General airport safety risk prediction method and risk level assessment method

Abstract

The invention provides a general airport safety risk prediction method and a risk level evaluation method, and relates to the field of general airport operation data analysis, and the general airport safety risk prediction method comprises the steps: obtaining the operation data of a general airport; according to the operation data of the general airport and the general airport safety risk prediction model, obtaining the probability of safety risk occurrence of the general airport; wherein the general airport safety risk model is obtained by training a first neural network by adopting a first training sample set; the first training sample set comprises a plurality of first training samples; each first training sample comprises training operation data of the general airport and a probability label of occurrence of the security risk. The method is suitable for the process of evaluating the safety risk of a general airport, and is used for solving the problem that a transportation airport safety risk prediction evaluation scheme cannot correctly evaluate the general airport.

Description

Technical Field

[0001] The present application relates to the field of general airports, specifically to the field of general airport operation data analysis, and in particular to a general airport safety risk prediction method and a risk level assessment method. Background Art

[0002] As my country's general aviation industry enters a new period of rapid development, the construction of general airports has also achieved sustained and rapid development.

[0003] A general airport refers to an airport that provides take-off, landing and other services for civil aircraft engaged in operational flights in industry, agriculture, forestry, fishery and construction, as well as medical and health care, emergency and disaster relief, meteorological detection, ocean monitoring, scientific experiments, education and training, culture and sports.

[0004] The transportation airport safety risk prediction and assessment scheme in the related art can predict and assess the safety risks of transportation airports, but the transportation airport safety risk prediction and assessment scheme cannot correctly predict and assess the safety risks of general airports. Therefore, how to predict and assess the safety risks of general airports has become our need. Summary of the invention

[0005] The present application provides a general airport safety risk prediction method and a risk level assessment method, which can predict and assess the safety risks of general airports.

[0006] The technical solution of this application is as follows: In a first aspect, the present application provides a general airport safety risk prediction method, the method comprising: Obtain operational data of general airports; According to the operation data of general airports and the safety risk prediction model of general airports, the probability of safety risks occurring at general airports is obtained; The general airport safety risk model is obtained by training a first neural network using a first training sample set; the first training sample set includes multiple first training samples; each first training sample includes training operation data of the general airport and a probability label of a safety risk.

[0007] Optionally, the operational data of a general airport includes at least one of the following: the number of types of flight missions performed by the general airport; the number of types of target flight missions performed by the general airport; the target flight missions are flight missions in which the number of safety risks in the historical safety records of the general airport is greater than a preset threshold; the number of aircraft types within the general airport; the number of personnel within the general airport.

[0008] Optionally, based on the operating data of the general airport and a safety risk prediction model for general airports, a probability of safety risks occurring at the general airport is obtained, including: acquiring semantic features of the operating data based on the operating data of the general airport and a semantic feature extraction model; acquiring time series features of the operating data based on the operating data of the general airport and a time series feature extraction model; preprocessing the semantic features and time series features; inputting the preprocessed semantic features and time series features into the general airport safety risk prediction model to obtain the probability of safety risks occurring at the general airport output by the general airport safety risk prediction model.

[0009] Optionally, before obtaining the probability of a safety risk occurring at a general airport based on the operating data of the general airport and the safety risk prediction model for the general airport, the method also includes: obtaining a first training sample set; the first training sample set includes multiple first training samples; each first training sample includes the training operating data of the general airport, and a probability label of the occurrence of a safety risk; and training a first neural network based on the first training sample set to obtain the safety risk prediction model for the general airport.

[0010] Optionally, the first neural network is trained based on the first training sample set to obtain a general airport safety risk prediction model, including: obtaining semantic features corresponding to each first training sample according to the semantic feature extraction model and each first training sample in the first training sample set; obtaining temporal features corresponding to each first training sample according to the temporal feature extraction model and each first training sample in the first training sample set; preprocessing the semantic features and temporal features; and using the preprocessed semantic features and temporal features to train the first neural network to obtain the general airport safety risk prediction model.

[0011] The general airport safety risk prediction method provided in this application can obtain the operation data of the general airport, and obtain the probability of the general airport having safety risks based on the operation data of the general airport and the general airport safety risk prediction model, thereby providing a solution that can predict and evaluate the safety risks of general airports based on a neural network model.

[0012] In a second aspect, the present application provides a general airport security risk prediction device, which includes: an acquisition module and a processing module.

[0013] The acquisition module is used to obtain the operation data of general airports.

[0014] A processing module is used to obtain the probability of a safety risk occurring at a general airport based on the operation data of the general airport and a safety risk prediction model for the general airport; wherein the safety risk model for the general airport is obtained by training a first neural network with a first training sample set; the first training sample set includes multiple first training samples; each first training sample includes the training operation data of the general airport and a probability label of a safety risk occurring.

[0015] Optionally, the operational data of a general airport includes at least one of the following: the number of types of flight missions performed by the general airport; the number of types of target flight missions performed by the general airport; the target flight missions are flight missions in which the number of safety risks in the historical safety records of the general airport is greater than a preset threshold; the number of aircraft types within the general airport; the number of personnel within the general airport.

[0016] Optionally, the processing module is specifically used to obtain semantic features of the operation data based on the operation data of the general airport and a semantic feature extraction model; obtain time series features of the operation data based on the operation data of the general airport and a time series feature extraction model; preprocess the semantic features and time series features; input the preprocessed semantic features and time series features into the general airport safety risk prediction model to obtain the probability of safety risks occurring in the general airport output by the general airport safety risk prediction model.

[0017] Optionally, the acquisition module is also used to acquire a first training sample set before the processing module obtains the probability of a safety risk occurring at the general airport based on the operation data of the general airport and the safety risk prediction model of the general airport; the first training sample set includes multiple first training samples; each first training sample includes the training operation data of the general airport and a probability label of the occurrence of a safety risk; the processing module is also used to train the first neural network based on the first training sample set to obtain the safety risk prediction model for the general airport.

[0018] Optionally, the processing module is specifically used to obtain the semantic features corresponding to each first training sample based on the semantic feature extraction model and each first training sample in the first training sample set; obtain the temporal features corresponding to each first training sample based on the temporal feature extraction model and each first training sample in the first training sample set; preprocess the semantic features and temporal features; and use the preprocessed semantic features and temporal features to train the first neural network to obtain a general airport safety risk prediction model.

[0019] In a third aspect, the present application provides a general airport risk level assessment method, the method comprising: obtaining the operating data of the general airport; obtaining the probability of a safety risk occurring at the general airport based on the operating data of the general airport and a general airport safety risk prediction model; wherein the general airport safety risk model is obtained by training a first neural network using a first training sample set; the first training sample set includes multiple first training samples; each first training sample includes the training operating data of the general airport, and a probability label of a safety risk occurring; and determining the risk assessment level of the general airport based on the probability of a safety risk occurring at the general airport.

[0020] In a fourth aspect, the present application provides a general airport risk level assessment device, which includes: an acquisition module and a processing module.

[0021] The acquisition module is used to obtain the operation data of general airports; A processing module is used to obtain the probability of a general airport having a safety risk based on the operation data of the general airport and a general airport safety risk prediction model; wherein the general airport safety risk model is obtained by training a first neural network with a first training sample set; the first training sample set includes multiple first training samples; each first training sample includes the training operation data of the general airport and a probability label of a safety risk; and the risk assessment level of the general airport is determined based on the probability of a safety risk occurring at the general airport.

[0022] In a fifth aspect, the present application provides a computer program product, which, when executed on a computer, enables the computer to implement the method described in the first aspect or the third aspect.

[0023] In a sixth aspect, the present application provides an electronic device, comprising: a processor and a memory; the memory stores instructions executable by the processor; when the processor is configured to execute the instructions, the electronic device implements the method described in the first aspect or the third aspect above.

[0024] In a seventh aspect, the present application provides a readable storage medium, which includes: software instructions; when the software instructions are executed in an electronic device, the electronic device implements the method described in the first aspect or the third aspect above.

[0025] The beneficial effects of the second to seventh aspects mentioned above can be referred to the first aspect and will not be elaborated on again. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0027] Figure 1 A schematic diagram of the composition of a general airport safety risk analysis and evaluation system provided in an embodiment of the present application; Figure 2 A schematic diagram of a general airport security risk prediction method provided in an embodiment of the present application; Figure 3 Another schematic diagram of a general airport security risk prediction method provided in an embodiment of the present application; Figure 4 A flowchart of a general airport risk level assessment method provided in an embodiment of the present application; Figure 5 A schematic diagram of the composition of a general airport security risk prediction device provided in an embodiment of the present application; Figure 6 A schematic diagram of the composition of a general airport risk level assessment device provided in an embodiment of the present application; Figure 7 A schematic diagram of the composition of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0028] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0029] It should be noted that, in the embodiments of the present application, words such as "exemplarily" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplarily" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplarily" or "for example" is intended to present related concepts in a specific way.

[0030] In order to facilitate the clear description of the technical solutions of the embodiments of the present application, in the embodiments of the present application, words such as "first" and "second" are used to distinguish between identical items or similar items with basically the same functions and effects. Those skilled in the art can understand that words such as "first" and "second" do not limit the quantity and execution order.

[0031] As my country's general aviation industry enters a new period of rapid development, the construction of general airports has also achieved sustained and rapid development.

[0032] A general airport refers to an airport that provides take-off, landing and other services for civil aircraft engaged in operational flights in industry, agriculture, forestry, fishery and construction, as well as medical and health care, emergency and disaster relief, meteorological detection, ocean monitoring, scientific experiments, education and training, culture and sports.

[0033] The transportation airport safety risk prediction and assessment scheme in the related art can predict and assess the safety risks of transportation airports, but the transportation airport safety risk prediction and assessment scheme cannot correctly predict and assess the safety risks of general airports. Therefore, how to predict and assess the safety risks of general airports has become our need.

[0034] Based on this, an embodiment of the present application provides a general airport security risk prediction method and a risk level assessment method, which can use a neural network model to predict and assess the security risks of a general airport.

[0035] The following is an introduction with reference to the accompanying drawings.

[0036] Figure 1 This is a schematic diagram of the composition of the general airport safety risk analysis and evaluation system provided in the embodiment of the present application. Figure 1 As shown, the general airport operation status evaluation system includes: a data acquisition device 100 and an analysis and evaluation device 200. The data acquisition device 100 and the analysis and evaluation device 200 can be connected via a wired network or a wireless network.

[0037] The data collection device 100 may be a control tower of a general airport, or other equipment connected to the control tower.

[0038] The data collection device 100 can be used to collect operation data of a general airport.

[0039] For example, taking the data collection device 100 as a control tower, the control tower can exchange data with multiple systems, such as a flight information system, a passenger information system, or a freight information system, etc. The control tower can collect the operation data of a general airport by interacting with these systems.

[0040] In some embodiments, the data collection device 100 can also be used to send the collected operation data of the general airport to the analysis and evaluation device 200 .

[0041] The analysis and evaluation device 200 may be an electronic device having a computing function, such as a computer or a server.

[0042] Among them, the server can be a single server, or it can be a server cluster composed of multiple servers. In some implementations, the server cluster can also be a distributed cluster. Optionally, the server can also be implemented on a cloud platform. For example, the cloud platform can include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an inter-cloud, and a multi-cloud, etc., or any combination thereof. The embodiments of the present application are not limited to this.

[0043] The analysis and evaluation device 200 can predict and evaluate the safety risk of the general airport based on the operation data of the general airport collected by the data collection device 100. The specific process can refer to the general airport safety risk prediction method and general airport risk level assessment method in the following embodiments, which will not be repeated here.

[0044] It should be noted that the above description is based on the example that the data acquisition device 100 and the analysis and evaluation device 200 are independent devices. Optionally, the above data acquisition device 100 and the analysis and evaluation device 200 can also be integrated into one. That is, the data acquisition device 100 or its corresponding functions, and the analysis and evaluation device 200 or its corresponding functions can be integrated into one device. For example, a data acquisition device specifically has the function of predicting and evaluating general airport security risks. The embodiments of the present application are not limited to this.

[0045] The execution subject of the general airport security risk prediction method and the general airport risk level assessment method provided in the embodiment of the present application is an analysis and evaluation device. As described above, the analysis and evaluation device (analysis and evaluation device 200) can be an electronic device with computing and processing functions such as a computer or a server. Optionally, the analysis and evaluation device can also be a processor (such as a central processing unit (CPU)) in the aforementioned electronic device; or, the analysis and evaluation device can also be an application (application, APP) installed in the aforementioned electronic device for executing the general airport security risk prediction method and the general airport risk level assessment method; or, the analysis and evaluation device can also be a software system or platform in the aforementioned electronic device; or, the analysis and evaluation device can also be a functional module in the aforementioned electronic device for executing the general airport security risk prediction method and the general airport risk level assessment method. The embodiment of the present application does not limit this.

[0046] First, the general airport security risk prediction method provided in the embodiment of the present application is introduced.

[0047] Figure 2 This is a flow chart of a general airport security risk prediction method provided in an embodiment of the present application. Figure 2 As shown, the method includes the following steps: S101. Obtain operation data of general airports.

[0048] Optionally, the operational data of the general airport may include at least one of the following: (1) The number of types of flight missions performed at general airports.

[0049] The flight missions performed by transport airports are relatively simple, usually including passenger transportation and cargo transportation. The number of types of flight missions performed by transport airports will not affect the probability of safety risks at transport airports. However, general airports can provide take-off, landing and other services for civil aircraft engaged in operational flights in industry, agriculture, forestry, fishery and construction, as well as medical and health, emergency rescue, meteorological detection, ocean monitoring, scientific experiments, education and training, culture and sports and other flight activities. There are many types of flight missions. If the number of flight missions performed is too large, the burden on general airports will be too heavy, which may cause safety risks.

[0050] (2) The number of types of target flight missions performed by general airports.

[0051] Among them, the target flight mission can be understood as a flight mission with a high number of safety risks. When a general airport simultaneously executes multiple target flight missions with a high number of safety risks, the probability of safety risks is high.

[0052] For example, the analysis and evaluation device can record the number of times safety risks occur in each flight mission to form a historical safety record, and take the flight missions in the historical safety record where the number of safety risks occurs greater than a preset threshold as target flight missions.

[0053] The preset threshold value may be preset in the analysis and evaluation device by the management personnel. For example, the preset threshold value may be set to 3 times, 5 times, or 10 times, etc. The embodiment of the present application does not limit the specific value of the preset threshold value.

[0054] (3) Number of aircraft types at general airports.

[0055] Transport airports usually only take off and land large commercial aircraft, and the number of aircraft types is relatively single. The number of aircraft types in transport airports will not affect the probability of safety risks in transport airports. However, general airports can usually take off and land small aircraft, light aircraft, helicopters, and drones, etc. There are many types of aircraft, which are more difficult to manage. If there are too many types of aircraft, general airports may have safety risks.

[0056] (4) Number of personnel in general airports.

[0057] Generally speaking, transport airports are generally large in scale, and the number of staff in transport airports is generally in the thousands or even tens of thousands. For example, an international airport may have 13,000 staff. In addition to staff, transport airports also include a large number of passengers. Transport airports have strong management capabilities for large numbers of people, and an increase in the number of people in transport airports will not significantly affect the probability of security risks in transport airports.

[0058] The scale of general airports is generally small, and the number of staff in a general airport is generally in the hundreds, such as 200 or 300 people, and there are usually not too many passengers in a general airport. The increase in the number of people in a general airport will affect the probability of safety risks in general airports.

[0059] S102. Obtain the probability of a safety risk occurring at the general airport based on the operation data of the general airport and the safety risk prediction model of the general airport.

[0060] For example, the analysis and evaluation device may input the operation data of the general airport into the general airport safety risk prediction model, analyze the operation data of the general airport through the general airport safety risk prediction model, and output the probability of safety risks occurring at the general airport.

[0061] Among them, the general airport safety risk model is obtained by training the first neural network using the first training sample set; the first training sample set includes multiple first training samples; each first training sample includes the training operation data of the general airport and the probability label of the occurrence of safety risks. The probability label of the occurrence of safety risks in each first training sample set in the first training sample set can be added by manual marking. The method for obtaining the training operation data in each first training sample in the first training sample set and the specific content can refer to the method for obtaining the operation data of the general airport in S101 above, and will not be repeated here.

[0062] Optionally, after the analysis and evaluation device inputs the operating data of the general airport into the general airport safety risk prediction model, the operating data of the general airport is analyzed through the general airport safety risk prediction model, and the obtained probability of safety risks occurring at the general airport can be a probability prediction label, which can represent the probability of safety risks occurring at the general airport.

[0063] For example, the probability of a general airport having a safety risk may include: 10%, 20%, 30%, 40%, or 50%. The above-mentioned probability prediction label may be a label corresponding to the above-mentioned probability, and the above-mentioned probability label may also be a label corresponding to the above-mentioned probability. The embodiment of the present application does not limit this.

[0064] In the general airport safety risk prediction method provided in the embodiment of the present application, the analysis and evaluation device can obtain the operation data of the general airport, and obtain the probability of the general airport having safety risks based on the operation data of the general airport and the general airport safety risk prediction model, thereby providing a solution that can predict and evaluate the safety risks of general airports based on the neural network model.

[0065] In some embodiments, as described above, the analysis and evaluation device can directly input the operation data of the general airport into the general airport safety risk prediction model, analyze the operation data of the general airport through the general airport safety risk prediction model, and output the probability of safety risks occurring at the general airport.

[0066] In other embodiments, the analysis and evaluation device may first extract semantic features of the operational data based on a semantic feature extraction model, then preprocess the semantic features, and input the preprocessed semantic features into a general airport safety risk prediction model to obtain the probability of safety risks occurring in general airports output by the general airport safety risk prediction model.

[0067] Among them, the semantic feature extraction model can be obtained by training the second neural network using the second training sample set. The second training sample set may include multiple second training samples. Each second training sample includes training operation data of a general airport and semantic feature labels corresponding to the training operation data. The semantic feature labels in each second training sample can be added by manual marking. The method for obtaining the training operation data and the specific content can refer to the above-mentioned S101, which will not be repeated here.

[0068] Optionally, the analysis and evaluation device may specifically utilize a convolutional neural network (CNN) model as a semantic feature extraction model to extract semantic features of the operation data.

[0069] For example, operational data can be regarded as a special "image", where each row or column can represent a set of operational data features within a period of time. The CNN model can scan and extract features of this "image" to obtain semantic features.

[0070] Exemplarily, the convolutional neural network model may include a convolutional layer, a pooling layer, and a fully connected layer, etc.

[0071] In some other embodiments, the analysis and evaluation device may extract the semantic features and temporal features of the operation data respectively, and then further make predictions based on the semantic features and temporal features. In this case, the above S102 may specifically include the following steps: Step 1a: According to the operation data of the general airport and the semantic feature extraction model, the semantic features of the operation data are obtained.

[0072] Step 1a can refer to the description in the other embodiments above and will not be repeated here.

[0073] Step 2a: According to the operation data of the general airport and the time series feature extraction model, the time series features of the operation data are obtained.

[0074] Among them, the time series feature extraction model can be obtained by training the third neural network using the third training sample set. The third training sample set may include multiple third training samples. Each third training sample includes training operation data of a general airport and a time series feature label corresponding to the training operation data. The time series feature label may be the operation data of the next time period. The time series feature label in each second training sample can be obtained by summarizing and analyzing historical operation data, or by manual marking. The method for obtaining the training operation data and the specific content can refer to the above-mentioned S101, which will not be repeated here.

[0075] Optionally, the analysis and evaluation device may specifically utilize a long short-term memory network (LSTM) model as a time series feature extraction model to extract the time series features of the operation data.

[0076] It should be noted that the above step 1a can be performed before step 2a, or after step 2a, or simultaneously with step 2a. The embodiment of the present application does not limit the execution sequence of step 1a and step 2a.

[0077] Step 3a: Preprocess the semantic features and temporal features.

[0078] The main purpose of the preprocessing operation is to clean and prepare the data to make it more suitable for the input of the neural network model. The preprocessing operation may include at least one of the following: denoising operation, filtering operation, feature extraction, and standardization.

[0079] By preprocessing the semantic features and temporal features in the above manner, the preprocessed semantic features and temporal features can be used for subsequent machine learning without losing their original meanings.

[0080] Step 4a: input the preprocessed semantic features and temporal features into the general airport safety risk prediction model to obtain the probability of safety risks occurring in the general airport output by the general airport safety risk prediction model.

[0081] In some possible embodiments, before the above S101 or S102, the analysis and evaluation device may also obtain a trained general airport safety risk prediction model.

[0082] In a possible implementation, the analysis and evaluation device can directly obtain the trained general airport safety risk prediction model from other equipment.

[0083] For example, the analysis and evaluation device can obtain the trained general airport safety risk prediction model by downloading it from other devices or transferring it through an intermediate storage medium.

[0084] In another possible implementation, the analysis and evaluation device may train the first neural network according to the first training sample set to obtain a general airport safety risk prediction model. In this case, Figure 3 Another flow chart of a general airport security risk prediction method provided in an embodiment of the present application. Figure 3 As shown, before the above S101 or S102, the method may further include the following steps: S201: Obtain a first training sample set.

[0085] As mentioned above, the first training sample set includes multiple first training samples; each first training sample includes training operation data of a general airport and a probability label of a safety risk.

[0086] S202: Training a first neural network based on a first training sample set to obtain a general airport safety risk prediction model.

[0087] Among them, the trained general airport safety risk prediction model has the function of outputting the probability of safety risks occurring in general airports based on the operation data of general airports.

[0088] For example, the first neural network may be a convolutional neural network, or a recurrent neural network (RNN), etc. The embodiment of the present application does not limit the specific type of the first neural network.

[0089] Optionally, the analysis and evaluation device can directly input one or more first training samples into the first neural network each time to obtain the predicted labels output by the first neural network, and calculate the loss function according to the predicted labels output by the first neural network and the labels in the first training samples, and adjust the parameters in the first neural network until the first neural network converges.

[0090] Optionally, the conditions for the first neural network to converge (or end the training of the first neural network) may include: the number of times the analysis and evaluation device inputs the first training sample into the first neural network reaches a number threshold, or the error between the predicted label output by the first neural network and the label marked in the first training sample is less than an error threshold.

[0091] Among them, the number threshold can be preset in the analysis and evaluation device by the management personnel. For example, the number threshold can be set to 10,000 times, 20,000 times, or 30,000 times, etc. The embodiment of the present application does not limit the specific value of the number threshold. The error threshold can also be preset in the analysis and evaluation device by the management personnel. For example, the error threshold can be set to 5% or 10%, etc. The embodiment of the present application does not limit the specific value of the error threshold.

[0092] Optionally, as described above, during the process of reasoning and prediction, the analysis and evaluation device can extract the semantic features and temporal features of the operation data and input them into the general airport safety risk prediction model. Accordingly, in this embodiment, when the analysis and evaluation device uses the first training sample set to train the first neural network to obtain the general airport safety risk prediction model, the semantic features and temporal features of the training operation data in the first training sample can be extracted for training. In this case, the above S202 can specifically include the following steps: Step 1b: According to the semantic feature extraction model and each first training sample in the first training sample set, obtain the semantic feature corresponding to each first training sample.

[0093] The semantic feature extraction model in step 1b can refer to that in step 1a of the aforementioned embodiment and will not be described in detail.

[0094] Step 2b: according to the time series feature extraction model and each first training sample in the first training sample set, obtain the time series feature corresponding to each first training sample.

[0095] The temporal feature extraction model in step 2b can refer to that in step 2a of the aforementioned embodiment and will not be described in detail.

[0096] Step 3b: preprocess the semantic features and temporal features.

[0097] The process of preprocessing the semantic features and temporal features in step 3b can refer to the description of step 3a in the above embodiment and will not be repeated here.

[0098] Step 4b: Use the preprocessed semantic features and temporal features to train the first neural network to obtain a general airport safety risk prediction model.

[0099] Step 4b may refer to the above-mentioned S202 and will not be described in detail here.

[0100] Based on the understanding of the above embodiments, the embodiments of the present application also provide a general airport risk level assessment method. Figure 4 The following is a flow chart of a general airport risk level assessment method provided in an embodiment of the present application. Figure 4 As shown, the method includes the following steps: S301. Obtain operation data of general airports.

[0101] S301 may refer to the above-mentioned S101, which will not be described in detail here.

[0102] S302: Obtain the probability of a safety risk occurring at the general airport based on the operation data of the general airport and the safety risk prediction model of the general airport.

[0103] The general airport safety risk model is obtained by training a first neural network using a first training sample set; the first training sample set includes multiple first training samples; each first training sample includes training operation data of the general airport and a probability label of a safety risk.

[0104] S302 may refer to the above-mentioned S102, which will not be described in detail here.

[0105] S303. Determine the risk assessment level of the general airport based on the probability of safety risks occurring at the general airport.

[0106] In a possible implementation, the analysis and evaluation device may preset a correspondence between the probability interval of the occurrence of safety risks at the general airport and the risk evaluation level. The analysis and evaluation device may determine the risk evaluation level of the general airport according to the probability of the occurrence of safety risks at the general airport and the correspondence.

[0107] Optionally, the analysis and evaluation device can first determine the target probability interval based on the probability of safety risks occurring at the general airport, and then traverse the above correspondence using the target probability interval as an index, and use the risk assessment level corresponding to the target probability interval in the above correspondence as the risk assessment level of the general airport.

[0108] For example, the corresponding relationship between the probability interval of safety risk occurring at a general airport and the risk assessment level can be specifically shown in the following Table 1: Table 1 As shown in Table 1, the table includes the probability interval items of safety risks occurring at general airports and the risk assessment level items. Among them, the probability interval items of safety risks occurring at general airports include: 10%-29%, 30%-49%, and 50%-80%. The risk assessment level items include: level 1, level 2, and level 3. There is a corresponding relationship between 10%-29% and level 1; there is a corresponding relationship between 30%-49% and level 2; there is a corresponding relationship between 50%-80% and level 3.

[0109] In another possible implementation, the analysis and evaluation device may obtain the risk assessment level of the general airport based on the probability of safety risks occurring at the general airport and a risk assessment level evaluation model.

[0110] The risk assessment level evaluation model can be obtained by training the fourth neural network using the fourth training sample set. The fourth training sample set can include multiple fourth training samples, each of which includes the probability of a safety risk occurring at a general airport and a risk assessment level label.

[0111] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of the method. In order to achieve the above functions, it includes hardware structures and / or software modules corresponding to the execution of each function. It should be easy to realize that the technical goals in this field are combined with the units and algorithm steps of each example described in the embodiments disclosed in this article, and the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical goals can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0112] In an exemplary embodiment, the present application also provides a general airport security risk prediction device, which can be applied to the above-mentioned analysis and evaluation device. Figure 5 This is a schematic diagram of the composition of a general airport security risk prediction device provided in an embodiment of the present application. Figure 5 As shown, the device includes: an acquisition module 501 and a processing module 502.

[0113] The acquisition module 501 is used to acquire the operation data of the general airport.

[0114] Processing module 502 is used to obtain the probability of a safety risk occurring at a general airport based on the operation data of the general airport and the general airport safety risk prediction model; wherein the general airport safety risk model is obtained by training a first neural network with a first training sample set; the first training sample set includes multiple first training samples; each first training sample includes the training operation data of the general airport and a probability label of a safety risk occurring.

[0115] In some possible embodiments, the operational data of a general airport includes at least one of the following: the number of types of flight missions performed by the general airport; the number of types of target flight missions performed by the general airport; the target flight missions being flight missions for which the number of safety risks in the general airport's historical safety records is greater than a preset threshold; the number of aircraft types within the general airport; and the number of personnel within the general airport.

[0116] In some other possible embodiments, the processing module 502 is specifically used to obtain semantic features of the operation data based on the operation data of the general airport and a semantic feature extraction model; obtain time series features of the operation data based on the operation data of the general airport and a time series feature extraction model; preprocess the semantic features and time series features; input the preprocessed semantic features and time series features into the general airport safety risk prediction model to obtain the probability of safety risks occurring in the general airport output by the general airport safety risk prediction model.

[0117] In some other possible embodiments, the acquisition module 501 is also used to acquire a first training sample set before the processing module 502 obtains the probability of a safety risk occurring at a general airport based on the operation data of the general airport and the safety risk prediction model of the general airport; the first training sample set includes multiple first training samples; each first training sample includes the training operation data of the general airport and a probability label of the occurrence of a safety risk; the processing module 502 is also used to train the first neural network based on the first training sample set to obtain the safety risk prediction model for the general airport.

[0118] In some other possible embodiments, the processing module 502 is specifically used to obtain the semantic features corresponding to each first training sample based on the semantic feature extraction model and each first training sample in the first training sample set; obtain the temporal features corresponding to each first training sample based on the temporal feature extraction model and each first training sample in the first training sample set; preprocess the semantic features and temporal features; and use the preprocessed semantic features and temporal features to train the first neural network to obtain a general airport safety risk prediction model.

[0119] In an exemplary embodiment, the present application also provides a general airport risk level assessment device, which can be applied to the above-mentioned analysis and evaluation device. Figure 6This is a schematic diagram of the composition of a general airport risk level assessment device provided in an embodiment of the present application. Figure 6 As shown, the device includes: an acquisition module 601 and a processing module 602.

[0120] The acquisition module 601 is used to acquire the operation data of the general airport.

[0121] Processing module 602 is used to obtain the probability of a safety risk occurring at a general airport based on the operation data of the general airport and the general airport safety risk prediction model; wherein the general airport safety risk model is obtained by training a first neural network with a first training sample set; the first training sample set includes multiple first training samples; each first training sample includes the training operation data of the general airport and a probability label of a safety risk occurring; and the risk assessment level of the general airport is determined based on the probability of a safety risk occurring at the general airport.

[0122] In an exemplary embodiment, the present application also provides an electronic device. Figure 7 The following is a schematic diagram of the composition of the electronic device provided in the embodiment of the present application. Figure 7 As shown, the electronic device includes: a processor 701 and a memory 702. The memory 702 stores instructions executable by the processor 701, and when the processor 701 is configured to execute the above instructions, the electronic device implements the method described in the above method embodiment.

[0123] In an exemplary embodiment, the embodiment of the present application further provides a computer program product, which, when executed on a computer, enables the computer to implement the method in the aforementioned method embodiment.

[0124] In an exemplary embodiment, the present application also provides a readable storage medium on which software instructions are stored; when the software instructions are executed by an electronic device, the electronic device implements the method described in the aforementioned embodiment. The computer-readable storage medium may be a non-temporary computer-readable storage medium, for example, the non-temporary computer-readable storage medium may be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0125] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using a software program, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer-executable instructions. When the computer-executable instructions are loaded and executed on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer-executable instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer-executable instructions can be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center.

[0126] Although the present application is described herein in conjunction with various embodiments, in the process of implementing the claimed application, those skilled in the art may understand and implement other changes to the disclosed embodiments by viewing the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "one" or "an" does not exclude multiple situations. A single processor or other unit may implement several functions listed in a claim. Certain measures are recorded in different dependent claims, but this does not mean that these measures cannot be combined to produce good results.

[0127] Although the present application has been described in conjunction with specific features and embodiments thereof, it is obvious that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and the drawings are merely exemplary illustrations of the present application as defined by the appended claims, and are deemed to have covered any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art may make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

[0128] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A general airport safety risk prediction method, characterized in that: The method comprises: Obtain operational data of general airports; Obtaining the probability of a safety risk occurring at the general airport according to the operation data of the general airport and the safety risk prediction model of the general airport; The general airport safety risk model is obtained by training a first neural network using a first training sample set; the first training sample set includes multiple first training samples; each of the first training samples includes the training operation data of the general airport and a probability label of a safety risk.

2. The method according to claim 1, characterized in that The operational data of the general airport includes at least one of the following: The number of types of flight missions performed by the general airport; The number of types of target flight missions executed by the general airport; the target flight missions are flight missions for which the number of safety risks occurring in the historical safety records of the general airport is greater than a preset threshold; The number of aircraft types at the general airport; The number of persons present at the said general airport.

3. The method according to claim 1, characterized in that The obtaining, based on the operation data of the general airport and the general airport safety risk prediction model, the probability of the general airport having safety risks comprises: Acquire semantic features of the operation data according to the operation data of the general airport and a semantic feature extraction model; According to the operation data of the general airport and the time series feature extraction model, the time series features of the operation data are obtained; Preprocessing the semantic features and the temporal features; The preprocessed semantic features and the time series features are input into the general airport safety risk prediction model to obtain the probability of the general airport having a safety risk output by the general airport safety risk prediction model.

4. The method according to claim 1, characterized in that: Before obtaining the probability of the general airport having a safety risk based on the operation data of the general airport and the general airport safety risk prediction model, the method further includes: Acquire a first training sample set; the first training sample set includes a plurality of first training samples; each of the first training samples includes training operation data of the general airport and a probability label of a safety risk; The first neural network is trained based on the first training sample set to obtain the general airport safety risk prediction model.

5. The method according to claim 4, characterized in that The step of training the first neural network based on the first training sample set to obtain the general airport safety risk prediction model includes: According to the semantic feature extraction model and each first training sample in the first training sample set, obtaining a semantic feature corresponding to each first training sample; According to the time series feature extraction model and each first training sample in the first training sample set, obtaining a time series feature corresponding to each first training sample; Preprocessing the semantic features and the temporal features; The first neural network is trained using the preprocessed semantic features and the temporal features to obtain the general airport safety risk prediction model.

6. A general airport risk level assessment method, characterized in that: The method comprises: Obtain operational data of general airports; According to the operation data of the general airport and the general airport safety risk prediction model, the probability of the general airport having a safety risk is obtained; wherein the general airport safety risk model is obtained by training a first neural network with a first training sample set; the first training sample set includes a plurality of first training samples; each of the first training samples includes the training operation data of the general airport and a probability label of the safety risk; The risk assessment level of the general airport is determined according to the probability of safety risks occurring at the general airport.

7. A general airport security risk prediction device, characterized in that: The device comprises: an acquisition module and a processing module; The acquisition module is used to acquire the operation data of the general airport; The processing module is used to obtain the probability of safety risks occurring at the general airport based on the operation data of the general airport and the general airport safety risk prediction model; wherein the general airport safety risk model is obtained by training a first neural network with a first training sample set; the first training sample set includes multiple first training samples; each of the first training samples includes the training operation data of the general airport and a probability label of the occurrence of safety risks.

8. A general airport risk level assessment device, characterized in that: The device comprises: an acquisition module and a processing module; The acquisition module is used to acquire the operation data of the general airport; The processing module is used to obtain the probability of safety risks occurring at the general airport based on the operation data of the general airport and the general airport safety risk prediction model; wherein the general airport safety risk model is obtained by training a first neural network with a first training sample set; the first training sample set includes multiple first training samples; each of the first training samples includes the training operation data of the general airport and a probability label of safety risks occurring; and the risk assessment level of the general airport is determined based on the probability of safety risks occurring at the general airport.

9. An electronic device, characterized in that: include: Processor and memory; The memory stores instructions executable by the processor; When the processor is configured to execute the instructions, the electronic device implements the method according to any one of claims 1 to 6.

10. A readable storage medium, characterized in that: include: Software instructions; When the software instructions are executed in an electronic device, the electronic device implements the method according to any one of claims 1 to 6.

Images