Aircraft intention recognition probability estimation method and system

Abstract

The invention provides an aircraft intention recognition probability estimation method and system, and relates to the technical field of aircraft intention recognition. Basic information of a target aircraft is obtained, and attribute information and state information are determined in the basic information; generating a semantic information fuzzy set according to the attribute information and the state information to serve as a antecedent structure parameter; obtaining target task information, and determining a membership function in the consequent structure according to the target task information; in combination with the basic information and the target task information, generating an intention probability prediction model of the target aircraft by aggregating a preset semantic rule; and obtaining basic information of the current target aircraft and determining a flight intention in combination with the intention probability prediction model. According to the method, the complex nonlinear relation is approached through the multiple rules, multiple kinds of complex data are fitted, meanwhile, each rule has semantic features, high interpretability can be achieved, and the technical effect of efficiently and accurately recognizing the intention of the aircraft is achieved.

Description

Technical Field

[0001] The present application relates to the technical field of aircraft intention recognition, and in particular to a method and system for estimating the probability of aircraft intention recognition. Background Art

[0002] Target intent refers to a certain purpose or desired state that the target unit hopes to achieve, which is highly related to the actual actions and state of the target unit. Different aircraft target trajectories usually represent different intentions. By monitoring aircraft elements and attributes and performing feature extraction and analysis to obtain the law of data changes, target intent prediction can be achieved.

[0003] The common methods of intention recognition can be divided into two categories. One is to realize reasoning based on prior knowledge. Traditional intention prediction methods mainly rely on the knowledge base and logical reasoning ability of prior knowledge to realize intention judgment. Prior knowledge includes domain expert knowledge, historical data and general natural laws. Experts in the field have formed a deep understanding of specific fields through long-term practice and experience accumulation; historical data contains action rules and potential information, which is conducive to inferring future trends; natural laws, as objective facts, can guide and assist the reasoning process. This method has strong reliability and interpretability, but poor flexibility. At the same time, the subjectivity of different expert knowledge is strong, and the situation converted into computational comprehension and processing is very complicated, and there are problems such as subjective bias. The other category is machine learning methods that do not require prior conditions. Methods based on neural networks are widely used in intention recognition. This type of method does not require pre-defined rules or knowledge. It can use machine learning algorithms to realize aircraft target feature extraction and information mining from data, and automatically learn the patterns and laws of aircraft targets in complex environments, so as to infer the intention of aircraft targets. At the same time, this method can continuously improve performance with the accumulation of effective data. However, in the process of intention judgment, the internal decision-making process of the neural network method is relatively complex, the entire process is difficult to explain, and the credibility and reliability of the model are low. In addition, training and deploying complex machine models requires high computing resources and time, and their feasibility in practical applications is limited. In summary, although the two existing methods perform well in some aspects, they both have some limitations. Methods based on prior knowledge require large amounts of data, are strongly influenced by subjective factors, and have high requirements for practical applications; machine learning methods are difficult to explain and have poor robustness.

[0004] Therefore, how to efficiently and accurately identify aircraft intentions has become a technical problem that needs to be solved urgently. Summary of the invention

[0005] In order to efficiently and accurately identify aircraft intentions, the present application provides an aircraft intention identification probability estimation method and system.

[0006] In the first aspect, the present application provides a method for estimating the probability of aircraft intention recognition using the following technical solution:

[0007] A method for estimating the probability of aircraft intention recognition, comprising:

[0008] Acquiring basic information of the target aircraft, and determining attribute information and status information in the basic information;

[0009] Generate a semantic information fuzzy set according to the attribute information and the state information as a precondition structure parameter;

[0010] Acquire target task information, and determine a membership function in a consequent structure according to the target task information;

[0011] Combining the basic information and the target mission information, generating an intention probability prediction model of the target aircraft by aggregating preset semantic rules;

[0012] The basic information of the current target aircraft is obtained and the flight intention is determined in combination with the intention probability prediction model.

[0013] Optionally, the step of generating a semantic information fuzzy set as a precondition structure parameter according to the attribute information and the state information includes:

[0014] generating an attribute set according to the attribute information;

[0015] generating a state set according to the state information;

[0016] According to the semantic information screening strategy, the attribute set and the state set are combined to generate a semantic information fuzzy set as a precondition structure parameter.

[0017] Optionally, the step of obtaining target task information and determining a membership function in a consequent structure according to the target task information includes:

[0018] Obtaining target task information and determining judgment conclusion information based on the target task information;

[0019] Determine whether the number of conclusions in the judgment conclusion information meets the preset conclusion condition;

[0020] If so, the membership function in the consequent structure is determined according to the judgment conclusion information.

[0021] Optionally, the step of determining a membership function in a consequent structure according to the judgment conclusion information includes:

[0022] Determining a conclusion probability set in the judgment conclusion information;

[0023] Determine the target parameter type in the semantic information fuzzy set by semantic reasoning according to the conclusion probability set;

[0024] A membership function in the consequent structure is established according to the target parameter type.

[0025] Optionally, the step of establishing a membership function in a consequent structure according to the target parameter type includes:

[0026] Establishing a rule set of the semantic information fuzzy set according to the target parameter type;

[0027] Performing rationality screening in the rule set to generate a target rule set;

[0028] The membership function in the consequent structure is generated by combining the target rule set in a rule aggregation manner.

[0029] Optionally, the step of obtaining basic information of the current target aircraft and determining the flight intention in combination with the intention probability prediction model includes:

[0030] Acquire basic information of the current target aircraft to generate an input parameter set;

[0031] Inputting the input parameter set into the intention probability prediction model and obtaining an output result;

[0032] Obtaining conclusions and corresponding probability information in the output results;

[0033] The flight intention is determined based on the conclusion and the corresponding probability information.

[0034] Optionally, the step of determining the flight intention according to the conclusion and the corresponding probability information includes:

[0035] Obtaining a preset determination threshold, and determining whether there is probability information satisfying the preset determination threshold in the output result;

[0036] If yes, determining the flight intention according to the probability information in the output result and the corresponding conclusion;

[0037] If not, a probability analysis report is generated according to the output result.

[0038] In a second aspect, the present application provides an aircraft intention recognition probability estimation system, the aircraft intention recognition probability estimation system comprising:

[0039] A basic information module, used to obtain basic information of the target aircraft, and to determine attribute information and status information in the basic information;

[0040] A precondition structure module, used for generating a semantic information fuzzy set as a precondition structure parameter according to the attribute information and the state information;

[0041] A subsequent structure module, used to obtain target task information and determine a membership function in the subsequent structure according to the target task information;

[0042] An aggregation module, used to combine the basic information and the target mission information to generate an intention probability prediction model of the target aircraft by aggregating preset semantic rules;

[0043] The intention judgment module is used to obtain the basic information of the current target aircraft and determine the flight intention in combination with the intention probability prediction model.

[0044] In a third aspect, the present application provides a computer device, comprising: a memory and a processor, wherein the processor executes the method described above when running computer instructions stored in the memory.

[0045] In a fourth aspect, the present application provides a computer-readable storage medium, comprising instructions, which, when executed on a computer, enable the computer to execute the method described above.

[0046] In summary, the present application includes the following beneficial technical effects:

[0047] This application obtains the basic information of the target aircraft, determines the attribute information and state information in the basic information; generates a semantic information fuzzy set based on the attribute information and state information as the antecedent structure parameter; obtains the target task information, and determines the membership function in the consequent structure based on the target task information; combines the basic information and the target task information, and generates the target aircraft's intention probability prediction model by aggregating preset semantic rules; obtains the basic information of the current target aircraft and determines the flight intention in combination with the intention probability prediction model. Approximating complex nonlinear relationships through multiple rules, fitting a variety of complex data, and each rule has semantic features, which can have strong interpretability, and achieves the technical effect of efficiently and accurately identifying aircraft intentions. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a schematic diagram of the computer device structure of the hardware operating environment involved in the embodiment of the present application.

[0049] Figure 2 It is a flowchart of the first embodiment of the aircraft intention recognition probability estimation method of the present application.

[0050] Figure 3 It is a membership function diagram of the target performing a reconnaissance action when the target of the first embodiment of the aircraft intention recognition probability estimation method of the present application is located in a general sea area;

[0051] Figure 4 It is a membership function diagram of the target conducting a reconnaissance operation when the target of the first embodiment of the aircraft intention recognition probability estimation method of the present application is located in a key sea area;

[0052] Figure 5 It is a membership function diagram of the target carrying out anti-submarine action when the target of the first embodiment of the aircraft intention recognition probability estimation method of the present application is located in a key sea area;

[0053] Figure 6 It is a membership function diagram of the target performing a reconnaissance action when the target is in communication with other targets in the first embodiment of the aircraft intention recognition probability estimation method of the present application;

[0054] Figure 7 This is a membership function diagram of the target conducting a reconnaissance operation when aircraft A approaches the target area in the first embodiment of the aircraft intention recognition probability estimation method of the present application;

[0055] Figure 8 This is a membership function diagram of the target conducting a reconnaissance operation when aircraft A approaches the target area in the first embodiment of the aircraft intention recognition probability estimation method of the present application;

[0056] Fig. 9 This is a membership function diagram of the target conducting a reconnaissance operation when aircraft A is close to aircraft B and a carrier-based aircraft takes off from aircraft B in the first embodiment of the aircraft intention recognition probability estimation method of the present application;

[0057] Fig.10 This is a membership function diagram of the target performing anti-submarine action when aircraft A is close to aircraft B and a carrier-based aircraft takes off from aircraft B in the first embodiment of the aircraft intention recognition probability estimation method of the present application;

[0058] Fig.11 It is a structural block diagram of the first embodiment of the aircraft intention recognition probability estimation system of the present application. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below through the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0060] Reference Figure 1 , Figure 1 A schematic diagram of the computer device structure of the hardware operating environment involved in the embodiment of the present application.

[0061] like Figure 1As shown, the computer device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM), or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk storage. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0062] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the computer device, and may include more or less components than shown in the figure, or combine some components, or arrange the components differently.

[0063] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and an aircraft intention recognition probability estimation program.

[0064] exist Figure 1 In the computer device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the present application can be set in the computer device, and the computer device calls the aircraft intention recognition probability estimation program stored in the memory 1005 through the processor 1001, and executes the aircraft intention recognition probability estimation method provided in the embodiment of the present application.

[0065] The present application embodiment provides a method for estimating the probability of aircraft intention recognition, referring to Figure 2 , Figure 2 This is a flow chart of the first embodiment of the aircraft intention recognition probability estimation method of the present application.

[0066] In this embodiment, the method for estimating the probability of aircraft intention recognition includes the following steps:

[0067] Step S10: Obtain basic information of the target aircraft, and determine attribute information and status information in the basic information.

[0068] It should be noted that the TS fuzzy rule model: Takagi-sugeno (TS) fuzzy rule model consists of a set of fuzzy rules that describe the relationship between input variables and output variables. Each rule consists of an antecedent structure (IF) and a consequent structure (THEN), representing a local linear function. The output of the TS fuzzy rule model is the aggregation of the outputs of each rule, where the weight is determined by the degree of activation of the rule.

[0069] It can be understood that the TS fuzzy rule model is introduced in this embodiment because the algorithm design of intent recognition needs to explore an efficient, accurate and interpretable reasoning model under the premise of introducing domain knowledge. Since the fuzzy rule model can approximate complex nonlinear relationships with multiple rules and fit a variety of complex data, and each rule has semantic features, it can have strong interpretability.

[0070] In the specific implementation, this embodiment realizes the interpretable reasoning of the probability estimation of the aircraft target intention based on fuzzy rules, explores the potential relationship between the attributes and behaviors of the aircraft's equipment and the tasks, and constructs corresponding fuzzy rules to approximate complex nonlinear relationships. The aircraft intention recognition probability estimation method based on fuzzy rule reasoning can be divided into two key parts: one is the construction of fuzzy rules; this embodiment takes into account all semantic information related to the aircraft's intention, that is, the aircraft's flight position, flight altitude, flight speed, distance from the target area, connectivity and distance with other equipment, etc., and uses it as semantic knowledge in the antecedent structure of the rule. In the consequent structure, each local output is related to the antecedent structure, and the membership function of the corresponding fuzzy set is constructed. The second is to aggregate the constructed fuzzy rules to achieve the final probability prediction, that is, output the probability of the corresponding aircraft target intention for different situations.

[0071] It is understandable that rules are an important way of common knowledge representation in artificial intelligence. Rule models can capture the correlation between input and output spaces, reasonably divide complex problems into a series of sub-problems, and realize local processing of complex information. Models based on "IF-THEN" (if..., then...) rules can realize the modeling of complex nonlinear systems due to their robustness and interpretability. Rule-based models can be constructed in various forms through different algorithms and optimization methods. Since fuzzy modeling can discover and mine hidden data information and realize human-centered knowledge representation, fuzzy rule systems have become a common framework for fuzzy rule generation and are widely used in many fields. Fuzzy rule modeling supports the basic paradigm of modularization, that is, each rule focuses on expressing the local modeling of complex systems and can decompose a complex problem into a series of sub-problems. The outstanding advantage of fuzzy rule reasoning is that it can transform fuzzy concepts into scientific and feasible control strategies and effectively deal with uncertainty and ambiguity in the real world. Mamdani fuzzy reasoning and Takagi-sugeno (TS) fuzzy reasoning, as two representative types of fuzzy systems in fuzzy reasoning, have been widely used in various industries. Mamdani fuzzy model is a commonly used fuzzy reasoning method, which mainly includes three stages: fuzzification, fuzzy reasoning and defuzzification. In the defuzzification stage, the fuzzy output is converted into an exact numerical result. The main difference between TS fuzzy reasoning and Mamdani fuzzy reasoning is that it combines the two stages of fuzzy reasoning and defuzzification into one stage. This means that the conclusion of TS fuzzy rules is directly numerical without the need for defuzzification.

[0072] TS fuzzy rules are generally composed of "If-Then" statements including antecedent and consequent structures. Fuzzy sets can interpretably represent and process the knowledge in the data. The conditions and consequent structures are usually expressed in the form of fuzzy sets. That is, the general form of the rule can be expressed as:

[0073] -If condition (the antecedent structure) is Ai,Then conclusion (the consequent structure) is Bi.

[0074] Among them, Ai and Bi are fuzzy sets of corresponding spaces. Rules are a mathematical expression to describe the relationship between fuzzy sets, which can characterize the local relationship between input space and output space. Rules have various forms and can express rich semantic information, providing powerful reasoning ability for fuzzy reasoning system.

[0075] Therefore, the target intention prediction probability estimation model based on rule reasoning can be divided into two parts: one is the construction of fuzzy rules; in detail, in the antecedent structure, this embodiment takes into account all semantic information related to the aircraft intention, that is, the flight position, flight altitude, flight speed, distance from the target area, connectivity and distance with other equipment, etc. of the equipment, and uses it as the semantic knowledge in the antecedent structure of the rule. In the consequent structure, each local output is related to the antecedent structure, and the membership function of the corresponding fuzzy set is constructed. The second is to aggregate the constructed fuzzy rules to achieve the final probability prediction, that is, output the probability of the corresponding aircraft intention for different situations.

[0076] It should be noted that, in the present embodiment, the attribute information and status information obtained refer to the flight performance information corresponding to the target aircraft and the hardware size information of the aircraft itself; the status information refers to the flight position, flight altitude, flight speed, distance from the target area or distance from other equipment, etc. of the target aircraft. The present embodiment does not limit the specific information content in the attribute information and status information.

[0077] Step S20: Generate a semantic information fuzzy set as antecedent structure parameter according to the attribute information and the state information.

[0078] It should be noted that the step of generating a fuzzy set of semantic information as a prior structure parameter based on attribute information and state information includes: generating an attribute set based on attribute information; generating a state set based on state information; and generating a fuzzy set of semantic information as a prior structure parameter by combining the attribute set and the state set according to a semantic information screening strategy.

[0079] It should be noted that, according to the semantic information screening strategy, combining the attribute set and the state set to generate the semantic information fuzzy set as the antecedent structural parameter means obtaining the semantic information in the attribute set and the semantic information in the state set at the same time, and generating the semantic information fuzzy set by merging the semantic information in the attribute set with the semantic information in the state set. Among them, the semantic information fuzzy set is used as the antecedent structural parameter to be applied in the TS fuzzy rule.

[0080] Step S30: Obtain target task information, and determine the membership function in the consequent structure according to the target task information.

[0081] It should be noted that the step of obtaining target task information and determining the membership function in the consequent structure according to the target task information includes: obtaining the target task information and determining the judgment conclusion information according to the target task information; judging whether the number of conclusions in the judgment conclusion information meets the preset conclusion condition; if so, determining the membership function in the consequent structure according to the judgment conclusion information.

[0082] In a specific implementation, the step of determining the membership function in the consequent structure according to the judgment conclusion information includes: determining a conclusion probability set in the judgment conclusion information; determining the target parameter type in the semantic information fuzzy set by semantic reasoning according to the conclusion probability set; and establishing the membership function in the consequent structure according to the target parameter type.

[0083] It should be noted that the step of establishing the membership function in the consequent structure according to the target parameter type includes: establishing a rule set of the semantic information fuzzy set according to the target parameter type; performing rationality screening in the rule set to generate a target rule set; and generating the membership function in the consequent structure by combining the target rule set through rule aggregation.

[0084] It is understandable that the purpose of the preset conclusion condition in this embodiment is to ensure that there are two or more conclusions in the judgment conclusion information. If there is only one or less than one conclusion in the judgment conclusion information, the TS fuzzy rule used in this embodiment cannot take effect. At this time, the judgment result corresponding to the preset conclusion condition will be sent to the preset port for reminder. Therefore, after the preset conclusion condition is set, it can avoid the situation where the number of conclusions in the subsequent conclusion is less than two, and avoid the waste of subsequent computing resources.

[0085] Step S40: combining the basic information and the target mission information, and generating an intention probability prediction model of the target aircraft by aggregating preset semantic rules.

[0086] In the specific implementation, the aircraft intention recognition problem in a simple war game simulation is taken as an example to analyze the aircraft intention recognition probability estimation method in this embodiment in detail.

[0087] Given scenario:

[0088] The vicinity of H Island, the vicinity of N Island and Reef, the AA area, and the BB area are all key sea areas;

[0089] The target area is around 12 nautical miles from H Island and around N Island and Reef;

[0090] In actual situations, when a certain equipment flies at an altitude of 5000-8000 meters, or 3000-4000 meters in key sea areas, it is very likely to be a reconnaissance operation. When the flight altitude is below 2500 meters, it is very likely to be an anti-submarine operation. For the above scenarios, this embodiment creates fuzzy rules based on language description to achieve semantic reasoning. represents the i-th rule related to the reconnaissance action, and its value represents the probability of belonging to the reconnaissance action; represents the jth prediction rule related to anti-submarine action, and its value represents the probability of taking anti-submarine action. The process is as follows:

[0091] The membership function of reconnaissance and anti-submarine operations is determined based on the aircraft's flight position, flight altitude, flight speed, distance from the target area, and communication and distance with other equipment.

[0092] There are generally two states of aircraft positions: general sea areas and key sea areas. In this part, this method constructs membership functions related to the flight altitude for these two states. For example, if the flight altitude of equipment A is 5000-8000 meters, or 3000-4000 meters in key sea areas, it is very likely to be a reconnaissance operation, and when the flight altitude is below 2500 meters, it is very likely to be an anti-submarine operation; therefore, three rules can be constructed for the two intention recognition results, namely:

[0093] Rule 1: If aircraft A is in a general sea area, then the probability of aircraft A conducting reconnaissance operations (such as Figure 3 When the target shown is located in a general sea area, the membership function of the target for reconnaissance operations is expressed as:

[0094]

[0095] Rule 2: If aircraft A is in a key sea area, then the probability of aircraft A conducting reconnaissance operations (such as Figure 4 When the target is located in the key sea area, the membership function of the target for reconnaissance operations is expressed as:

[0096]

[0097] Rule 3: If aircraft A is in a key sea area, then the probability of aircraft A conducting anti-submarine operations (such as Figure 5 When the target shown is located in the key sea area, the membership function of the target for anti-submarine action is expressed as:

[0098]

[0099] In the above formula, h represents the flight altitude information of the aircraft.

[0100] In the case of communication between aircraft and other aircraft, a membership function related to the flight altitude is constructed. For example, when aircraft A is in communication with aircraft B, and the flight altitude of aircraft A is between 1000-1500 meters, it must be a reconnaissance operation; therefore, the corresponding rule can be expressed as:

[0101] Rule 4: If aircraft A is in communication with aircraft B, then the probability that aircraft A conducts reconnaissance operations (e.g. Figure 6 When the target is in communication with other targets, the membership function of the target for reconnaissance action is expressed as:

[0102]

[0103] In actual process, the intention of the aircraft can be reflected by judging the distance between the aircraft and the target area.

[0104] Rule 5: If aircraft A approaches the target area, then the probability that the aircraft will conduct reconnaissance operations (such as Figure 7 As shown in the figure, when aircraft A approaches the target area, the membership function of the target for reconnaissance action can be expressed as:

[0105]

[0106] Rule 6: If aircraft A approaches the target area, then the probability that the aircraft will conduct anti-submarine operations (such as Figure 8 As shown in the figure, when aircraft A approaches the target area, the membership function of the target to conduct anti-submarine action can be expressed as:

[0107]

[0108] In the above formula, d represents the flight altitude information of the aircraft.

[0109] When analyzing the intention of an aircraft, it is related to the flight speed and the distance from other aircraft. For example, if aircraft A is 150-300 kilometers outside aircraft B, and a carrier-based aircraft takes off from aircraft B, then aircraft A is likely to conduct reconnaissance operations. If aircraft A is outside aircraft B and the distance is less than 150 kilometers, then aircraft A is more likely to conduct anti-submarine operations. The corresponding rules can be expressed as follows:

[0110] Rule 7: If aircraft A and aircraft B are close and the distance is d km, and there is a carrier-based aircraft taking off from aircraft B, then the probability of aircraft A conducting a reconnaissance operation is expressed as:

[0111]

[0112] Rule 8: If aircraft A is close to aircraft B and their flying speed is v km / h, and there is a carrier-based aircraft taking off from aircraft B, then the probability that aircraft A will conduct an anti-submarine operation (such as Fig.10 When aircraft A is close to aircraft B and a carrier-based aircraft takes off from aircraft B, the membership function of the target taking anti-submarine action is expressed as:

[0113]

[0114] Taking into account the domain knowledge based on expert experience and the general laws of the problem, eight rules are constructed around the reconnaissance mission and anti-submarine mission, of which four are related to reconnaissance operations and four are related to reconnaissance operations. On this basis, the intention probability of the aircraft, namely the X probability and the Y probability, is obtained by rule aggregation.

[0115] The final predicted probability of X can be expressed as p 吊撞 :

[0116]

[0117] The final predicted probability of Y can be expressed as p 链 :

[0118]

[0119] Step S50: Obtain basic information of the current target aircraft and determine the flight intention in combination with the intention probability prediction model.

[0120] Furthermore, in order to improve the accuracy of flight intention determination, the steps of obtaining basic information of the current target aircraft and determining the flight intention in combination with the intention probability prediction model include: obtaining basic information of the current target aircraft to generate an input parameter set; inputting the input parameter set into the intention probability prediction model and obtaining an output result; obtaining conclusions and corresponding probability information in the output result; and determining the flight intention based on the conclusions and the corresponding probability information.

[0121] It should be noted that the step of determining the flight intention based on the conclusion and the corresponding probability information includes: obtaining a preset judgment threshold, and determining whether there is probability information that meets the preset judgment threshold in the output result; if so, determining the flight intention based on the probability information in the output result and the corresponding conclusion; if not, generating a probability analysis report based on the output result.

[0122] It can be understood that, in this embodiment, the preset determination threshold can be screened according to specific probability information, and the setting of the preset determination threshold is preset according to specific usage conditions.

[0123] In the specific implementation, in order to verify the effectiveness of the proposed method in target intention recognition, data from three types of effective scenarios were collected on the war game simulation platform for verification.

[0124] Given the hypothetical background: the vicinity of H Island, the vicinity of N islands and reefs, the AA area, and the BB area are all key sea areas; the vicinity of 12 nautical miles from H Island and the vicinity of N islands and reefs are target areas;

[0125] Scenario 1: Aircraft A is now flying at an altitude of 3,500 meters, 30 nautical miles near Island H, and is about 150 kilometers away from aircraft B. What are the possible actions of aircraft A?

[0126] According to the condition "30 nautical miles around H Island", the location of equipment A is judged as the key sea area. According to the flight altitude of A and the distance from B, the 8 pre-defined rules are used to judge in sequence, and the following can be obtained:

[0127]

[0128]

[0129] Therefore, the probability that aircraft A intends to perform reconnaissance operations is 0.75, and the probability of anti-submarine operations is 0.15. The aircraft's likely mission is reconnaissance operations.

[0130] Scenario 2: Aircraft A is operating near Island H at a speed of 420km / h and is 200km outside of aircraft B. There are carrier-based aircraft taking off from B. What are the possible actions of aircraft A?

[0131] According to the "activity near H Island", the location of aircraft A is judged to be a key sea area. At the same time, aircraft A is close to aircraft B, and there is a carrier-based aircraft taking off from aircraft B. According to the distance d = 200 kilometers, it can be calculated by Rule 7 At the same time, the flight speed v = 420 km / h, which can be calculated by Rule 8 The final rule post-structure and aggregation results are as follows:

[0132]

[0133] Therefore, the probability that aircraft A intends to perform reconnaissance operations is 0.28, and the probability of anti-submarine operations is 0.6. The mission that aircraft A may perform is anti-submarine operations.

[0134] Scenario 3: Aircraft A is flying near island N at an altitude of 4,000 meters and 200 kilometers from the target area. What are the possible actions of aircraft A at this time?

[0135] According to the fact that aircraft A is flying near "N island reef", it is judged that the location of aircraft A is a key sea area. At the same time, the flight altitude h = 2500 meters. According to rules 2 and 3, it can be calculated that The aircraft approaches the target area and the distance is 200 kilometers. According to rules 5 and 6, it can be calculated that The final rule post-component structure and aggregation results are as follows:

[0136]

[0137]

[0138] Therefore, the probability that the aircraft intends to perform reconnaissance operations is 0.665, and the probability of anti-submarine operations is 0.5. The possible mission of the aircraft is reconnaissance operations.

[0139] It should be noted that, compared with the prior art, this embodiment has the following differences:

[0140] 1) Analyze the properties and behaviors of the target equipment, consider all semantic information related to the target aircraft's intentions, and generate fuzzy sets to interpretably represent and process the knowledge;

[0141] 2) Effectively utilize empirical information to construct semantic fuzzy rules to describe the local relationship of aircraft target intention probability estimation;

[0142] 3) Based on the constructed semantic rules, the interpretable reasoning of intent probability prediction is achieved through aggregation method, which is conducive to the balance between the accuracy and interpretability of the intent prediction model.

[0143] This embodiment obtains the basic information of the target aircraft, determines the attribute information and state information in the basic information; generates a semantic information fuzzy set based on the attribute information and state information as a precondition structure parameter; obtains the target task information, determines the second fuzzy set based on the target task information as a subsequent conclusion; determines the membership function between the semantic information fuzzy set and the second fuzzy set based on the semantic fuzzy rule strategy in combination with the basic information and the target task information; obtains the basic information of the current target aircraft, and determines the flight intention of the target aircraft based on the membership function. Approximating complex nonlinear relationships through multiple rules, fitting a variety of complex data, and each rule has semantic features, which can have strong interpretability, and achieves the technical effect of efficiently and accurately identifying the intention of the aircraft.

[0144] In addition, an embodiment of the present application also proposes a computer-readable storage medium, on which a program for estimating the probability of aircraft intention recognition is stored. When the program for estimating the probability of aircraft intention recognition is executed by a processor, the steps of the method for estimating the probability of aircraft intention recognition as described above are implemented.

[0145] Reference Fig.11 , Fig.11 This is a structural block diagram of the first embodiment of the aircraft intention recognition probability estimation system of the present application.

[0146] like Fig.11 As shown, the aircraft intention recognition probability estimation system proposed in the embodiment of the present application includes:

[0147] The basic information module 10 is used to obtain basic information of the target aircraft and determine attribute information and status information in the basic information;

[0148] A precondition structure module 20, for generating a semantic information fuzzy set according to the attribute information and the state information as a precondition structure parameter;

[0149] The subsequent structure module 30 is used to obtain target task information and determine the membership function in the subsequent structure according to the target task information;

[0150] Aggregation module 40, used to combine basic information and target mission information, and generate an intention probability prediction model of the target aircraft by aggregating preset semantic rules;

[0151] The intention judgment module 50 is used to obtain the basic information of the current target aircraft and determine the flight intention in combination with the intention probability prediction model.

[0152] It should be understood that the above is only an example and does not constitute any limitation on the technical solution of the present application. In specific applications, technicians in this field can make settings as needed, and the present application does not impose any limitation on this.

[0153] This embodiment obtains the basic information of the target aircraft, determines the attribute information and state information in the basic information; generates a semantic information fuzzy set based on the attribute information and state information as the antecedent structure parameter; obtains the target task information, and determines the membership function in the consequent structure based on the target task information; combines the basic information and the target task information, and generates the intention probability prediction model of the target aircraft by aggregating preset semantic rules; obtains the basic information of the current target aircraft and determines the flight intention in combination with the intention probability prediction model. Approximating complex nonlinear relationships through multiple rules, fitting a variety of complex data, and each rule has semantic features, which can have strong interpretability, and achieves the technical effect of efficiently and accurately identifying the intention of the aircraft.

[0154] In one embodiment, the antecedent structure module 20 is further used to generate an attribute set according to attribute information; generate a state set according to state information; and generate a semantic information fuzzy set as antecedent structure parameter by combining the attribute set and the state set according to a semantic information screening strategy.

[0155] In one embodiment, the consequent structure module 30 is also used to obtain target task information and determine judgment conclusion information based on the target task information; determine whether the number of conclusions in the judgment conclusion information meets the preset conclusion conditions; if so, determine the membership function in the consequent structure based on the judgment conclusion information.

[0156] In one embodiment, the consequent structure module 30 is also used to determine a conclusion probability set in the judgment conclusion information; determine the target parameter type in the semantic information fuzzy set by semantic reasoning based on the conclusion probability set; and establish a membership function in the consequent structure based on the target parameter type.

[0157] In one embodiment, the consequent structure module 30 is also used to establish a rule set of semantic information fuzzy set according to the target parameter type; perform rationality screening in the rule set to generate a target rule set; and generate a membership function in the consequent structure by combining the target rule set through rule aggregation.

[0158] In one embodiment, the intention judgment module 50 is also used to obtain basic information of the current target aircraft to generate an input parameter set; input the input parameter set into the intention probability prediction model and obtain an output result; obtain the conclusion and corresponding probability information in the output result; and determine the flight intention based on the conclusion and the corresponding probability information.

[0159] In one embodiment, the intention judgment module 50 is also used to obtain a preset judgment threshold and determine whether there is probability information that meets the preset judgment threshold in the output result; if so, the flight intention is determined based on the probability information in the output result and the corresponding conclusion; if not, a probability analysis report is generated based on the output result.

[0160] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present application. In practical applications, technicians in this field can select part or all of it according to actual needs to achieve the purpose of the present embodiment, and no limitation is made here.

[0161] In addition, for technical details not fully described in this embodiment, reference can be made to the method for estimating the probability of aircraft intention recognition provided in any embodiment of the present application, and will not be repeated here.

[0162] In addition, it should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0163] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0164] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory (ROM) / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods of each embodiment of the present application.

[0165] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for estimating the probability of aircraft intention recognition, characterized in that: include: Acquiring basic information of the target aircraft, and determining attribute information and status information in the basic information; Generate a semantic information fuzzy set according to the attribute information and the state information as a precondition structure parameter; Acquire target task information, and determine a membership function in a consequent structure according to the target task information; Combining the basic information and the target mission information, generating an intention probability prediction model of the target aircraft by aggregating preset semantic rules; The basic information of the current target aircraft is obtained and the flight intention is determined in combination with the intention probability prediction model.

2. The method for estimating the probability of aircraft intention recognition according to claim 1, characterized in that: The step of generating a semantic information fuzzy set as a precondition structure parameter according to the attribute information and the state information comprises: generating an attribute set according to the attribute information; generating a state set according to the state information; According to the semantic information screening strategy, the attribute set and the state set are combined to generate a semantic information fuzzy set as a precondition structure parameter.

3. The method for estimating the probability of aircraft intention recognition according to claim 1, characterized in that: The step of obtaining target task information and determining a membership function in a consequent structure according to the target task information comprises: Obtaining target task information and determining judgment conclusion information based on the target task information; Determine whether the number of conclusions in the judgment conclusion information meets the preset conclusion condition; If so, the membership function in the consequent structure is determined according to the judgment conclusion information.

4. The method for estimating the probability of aircraft intention recognition according to claim 3, characterized in that: The step of determining the membership function in the consequent structure according to the judgment conclusion information comprises: Determining a conclusion probability set in the judgment conclusion information; Determine the target parameter type in the semantic information fuzzy set by semantic reasoning according to the conclusion probability set; A membership function in the consequent structure is established according to the target parameter type.

5. The method for estimating the probability of aircraft intention recognition according to claim 4, characterized in that: The step of establishing a membership function in a consequent structure according to the target parameter type comprises: Establishing a rule set of the semantic information fuzzy set according to the target parameter type; Performing rationality screening in the rule set to generate a target rule set; The membership function in the consequent structure is generated by combining the target rule set in a rule aggregation manner.

6. The method for estimating the probability of aircraft intention recognition according to claim 1, characterized in that: The step of obtaining basic information of the current target aircraft and determining the flight intention in combination with the intention probability prediction model includes: Acquire basic information of the current target aircraft to generate an input parameter set; Inputting the input parameter set into the intention probability prediction model and obtaining an output result; Obtaining conclusions and corresponding probability information in the output results; The flight intention is determined based on the conclusion and the corresponding probability information.

7. The method for estimating the probability of aircraft intention recognition according to claim 6, characterized in that: The step of determining the flight intention according to the conclusion and the corresponding probability information comprises: Obtaining a preset determination threshold, and determining whether there is probability information satisfying the preset determination threshold in the output result; If yes, determining the flight intention according to the probability information in the output result and the corresponding conclusion; If not, a probability analysis report is generated according to the output result.

8. An aircraft intention recognition probability estimation system, characterized in that: The aircraft intention recognition probability estimation system comprises: A basic information module, used to obtain basic information of the target aircraft, and to determine attribute information and status information in the basic information; A precondition structure module, used for generating a semantic information fuzzy set as a precondition structure parameter according to the attribute information and the state information; A subsequent structure module, used to obtain target task information and determine a membership function in the subsequent structure according to the target task information; An aggregation module, used to combine the basic information and the target mission information to generate an intention probability prediction model of the target aircraft by aggregating preset semantic rules; The intention judgment module is used to obtain the basic information of the current target aircraft and determine the flight intention in combination with the intention probability prediction model.

9. A computer device, characterized in that: The device comprises: a memory and a processor, and when the processor runs the computer instructions stored in the memory, the processor executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The method comprises instructions, which, when executed on a computer, cause the computer to execute the method according to any one of claims 1 to 7.

Images