A strategy recommendation method based on traffic situation map classification

Abstract

The application provides a strategy recommendation method based on traffic situation map classification, comprising: creating a historical strategy information database; selecting a control area as a concerned area, obtaining traffic information in the concerned area, and constructing a traffic situation map; obtaining a published strategy of the concerned area from the historical strategy information database, constructing a historical traffic situation map, and recording the published strategy corresponding to each historical traffic situation map; selecting a recommended strategy, regarding each historical traffic situation map as a kind of map category, finding a historical traffic situation map of the same category as the traffic situation map by performing map classification on the traffic situation map, and selecting the published strategy corresponding to the historical traffic situation map as the recommended strategy; correcting an action period of the recommended strategy, and pushing the recommended strategy to a user for use; and updating the historical strategy information database.

Description

Technical Field

[0001] This invention relates to a method for recommending air traffic flow management strategies, and more particularly to a strategy recommendation method based on traffic situation map classification. Background Technology

[0002] This section provides only background information relevant to this disclosure and is not necessarily prior art.

[0003] The purpose of air traffic flow management is to achieve a balance between air traffic supply and demand, and the means to achieve this is through strategy development. More precisely, air traffic flow management refers to the process by which flow management personnel optimize the spatiotemporal distribution of flight traffic by adopting effective allocation strategies when air traffic flow approaches or reaches the available capacity of the control unit, thereby ensuring the orderly and smooth flow of air traffic.

[0004] With the continued growth in air transport demand, significant progress has been made in the research and development of air traffic management systems. Unfortunately, currently widely used air traffic management systems lack automatic strategy recommendation capabilities. Strategy formulation is entirely done by air traffic managers based on real-time information provided by the system, forecasts for the near future, and their own experience. This approach suffers from high workload, high subjectivity, and low coordination. Therefore, the ability to save past successful strategies and automatically recommend them to air traffic managers at appropriate times has become a pressing need.

[0005] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0006] Purpose of the invention: The technical problem to be solved by the present invention is to provide a strategy recommendation method based on traffic situation map classification, which addresses the shortcomings of the existing technology.

[0007] To address the aforementioned technical problems, this invention discloses a strategy recommendation method based on traffic situation map classification, comprising the following steps:

[0008] Step 1: Create a historical policy information database to store published policies and traffic information within the controlled area of ​​the unit that published the policy at the time of its publication.

[0009] Step 2: Select a controlled area as the area of ​​interest, obtain traffic information within the area of ​​interest, and construct a traffic situation map;

[0010] Step 3: Obtain the published policies for the areas of interest from the historical policy information database. For each published policy, obtain the traffic information of the areas of interest when the policy was published from the historical policy information database, construct a historical traffic situation map, and record the published policies corresponding to each historical traffic situation map.

[0011] Step 4: Select a recommended strategy. Treat each historical traffic situation map as a map category. By classifying the traffic situation maps into maps, find the historical traffic situation maps of the same category as the traffic situation map, and select the published strategy corresponding to the historical traffic situation map as the recommended strategy.

[0012] Step 5: Adjust the effective period of the recommendation strategy and push it to users;

[0013] Step 6: Update the historical strategy information database to record the user's usage of the recommended strategy. If the user does not use the recommended strategy but adopts a new strategy, store the new strategy and the traffic information of the area of ​​interest when the new strategy is released in the historical strategy information database.

[0014] Furthermore, the traffic information mentioned in step 1 includes: route information, airport predicted capacity information, and waypoint predicted capacity information.

[0015] Furthermore, the route information mentioned in step 1 includes temporary route information.

[0016] Furthermore, the historical strategy information database mentioned in step 1 includes:

[0017] Historical strategy information data table, historical route information data table, and historical prediction information data table, among which,

[0018] The historical strategy information data table stores information about published strategies, including: strategy identifier, strategy name, number of recommendations, strategy duration, strategy release area, strategy release time, and strategy content.

[0019] The historical route information data table stores route information of the controlled area of ​​the unit that issued the policy when the policy was issued, including: policy identifier, policy issuance area, route information and temporary route information;

[0020] The historical forecast information data table stores the predicted traffic and capacity information for each airport and waypoint within the control area of ​​the unit that issued the strategy at the time of the strategy release, for the next k hours.

[0021] Furthermore, the historical prediction information data table mentioned in step 1 includes: strategy identifier, object type, object name, strategy release area, predicted traffic for the next k hours, and predicted capacity for the next k hours; wherein, the object is an airport or waypoint.

[0022] Furthermore, the construction of the traffic situation map described in step 2 includes:

[0023] Step 2-1, establish the node set V, as follows:

[0024] Airports and waypoints within the region of interest are sequentially placed into a node set V. Let N be the total number of airports and waypoints within the region of interest. The node set is then represented as follows:

[0025] V = {v1, v2, v3, ... v N}

[0026] Among them, v N This represents the Nth node;

[0027] Step 2-2, establish the edge set E, as follows:

[0028] The airway segment is analyzed from the airway information and temporary airway information in the traffic information of the area of ​​interest. If there is a segment by v i to v j For the route segment, <v i v j > Add it to the edge set E, where v i and v j Let i and j represent the i-th and j-th nodes in the node set V;

[0029] Steps 2-3: Construct an adjacency matrix A of dimension N×N, as follows:

[0030] Iterate through the edge set E and set each element in the adjacency matrix A according to the following rules:

[0031]

[0032] Among them, A i，j This represents the element in the i-th row and j-th column of the adjacency matrix A;

[0033] Steps 2-4: Calculate the ratio of predicted flow to predicted capacity for each node in the node set V over the next k hours, and use the resulting k-dimensional vector as the attribute vector for that node; let f be the predicted flow and predicted capacity of the i-th node in the t-th hour. i，t and c i，t Where t = 1, 2, ..., k, then the attribute vector x of the i-th node is... i Represented as:

[0034]

[0035] The node attribute matrix X, consisting of all nodes in the node set V, is:

[0036] X = [x1 x2 … x N ]

[0037] Steps 2-5: Using airports and waypoints within the area of ​​interest as nodes, and waypoint segments consisting of airways and temporary airways as edges, and using the ratio of predicted node traffic and predicted node capacity over the next k hours as node attribute vectors, construct a traffic situation map G. pre , means as follows:

[0038] G pre = (V, E, A, X).

[0039] Furthermore, step 3, which involves constructing historical traffic situation maps and recording the published policies corresponding to each historical traffic situation map, includes:

[0040] Step 3-1: Obtain the published strategies for the regions of interest from the historical strategy information data table. Let the number of published strategies be M.

[0041] Step 3-2: Select the m-th published policy, whose policy identifier is y. m ;

[0042] Step 3-3, using the policy identifier y m Obtain route information and temporary route information for the area of ​​interest from the historical route information data table;

[0043] Steps 3-4, using the policy identifier y m Obtain the predicted traffic and predicted capacity of all nodes k hours at the time of strategy release from the historical prediction information data table;

[0044] Steps 3-5: Using airports and waypoints within the area of ​​interest in the historical strategy information database as nodes, and the route segments consisting of routes and temporary routes within the area of ​​interest in the historical strategy information database as edges, and using the ratio of predicted flow to predicted capacity for node k hours in the historical strategy information database as node attributes, construct a historical traffic situation map G using the same method described in Step 2 for constructing the traffic situation map. m =(V m E m A m X m );

[0045] Steps 3-6: Record historical traffic situation map G m With policy identifier y m The correspondence;

[0046] Step 3-7: For all the published policies obtained in Step 3-1, repeat steps 3-2 to 3-6 to obtain M historical traffic situation maps G1, G2, G3, ..., G MAnd their corresponding strategy identifiers y1, y2, y3, ..., yM.

[0047] Furthermore, the recommendation strategy described in step 4 includes:

[0048] Step 4-1: Treat the M historical traffic situation maps as M types of traffic situation maps, use their corresponding policy identifiers as category labels, and classify the traffic situation map G according to the M categories of the historical traffic situation maps. pre Classify the data and obtain the category labels after classification;

[0049] Step 4-2: Obtain the recommended strategy content from the historical strategy information data table using category tags, i.e., strategy identifiers.

[0050] Furthermore, the effective period of the revised recommendation strategy described in step 5 includes:

[0051] Step 5-1, let the release time of the recommendation strategy be T. pub The strategy starts at time T. start The strategy ends at time T. end The current time is T. now Regarding the strategy release time T pub and the current time T now Rounding down by the hour (i.e., retaining only the hourly information) yields the rounding strategy release time T′. pub Sum and round down to the current time T′ now ;

[0052] Step 5-2, calculate the revised policy start time T′ start and the revised policy end time T′ end The details are as follows:

[0053]

[0054] Start time T′ using the modified strategy start and the revised policy end time T′ end Update and replace the recommended strategy start time T start Strategy end time T end .

[0055] Furthermore, the update of the historical strategy information database mentioned in step 6 includes:

[0056] Step 6-1: If the recommendation strategy is used directly by the user or used after modification, increment the recommendation count of the published strategy in the historical strategy information data table corresponding to the recommendation strategy by 1, and execute step 6-3; otherwise, execute step 6-2.

[0057] Step 6-2: Store the new strategy adopted by the user in the historical strategy information data table and set the recommendation count to 0. Store the predicted traffic and predicted capacity information of each airport and each waypoint in the current area of ​​interest for the next k hours in the historical prediction information data table. Store the route information and temporary route information of the area of ​​interest in the historical route information data table.

[0058] Step 6-3: Iterate through all published strategies in the historical strategy information data table, and regard published strategies whose recommendation count has been 0 for a preset period from the time of strategy publication as random strategies; delete the relevant information of random strategies in the historical strategy information data table, historical prediction information data table, and historical route information data table.

[0059] Beneficial effects:

[0060] (1) The method of this invention fills the gap in the research of strategy recommendation function technology in the field of air traffic flow management, and provides technical support for the technical breakthroughs in the development of air traffic flow management system.

[0061] (2) The method of the present invention helps to reduce the workload of traffic management personnel and improve traffic management efficiency.

[0062] (3) The method of the present invention helps to reduce the subjectivity of traffic management personnel when formulating strategies, maintain the consistency of traffic control work, and improve collaboration efficiency.

[0063] (4) By statistically analyzing the number of recommendations and periodically removing random strategies, it is helpful to reduce the probability of random strategies recurring and improve the scientific nature of the strategies. Attached Figure Description

[0064] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments, and the advantages of the present invention in the above and / or other aspects will become clearer.

[0065] Figure 1 This is a flowchart of a strategy recommendation method based on traffic situation map classification.

[0066] Figure 2 This is a schematic diagram of all published policy information for a certain period of time in control area B of one embodiment.

[0067] Figure 3 This is a diagram of the graph classifier structure.

[0068] Figure 4 This is a schematic diagram illustrating the strategy information for the recommendation strategy. Detailed Implementation

[0069] This invention addresses the gap in automatic strategy recommendation in current air traffic flow management systems by providing a strategy recommendation method based on traffic situation map classification. The principle of this invention is that traffic flow managers often directly use or refer to strategies developed in similar scenarios from their work experience when formulating strategies. This invention constructs a structured traffic situation map from the key information that traffic flow managers focus on when formulating strategies. Through graph classification, it finds historical traffic situation maps of the same category as the current traffic situation map, selects the published strategies corresponding to the historical traffic situation maps of the same category (those with the highest similarity to the current traffic situation map) as recommended strategies, and then adjusts the effective period of the recommended strategies before recommending them to users. The technical solution is as follows: A strategy recommendation method based on traffic situation map classification, such as... Figure 1 As shown, it includes the following steps:

[0070] Step 1: Create a historical policy information database. Store published policy information, airway information (including temporary airways) within the policy-issuing unit's controlled area at the time of policy issuance, and predicted flow capacity information for each airport and waypoint within the policy-issuing unit's controlled area for the next k hours; specifically including:

[0071] Step 1-1: Create a historical strategy information database;

[0072] Steps 1-2: Create a historical strategy information table in the historical strategy information database to store published strategy information. The stored content must include the following information: strategy identifier (the strategy identifier is the unique identifier of the strategy, which can be considered the strategy's "ID card"), strategy name, number of recommendations (recording the number of times the strategy was directly used or modified by users after being recommended), strategy duration (including strategy start time and strategy end time), strategy publication area, strategy publication time, and strategy details.

[0073] Steps 1-3: Create a historical route information data table in the historical strategy information database to store route information (including temporary routes) for the area of ​​interest when the strategy is issued. The stored content must include the following information: strategy identifier, strategy issuance area, route information, and temporary route information;

[0074] Steps 1-4: Create a historical forecast information table in the historical strategy information database to store the predicted traffic and capacity information for each airport and waypoint within the target area for the next k hours when the strategy is issued. The stored content must include the following information: strategy identifier, type (airport or waypoint), object name (airport four-letter code or waypoint name), strategy issuance area, predicted traffic for the next k hours, and predicted capacity for the next k hours.

[0075] Step 2: Select a controlled area as the area of ​​interest. Obtain predicted capacity information for airports, waypoints, and airways (including temporary airways) within the area of ​​interest to construct a traffic situation map; specifically including:

[0076] Step 2-1: Obtain the user's controlled area (i.e., the area of ​​concern) through the user's login information;

[0077] Step 2-2: Obtain route and temporary route information for the area of ​​interest;

[0078] Steps 2-3: Obtain the predicted traffic and capacity for each airport and waypoint in the area of ​​interest for the next k hours;

[0079] Steps 2-4: Constructing the traffic situation map G pre Steps 2-4 include:

[0080] Step 2-4-1: Establish node set V. Add the airports and waypoints of the region of interest to node set V sequentially. Assuming the total number of airports and waypoints in the region of interest is N, then V = {v1, v2, v3, ... v...} N}. Where v1 represents the first node, v2 represents the second node, and so on;

[0081] Step 2-4-2: Establish the edge set E. Parse the route segment information from the route and temporary route information of the area of ​​interest obtained in Step 2-2. If there exists a route segment information derived from v... i to v j For the route segment, <v i v j > Add it to the edge set E;

[0082] Step 2-4-3: Construct an adjacency matrix A (N×N). Traverse the edge set E, setting each element in A according to the following rules:

[0083]

[0084] Among them, A i，j This represents the element in the i-th row and j-th column of the adjacency matrix A;

[0085] Step 2-4-4: Calculate the ratio of predicted flow to predicted capacity for a node in the next k hours (if the predicted capacity is 0, then use 0.01 for calculation). Use the resulting k-dimensional vector as the node's attribute vector. Assume the predicted flow and predicted capacity for the i-th node in the j-th hour (j takes the values ​​1, 2, 3, ..., k) are f... i，j and c i，j Then the attribute vector x of the i-th node i It can be represented as:

[0086]

[0087] The node attribute matrix X, consisting of all nodes in the node set V, is: X = [x1 x2 … x N ];

[0088] Steps 2-4-5: Using airports and waypoints in the area of ​​interest as nodes, and waypoint segments consisting of airways and temporary airways as edges, construct a traffic situation map G using the ratio of predicted node traffic and predicted node capacity over the next k hours as node attribute vectors. pre = (V, E, A, X).

[0089] Step 3: Retrieve all published policies for the target area from the historical policy information database. For each published policy, retrieve the airport predicted capacity information, waypoint predicted capacity information, and route information (including temporary routes) for the target area at the time of policy publication from the historical policy information database. Construct a historical traffic situation map and record the published policies corresponding to each historical traffic situation map; specifically including:

[0090] Step 3-1: Retrieve all published strategies for the target region from the historical strategy information data table (assuming a total of M strategies).

[0091] Step 3-2: Select a published policy (assuming the selected published policy has the index i among all published policies), and record the policy identifier of the selected published policy as y. i ;

[0092] Step 3-3: Using the policy identifier y i Obtain route and temporary route information for the area of ​​interest from the historical route information data table;

[0093] Steps 3-4: Using policy identifier y i Obtain the predicted traffic and predicted capacity of all nodes k hours at the time of strategy release from the historical prediction information data table;

[0094] Steps 3-5: Using airports and waypoints in the region of interest from the historical strategy information database as nodes, using the route segments formed by air routes and temporary air routes in the region of interest from the historical strategy information database as edges, and using the ratio of predicted traffic flow to predicted capacity of node k hours from the historical strategy information database as node attributes, construct a historical traffic situation map G. i =(V i E i A i X i G i The construction process and steps 2-4 of G pre The construction process is basically the same, the only difference being V. i Ei A i and X i All information used in the construction process is taken from the historical strategy information database;

[0095] Steps 3-6: Record historical traffic situation map G i With policy identifier y i The correspondence;

[0096] Step 3-7: For all the published policies obtained in Step 3-1, repeat Steps 3-2 to 3-6 to obtain M historical traffic situation maps G1, G2, G3, ..., G M And the policy identifiers y1, y2, y3, ..., y1 corresponding to each historical traffic situation map. M .

[0097] Step 4: Treat each historical traffic situation map as a map category. By classifying the traffic situation maps (see supplementary explanation for map classification), find historical traffic situation maps of the same category and select the corresponding published strategies as recommended strategies. Specifically, this includes:

[0098] Step 4-1: Treat each historical traffic situation map as a type of traffic situation map, and use the strategy identifier corresponding to each historical traffic situation map as a type of category label for the traffic situation map. Classify the traffic situation maps according to the M categories of historical traffic situation maps and obtain the classified category labels.

[0099] Step 4-2: Obtain recommended strategy content information from the historical strategy information data table using the category labels (actually a strategy identifier) ​​after the traffic situation map is classified.

[0100] Step 5: Adjust the effective period of the recommendation strategy and then push it to users; specifically including:

[0101] Step 5-1: Assume the release time of the recommendation strategy is T. pub The strategy starts at time T. start The strategy ends at time T. end The current time is T. now First, regarding T pub and T now Rounding down by the hour (keeping only the hour information), we get T′. pub and T′ now ;

[0102] Step 5-2: Calculate the modified strategy start time T′ using the following formula. start and the revised policy end time T′ endThe strategy to update the recommended strategy starts at time T′. start The strategy ends at time T′. end :

[0103]

[0104] Step 6: Record user usage of the recommended strategy. If a user does not use the recommended strategy but formulates a new strategy, then when the new strategy is released, the new strategy and the airport predicted capacity information, waypoint predicted capacity information, and route information (including temporary routes) for the area of ​​interest at the time of the new strategy's release must be stored in the historical strategy information database. Periodically check and clear any incidental strategies and the airport predicted capacity information, waypoint predicted capacity information, and route information (including temporary routes) for the area of ​​interest at the time of the incidental strategy's release from the historical strategy information database. Specifically, this includes:

[0105] Step 6-1: If the recommendation strategy is used directly by the user or used after modification, increment the recommendation count of the published strategy in the historical strategy information data table corresponding to the recommendation strategy by 1, and skip step 6-2; otherwise, execute step 6-2.

[0106] Step 6-2: When a user publishes a new strategy, the new strategy information (with the recommendation count set to 0 at this time) is stored in the historical strategy information data table, the predicted traffic and predicted capacity of each airport and waypoint in the area of ​​interest for the next k hours are stored in the historical prediction information data table, and the waypoint information (including temporary waypoints) of the area of ​​interest is stored in the historical waypoint information data table.

[0107] Step 6-3: Iterate through all published strategies in the historical strategy information data table. Published strategies whose recommendation count remains 0 for a certain period (e.g., 3 years) from the strategy's publication date are considered random strategies. Delete the random strategy information from the historical strategy information data table, and then delete the relevant information from the historical prediction information data table and the historical route information data table using the strategy identifier of the random strategy.

[0108] Additional explanation: Graph classification is a graph-level learning task. In simple terms, it involves comparing the similarity between graphs of unknown categories and graphs of known categories by combining the structural information and node information of the graph, and finding the category of the unknown category graph from a limited number of graph categories. Graph classification functions are mostly implemented using graph neural network technology, which mainly consists of two steps: (1) using global pooling or hierarchical pooling to extract and aggregate the structural features and node features of the graph to obtain the vector space representation of the graph; (2) using the vector space classification method to classify the vector space representation of the graph. The specific method is as follows: (1) learning a score for each node in the graph through graph convolution; (2) eliminating nodes with low scores through graph pooling; (3) aggregating the remaining node information through a readout mechanism to obtain the vector space representation of the graph; (4) using the vector space representation of the graph to implement the graph classification function using the vector space classification method.

[0109] Example:

[0110] The following section, using a portion of the B-controlled area as the region of interest within a real-world traffic management system (A), further illustrates a specific implementation of the strategy recommendation method based on traffic situation map classification, as described in the present invention, with reference to the accompanying drawings. Parameter description: k = 6, T now The timeframe is 2021-09-17 19:01. The specific implementation steps are as follows:

[0111] 1. Create a historical strategy information database, and create historical strategy information data tables, historical route information data tables, and historical prediction information data tables in the historical strategy information database.

[0112] 2. Construct a traffic situation map

[0113] 2-1. Obtain information on airports (24 in total) and waypoints (267 in total) in control area B through the environmental data interface of traffic management system A. N = 24 + 267 = 291;

[0114] 2-2. Obtain information on 961 domestic air routes (including 254 temporary air routes) and corridor entrances of all airports in the B control area through the A flow management system, and parse it to obtain information on all air route segments (285 segments) in the B control area at the current time.

[0115] 2-3. Obtain the predicted traffic flow for each airport and waypoint in Control Area B for the next k hours through Traffic Management System A, and obtain the predicted capacity for each airport and waypoint in Control Area B for the next k hours through Traffic Management System A. Since there are many airports and waypoints in Control Area B, for simplicity, this implementation method only uses Airport C as an example. The predicted arrival traffic flow and predicted arrival capacity for Airport C for the next k hours (starting from 20:00 on September 17, 2021) are [48,51,43,40,31,29] and [45,45,45,45,45,45]. It is easy to see that Airport C is in a state of capacity imbalance for the next 2 hours, and traffic management personnel need to formulate and issue strategies to achieve capacity balance.

[0116] 2-4. Using the airport and waypoint information of control area B obtained in 2-1, the airway information of control area B obtained in 2-2, and the predicted capacity information of each airport and waypoint in control area B for the next k hours obtained in 2-3, construct a traffic situation map.

[0117] 3. Construct historical traffic situation maps

[0118] 3-1. Retrieve all historical policies issued in Control Area B from the historical policy information data table, such as... Figure 2 As shown;

[0119] 3-2. Select a strategy and record the strategy identifier (in the A traffic management system, the strategy identifier is generated when the strategy is formulated, usually as the primary key field of the database, and is generally not displayed in the interface);

[0120] 3-3. Using the policy identifier of the selected published policy, retrieve the route and temporary route information at the time of policy publication from the historical route information data table, and retrieve the predicted traffic flow and predicted capacity for each airport and waypoint in Control Area B for k hours at the time of policy publication from the historical forecast information data table, and construct a historical traffic situation map. Record the correspondence between the historical traffic situation map and the policy identifier;

[0121] 3-4. Repeat steps 3-2 and 3-3 for all historical strategies obtained in step 3-1 to obtain historical traffic situation maps corresponding to all published strategies.

[0122] 4. Obtain recommendation strategies through graph classification.

[0123] 4-1. Establish a graph classifier, the structure graph is as follows: Figure 3As shown in the figure. The graph classifier in this implementation method adopts a hierarchical pooling method. Hierarchical pooling can effectively solve the problem of a large amount of information loss in the early stage of graph pooling. By connecting the output of each pooling layer through a fully connected layer, the vector space representation of the graph is obtained. The vector space representation of the graph is then used as the input of a convolutional neural network classifier in the vector space, thereby realizing graph classification.

[0124] 4-2. Use historical traffic situation maps and the corresponding policy identifiers for each historical traffic situation map as training samples to train the graph classifier;

[0125] 4-3. Input the traffic situation map into the map classifier to obtain the category label of the traffic situation map. Then, use the category label (which is actually a policy identifier for a published policy) to retrieve recommended policy content information from the historical policy information data table. For example... Figure 4 As shown;

[0126] 5. Adjust the duration of the recommended strategy's effectiveness. For example... Figure 4 As shown, the recommendation strategy was released at 19:12 on June 25, 2021, started at 20:30, and ended at 23:59. The revised strategy start time was calculated to be 20:30 on September 17, 2021, and the revised strategy end time was 23:59 on September 17, 2021. After updating the strategy's start and end times, the strategy content will be pushed to users.

[0127] 6. Using the A traffic management system, a strategy simulation analysis was performed on the recommended strategy. The simulated predicted traffic flow for Airport C was [45,47,46,43,32,29], which greatly alleviated the capacity balancing requirement. After the user added the flow control "strategy start time: 2021-09-17 20:30; strategy end time: 2021-09-17 23:59; flow control content: 3 aircraft landing at Airport C via ENLAB point / 60 minutes _ minimum 10 minutes", another strategy simulation analysis was performed. The simulated predicted traffic flow for Airport C was [45,45,44,44,34,30], which met the capacity balancing requirement.

[0128] 7. This recommendation strategy is a user-modified recommendation strategy. After the strategy is published, the recommendation count of the corresponding published strategy in the historical strategy information data table will be incremented by 1.

[0129] In its specific implementation, this application provides a computer storage medium and a corresponding data processing unit. The computer storage medium is capable of storing a computer program, which, when executed by the data processing unit, can run the invention's content regarding a strategy recommendation method based on traffic situation map classification, as well as some or all of the steps in various embodiments. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0130] Those skilled in the art will clearly understand that the technical solutions in the embodiments of the present invention can be implemented using computer programs and their corresponding general-purpose hardware platforms. Based on this understanding, the technical solutions in the embodiments of the present invention, or the parts that contribute to the prior art, can be embodied in the form of computer programs, i.e., software products. These computer program software products can be stored in a storage medium and include several instructions to cause a device containing a data processing unit (which may be a personal computer, server, microcontroller, MCU, or network device, etc.) to execute the methods described in various embodiments or certain parts of the embodiments of the present invention.

[0131] This invention provides an idea and method for strategy recommendation based on traffic situation map classification. Many methods and approaches exist for implementing this technical solution; the above description is merely a preferred embodiment of the invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of this invention, and these improvements and modifications should also be considered within the scope of protection of this invention. All components not explicitly stated in this embodiment can be implemented using existing technologies.

Claims

1. A strategy recommendation method based on traffic situation map classification, characterized in that, Includes the following steps: Step 1: Create a historical policy information database to store published policies and traffic information within the controlled area of ​​the unit that published the policy at the time of its publication. Step 2: Select a controlled area as the area of ​​interest, obtain traffic information within the area of ​​interest, and construct a traffic situation map; Step 3: Obtain the published policies for the areas of interest from the historical policy information database. For each published policy, obtain the traffic information of the areas of interest when the policy was published from the historical policy information database, construct a historical traffic situation map, and record the published policies corresponding to each historical traffic situation map. Step 4: Select a recommended strategy. Treat each historical traffic situation map as a map category. By classifying the traffic situation maps into maps, find the historical traffic situation maps of the same category as the traffic situation map, and select the published strategy corresponding to the historical traffic situation map as the recommended strategy. Step 5: Adjust the effective period of the recommendation strategy and push it to users; Step 6: Update the historical strategy information database to record the user's usage of the recommended strategy. If the user does not use the recommended strategy but adopts a new strategy, store the new strategy and the traffic information of the area of ​​interest when the new strategy is released in the historical strategy information database. The recommendation strategy mentioned in step 4 includes: Step 4-1: Treat the M historical traffic situation maps as M types of traffic situation maps, use their corresponding policy identifiers as category labels, and classify the traffic situation map G according to the M categories of the historical traffic situation maps. pre Classify the data and obtain the category labels after classification; Step 4-2: Obtain the recommended strategy content from the historical strategy information data table using category tags, i.e., strategy identifiers.

2. The strategy recommendation method based on traffic situation map classification according to claim 1, characterized in that, The traffic information mentioned in step 1 includes: route information, airport predicted capacity information, and waypoint predicted capacity information.

3. The strategy recommendation method based on traffic situation map classification according to claim 2, characterized in that, The route information mentioned in step 1 includes temporary route information.

4. The strategy recommendation method based on traffic situation map classification according to claim 3, characterized in that, The historical strategy information database mentioned in step 1 includes: Historical strategy information data table, historical route information data table, and historical prediction information data table, among which, The historical strategy information data table stores information about published strategies, including: strategy identifier, strategy name, number of recommendations, strategy duration, strategy release area, strategy release time, and strategy content. The historical route information data table stores route information of the controlled area of ​​the unit that issued the policy when the policy was issued, including: policy identifier, policy issuance area, route information and temporary route information; The historical forecast information data table stores the predicted traffic and capacity information for each airport and waypoint within the control area of ​​the unit that issued the strategy at the time of the strategy release, for the next k hours.

5. The strategy recommendation method based on traffic situation map classification according to claim 4, characterized in that, The historical forecast information data table mentioned in step 1 includes: strategy identifier, object type, object name, strategy release area, predicted traffic for the next k hours, and predicted capacity for the next k hours; wherein, the object is an airport or waypoint.

6. The strategy recommendation method based on traffic situation map classification according to claim 5, characterized in that, The construction of the traffic situation map in step 2 includes: Step 2-1, establish the node set V, as follows: Airports and waypoints within the region of interest are sequentially placed into a node set V. Let N be the total number of airports and waypoints within the region of interest. The node set is then represented as follows: V={v1,v2,v3,…v N } Among them, v N This represents the Nth node; Step 2-2, establish the edge set E, as follows: The airway segment is analyzed from the airway information and temporary airway information in the traffic information of the area of ​​interest. If there is a segment by v i to v j The route segment will be <v i ,v j >Place it in the edge set E, where v i and v j Let i and j represent the i-th and j-th nodes in the node set V; Steps 2-3: Construct an adjacency matrix A of dimension N×N, as follows: Iterate through the edge set E and set each element in the adjacency matrix A according to the following rules: Among them, A i,j This represents the element in the i-th row and j-th column of the adjacency matrix A; Steps 2-4: Calculate the ratio of predicted flow to predicted capacity for each node in the node set V over the next k hours, and use the resulting k-dimensional vector as the attribute vector for that node; let f be the predicted flow and predicted capacity of the i-th node in the t-th hour. i,t and c i,t Where t = 1, 2, ..., k, then the attribute vector x of the i-th node is... i Represented as: The node attribute matrix X, consisting of all nodes in the node set V, is: X=[x1 x2 … x N ] Steps 2-5: Using airports and waypoints within the area of ​​interest as nodes, and waypoint segments consisting of airways and temporary airways as edges, and using the ratio of predicted node traffic and predicted node capacity over the next k hours as node attribute vectors, construct a traffic situation map G. pre , means as follows: G pre =(V,E,A,X)。 7. The strategy recommendation method based on traffic situation map classification according to claim 6, characterized in that, Step 3, which involves constructing historical traffic situation maps and recording the published policies corresponding to each historical traffic situation map, includes: Step 3-1: Obtain the published strategies for the regions of interest from the historical strategy information data table. Let the number of published strategies be M. Step 3-2: Select the m-th published policy, whose policy identifier is y. m ; Step 3-3, using the policy identifier y m Obtain route information and temporary route information for the area of ​​interest from the historical route information data table; Steps 3-4, using the policy identifier y m Obtain the predicted traffic and predicted capacity of all nodes k hours at the time of strategy release from the historical prediction information data table; Steps 3-5: Using airports and waypoints within the area of ​​interest in the historical strategy information database as nodes, and the route segments consisting of routes and temporary routes within the area of ​​interest in the historical strategy information database as edges, and using the ratio of predicted flow to predicted capacity for node k hours in the historical strategy information database as node attributes, construct a historical traffic situation map G using the same method described in Step 2 for constructing the traffic situation map. m =(V m E m A m ,X m ); Steps 3-6: Record historical traffic situation map G m With policy identifier y m The correspondence; Step 3-7: For all the published policies obtained in Step 3-1, repeat steps 3-2 to 3-6 to obtain M historical traffic situation maps G1, G2, G3, ..., G M and their corresponding strategy identifiers y1, y2, y3, ..., y M .

8. The strategy recommendation method based on traffic situation map classification according to claim 7, characterized in that, The effective period of the revised recommendation strategy described in step 5 includes: Step 5-1, let the release time of the recommendation strategy be T. pub The strategy starts at time T. start The strategy ends at time T. end The current time is T. now Regarding the strategy release time T pub and the current time T now Rounding down by the hour (i.e., retaining only the hourly information) yields the rounding strategy release time T′. pub Sum and round down to the current time T′ now ; Step 5-2, calculate the revised policy start time T′ start and the revised strategy end time T′ end The details are as follows: Start time T′ using the modified strategy start and the revised policy end time T′ end Update and replace the recommended strategy start time T start Strategy end time T end .

9. The strategy recommendation method based on traffic situation map classification according to claim 8, characterized in that, The updated historical strategy information database mentioned in step 6 includes: Step 6-1: If the recommendation strategy is used directly by the user or used after modification, increment the recommendation count of the published strategy in the historical strategy information data table corresponding to the recommendation strategy by 1, and execute step 6-3; otherwise, execute step 6-2. Step 6-2: Store the new strategy adopted by the user in the historical strategy information data table and set the recommendation count to 0. Store the predicted traffic and predicted capacity information of each airport and each waypoint in the current area of ​​interest for the next k hours in the historical prediction information data table. Store the route information and temporary route information of the area of ​​interest in the historical route information data table. Step 6-3: Iterate through all published strategies in the historical strategy information data table, and regard published strategies whose recommendation count has been 0 for a preset period from the time of strategy publication as random strategies; delete the relevant information of random strategies in the historical strategy information data table, historical prediction information data table, and historical route information data table.

Images