe event, so that the reason of the event is positioned;
and displaying the score of each weighted parameter, and comparing the total score of the statistical parameters with the score table, thereby outputting the prediction result of the event and the reason of the event occurrence.
Preferably, the predicted result shows that a proportion graph of scores of each parameter in the unsafe event information to the total score is generated through a graph unit, and reason positioning is carried out on each parameter.
In a second aspect, the present invention provides an airport core risk prediction system, including:
the data acquisition unit is used for accessing each system of the airport to acquire unsafe event information;
the data processing unit is used for processing the collected unsafe event information and extracting effective words and sentences of the unsafe event information;
the event analysis model is used for splitting the unsafe event information according to five parameters including time, place, type, severity level and processing measure by extracting keywords of the unsafe event information, wherein the splitting is used for refining the event information, each parameter is used as a prediction factor, and the prediction factors are used as the input of the prediction model for positioning and predicting reasons of the split unsafe event information;
and the data display unit is used for displaying the predicted result.
Preferably, the event analysis model includes:
the classification model is used for dividing the event into five parameters of a time period, an event place, an event type, a severity level and a processing measure;
the analytic model is used for weighting each classified parameter;
the reason positioning model is used for searching the reasons generated by the unsafe events layer by setting a layered framework and determining the specific reasons generated by the unsafe events;
and the prediction model is used for comparing the total score after the weighting of the calculation parameters with the risk rated score to determine the risk level.
Preferably, the event analysis model is further connected with a database and a model training unit, the database is connected with the data processing unit, unsafe event information of manual analysis provided by each system is stored, the unsafe event information is input to the model training unit to train the event analysis model, and the database is further connected with the data display unit and used for backing up displayed chart information.
Third aspect the present invention achieves the above object by a computing device, comprising a memory and a processor, wherein the memory stores executable codes, and the processor executes the executable codes to implement the method of the first aspect.
Compared with the prior art, the invention has the beneficial effects that:
by splitting the unsafe event information of the airport into five parameters, taking each parameter as a prediction factor of a prediction model, adding different weights to the prediction factors, accumulating scores of different parameters, and comparing the total score output to which risk level, the output prediction result is more accurate, and if one parameter is changed, the output prediction result is influenced, and the sensitivity is higher.
The reason of the occurrence of the unsafe event is positioned by adopting a layered framework, the reason is refined layer by layer, the accurate reason of the occurrence of the unsafe event is quickly searched, and the risk handling of workers is facilitated when the risk occurs in the later period.
Drawings
FIG. 1 is a flow chart of a risk prediction method of the present invention.
Fig. 2 is a flowchart of the unsafe time information cause locating and predicting method of the present invention.
FIG. 3 is a schematic diagram of the risk prediction system according to the present invention.
FIG. 4 is a schematic diagram of an event analysis model according to the present invention.
Fig. 5 is a hierarchical diagram illustrating the cause of unsafe event according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1
Referring to fig. 1, a method for predicting risk of an airport core includes the following steps:
step S1, unsafe event information of the airport is obtained, the unsafe event information is uploaded by all systems and threatens the operation of the airport, the unsafe event information is obtained by collecting manual systems, equipment systems and environment systems, the manual systems are used for providing artificial unsafe event information, the equipment systems are used for providing equipment unsafe event information, the environment systems are used for providing environment unsafe event information, unsafe events of the airport mainly comprise three types, potential safety hazards brought by artificial operation problems, potential safety hazards brought by faults in the operation process of the equipment and potential safety hazards caused by environment factors, and the events of the airport can be comprehensively mastered by the manual systems, the equipment systems and the environment systems.
Step S2, extracting the key words of the unsafe event information, splitting the unsafe event information according to five parameters of time, place, type, severity level and processing measure, wherein the splitting is used for refining the event information, each parameter is used as a prediction factor which is used as the input of a prediction model, the five parameters of time, place, type, severity level and processing measure are necessary components for forming an event, the time, place and type can reflect the time and place of an unsafe event information and the time in three major systems of manpower, equipment and environment, the severity level and processing measure can reflect the consequences and whether the event is processed, the time, place and type belong to the factors influencing the relatively weak risk of the event in the unsafe event, and the severity level and processing measure are the factors influencing the relatively strong risk, therefore, the risk of the event can be conveniently predicted by refining the information of the unsafe event;
step S3, performing cause location and prediction on the split unsafe time information, and displaying a prediction result, where the method for performing cause location and prediction on the split unsafe time information is shown in fig. 2, and includes the following steps:
acquiring unsafe event information, and splitting parameters by extracting keywords of the unsafe event;
the split parameters are used to: weighting the event parameters including time, place, type, severity level and treatment measure, and calculating an overall score, wherein the weighting ratio is low because the time, the place and the type have weak influence on the risk of the event, and the weighting ratio is high because the severity level and the treatment measure have strong risk on the event. The reason of the event is layered to obtain the generation reason of the unsafe event, so that the reason of the event is positioned, the reason of each parameter in the unsafe event is positioned, and the risk caused by the unsafe event can be conveniently processed in the later period.
And displaying the score of each weighted parameter, comparing the total score of the statistical parameter with a score table, and outputting a prediction result of the event and the reason of the event, wherein the prediction result is displayed by generating a ratio chart of the score of each parameter in the unsafe event information in the total score through a chart unit, and positioning the reason of each parameter, so that a user can more intuitively check the prediction result.
As shown in fig. 3, an airport core risk prediction system includes:
the data acquisition unit is used for accessing each system of the airport to acquire unsafe event information;
the data processing unit is used for processing the collected unsafe event information and extracting effective words and sentences of the unsafe event information, and the data processing unit is used for extracting the information of the unsafe events from the uploaded data because the data contents uploaded by each system are more;
an event analysis model, configured to split the unsafe event information according to five parameters, i.e., time, location, type, severity level, and processing measure, by extracting a keyword of the unsafe event information, where the splitting is used to refine the event information, so that each parameter is used as a prediction factor, and the prediction factor is used as an input of a prediction model to perform cause location and prediction on the split unsafe event information, as shown in fig. 4, where the event analysis model includes: the classification model is used for dividing the event into five parameters of a time period, an event place, an event type, a severity level and a processing measure; the analytic model is used for weighting each classified parameter; a reason positioning model, which is used for searching the reason generated by the unsafe event layer by setting a hierarchical structure to determine the specific reason generated by the unsafe event, for example, as shown in fig. 5, by refining one reason layer by layer, when the event type is acquired as the artificially-caused unsafe event, the first layer is the event type, the second layer analyzes whether the artificially-caused unsafe event is caused by an artificial threat or an artificial misoperation, the third layer of the artificial threat begins to analyze whether the threat belongs to an internal threat or an external threat, the third layer of the artificial misoperation begins to analyze whether the artificial misoperation belongs to an misoperation, a program misoperation or a communication misoperation, and each reason of the fourth layer is analyzed again, so when the reason positioning is met, through the tree analysis mode, the method can accurately position the reason of the unsafe event, is convenient for processing the problem in the later period in time and is convenient for safety management. And the prediction model is used for comparing the total score after the weighting of the calculation parameters with the risk rated score to determine the risk level. The event analysis model is also connected with a database and a model training unit, the database is connected with the data processing unit, unsafe event information of manual analysis provided by each system is stored, the unsafe event information is input to the model training unit to train the event analysis model, and the database is also connected with the data display unit and used for backing up displayed chart information.
And the data display unit is used for displaying the predicted result.
A computing device comprising a memory having executable code stored therein and a processor that, when executing the executable code, implements the method of embodiment 1.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.
Claims (8)
1. An airport core risk prediction method, comprising the steps of:
acquiring unsafe event information of an airport, wherein the unsafe event information is event information which is uploaded by each system and threatens the operation of the airport;
extracting keywords of the unsafe event information, and splitting the unsafe event information according to five parameters of time, place, type, severity level and processing measure, wherein the splitting is used for refining the event information, so that each parameter is used as a prediction factor, and the prediction factor is used as the input of a prediction model;
and carrying out reason positioning and prediction on the split unsafe time information, and displaying a prediction result.
2. The method according to claim 1, wherein the unsafe event information is obtained by collecting a manual system, an equipment system and an environment system, the manual system is used for providing the artificial unsafe event information, the equipment system is used for providing the equipment unsafe event information, and the environment system is used for providing the environment unsafe event information.
3. The method for predicting the core risk of the airport according to claim 1, wherein the method for locating and predicting the cause of the unsafe time information after splitting comprises the following steps:
acquiring unsafe event information, and splitting parameters by extracting keywords of the unsafe event;
the split parameters are used to:
weighting the event parameters including time, place, type, severity level and treatment measure, and calculating an overall score;
the reason of the event is layered to obtain the generation reason of the unsafe event, so that the reason of the event is positioned;
and displaying the score of each weighted parameter, and comparing the total score of the statistical parameters with the score table, thereby outputting the prediction result of the event and the reason of the event occurrence.
4. The method of claim 3, wherein the predicted result is displayed by generating a ratio of score of each parameter in the unsafe event information to total score by a graph unit, and performing cause location for each parameter.
5. An airport core risk prediction system, comprising:
the data acquisition unit is used for accessing each system of the airport to acquire unsafe event information;
the data processing unit is used for processing the collected unsafe event information and extracting effective words and sentences of the unsafe event information;
the event analysis model is used for splitting the unsafe event information according to five parameters including time, place, type, severity level and processing measure by extracting keywords of the unsafe event information, wherein the splitting is used for refining the event information, each parameter is used as a prediction factor, and the prediction factors are used as the input of the prediction model for positioning and predicting reasons of the split unsafe event information;
and the data display unit is used for displaying the predicted result.
6. The system of claim 5, wherein the event analysis model comprises:
the classification model is used for dividing the event into five parameters of a time period, an event place, an event type, a severity level and a processing measure;
the analytic model is used for weighting each classified parameter;
the reason positioning model is used for searching the reasons generated by the unsafe events layer by setting a layered framework and determining the specific reasons generated by the unsafe events;
and the prediction model is used for comparing the total score after the weighting of the calculation parameters with the risk rated score to determine the risk level.
7. The system of claim 5, wherein the event analysis model is further connected to a database and a model training unit, the database is connected to the data processing unit, stores unsafe event information of manual analysis provided by each system, inputs the unsafe event information to the model training unit to train the event analysis model, and is further connected to the data presentation unit to backup the presented graph information.
8. A computing device comprising a memory and a processor, wherein the memory has stored therein executable code that, when executed by the processor, implements the method of any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110805418.XA CN113610356A (en) | 2021-07-16 | 2021-07-16 | Airport core risk prediction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110805418.XA CN113610356A (en) | 2021-07-16 | 2021-07-16 | Airport core risk prediction method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113610356A true CN113610356A (en) | 2021-11-05 |
Family
ID=78304745
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110805418.XA Pending CN113610356A (en) | 2021-07-16 | 2021-07-16 | Airport core risk prediction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113610356A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103854064A (en) * | 2012-11-29 | 2014-06-11 | 中国科学院计算机网络信息中心 | Event occurrence risk prediction and early warning method targeted to specific zone |
| CN108734201A (en) * | 2018-04-26 | 2018-11-02 | 大连施米机电设备有限公司 | The sorting technique and system of nuclear power plant's Experience Feedback event based on layering analysis of causes method |
| CN109474515A (en) * | 2018-11-13 | 2019-03-15 | 平安科技（深圳）有限公司 | Mail push method, device, computer equipment and the storage medium of risk case |
| WO2020037942A1 (en) * | 2018-08-20 | 2020-02-27 | 平安科技（深圳）有限公司 | Risk prediction processing method and apparatus, computer device and medium |
-
2021
- 2021-07-16 CN CN202110805418.XA patent/CN113610356A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103854064A (en) * | 2012-11-29 | 2014-06-11 | 中国科学院计算机网络信息中心 | Event occurrence risk prediction and early warning method targeted to specific zone |
| CN108734201A (en) * | 2018-04-26 | 2018-11-02 | 大连施米机电设备有限公司 | The sorting technique and system of nuclear power plant's Experience Feedback event based on layering analysis of causes method |
| WO2020037942A1 (en) * | 2018-08-20 | 2020-02-27 | 平安科技（深圳）有限公司 | Risk prediction processing method and apparatus, computer device and medium |
| CN109474515A (en) * | 2018-11-13 | 2019-03-15 | 平安科技（深圳）有限公司 | Mail push method, device, computer equipment and the storage medium of risk case |
Non-Patent Citations (1)
| Title |
|---|
| 许诺;唐锡晋;: "基于百度热搜新闻词的社会风险事件5W提取研究", 系统工程理论与实践, no. 02 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chiu et al. | Latent human error analysis and efficient improvement strategies by fuzzy TOPSIS in aviation maintenance tasks | |
| CN111553411A (en) | Pilot risk portrait method based on multidimensional quantitative data | |
| Li et al. | Methodology for analyzing the dependencies between human operators in digital control systems | |
| CN115409395A (en) | Quality acceptance inspection method and system for hydraulic construction engineering | |
| CN110570097A (en) | business personnel risk identification method and device based on big data and storage medium | |
| CN115545516A (en) | Performance data processing method, device and system based on process engine | |
| CN112084220A (en) | Method and device for diagnosing abnormity of electric energy metering device and readable storage medium | |
| Nagaraju et al. | Practical software reliability engineering with the Software Failure and Reliability Assessment Tool (SFRAT) | |
| CN111045902A (en) | Pressure testing method and device for server | |
| US20170132731A1 (en) | Intellectual property evaluation system, intellectual property evaluation system control method, and intellectual property evaluation program | |
| CN113807751B (en) | Safety risk grade assessment method and system based on knowledge graph | |
| CN111475548A (en) | Power utilization abnormity analysis decision system based on big data mining technology | |
| CN113610356A (en) | Airport core risk prediction method and system | |
| CN110928752A (en) | Method, device and equipment for evaluating health degree of air traffic control station | |
| CA3020799A1 (en) | Requirements determination | |
| CN113592311B (en) | Method for selecting personal factor method for complex man-machine system | |
| CN115409616A (en) | Risk detection method, device, equipment, storage medium and product | |
| CN114201328A (en) | Fault processing method and device based on artificial intelligence, electronic equipment and medium | |
| CN109754159B (en) | Method and system for extracting information of power grid operation log | |
| CN111221704B (en) | Method and system for determining running state of office management application system | |
| CN113515560A (en) | Vehicle fault analysis method and device, electronic equipment and storage medium | |
| Çalişkan et al. | Climate change disclosures in different cultures: a study of sustainability reports | |
| WO2024065776A1 (en) | Method for data processing, apparatus for data processing, electronic device, and storage medium | |
| Li et al. | Applying Coding Behavior Features to Student Plagiarism Detection on Programming Assignments | |
| KR102385811B1 (en) | Observation evaluation support system, observation evaluation support method, and program stored in recording 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 |