A method for understanding UAV command intention based on knowledge graph

Abstract

The present application belongs to the field of aviation command and control, and in particular, relates to a method for understanding drone command intentions based on a knowledge graph. It includes: obtaining a general knowledge graph in the field of drone command, wherein the general knowledge graph in the field of drone command is G∈(A, S, I, R), wherein A represents a platform entity, S represents a situation entity, I represents the command field intention, and R represents a relationship chain in the knowledge base; understanding drone command intentions based on the general knowledge graph in the field of drone command. The drone command intention understanding method based on the knowledge graph of the present application stratifies, summarizes, and counts knowledge of drone data, and can support the command system's intention understanding support in auxiliary decision-making, speech recognition, natural language understanding, etc., greatly improving the level of intelligence in the field of drone command.

Description

Technical Field

[0001] The present application belongs to the field of aviation command and control, and in particular, relates to a method for understanding drone command intentions based on a knowledge graph. Background Art

[0002] The air-based command and control system is an interactive control system with humans in the loop. The construction of the knowledge graph needs to be combined with the specific usage patterns of the drone. The traditional database is independent parameters, status and other information, lacking effective data associations and causal relationships of specific intentions.

[0003] Therefore, it is desired to have a technical solution to overcome or at least alleviate at least one of the above-mentioned defects of the prior art. Summary of the invention

[0004] The purpose of this application is to provide a method for understanding drone command intention based on knowledge graph to solve at least one problem existing in the prior art.

[0005] The technical solution of this application is:

[0006] A method for understanding UAV command intention based on knowledge graph, including:

[0007] Obtain a general knowledge graph in the field of drone command and control, where the general knowledge graph in the field of drone command and control is G∈(A, S, I, R), where A represents the platform entity, S represents the situation entity, I represents the command and control domain intention, and R represents the relationship chain in the knowledge base;

[0008] The drone command intention is understood based on the general knowledge graph in the drone command field.

[0009] In at least one embodiment of the present application, the platform entity A is a three-layer graph structure, defined as A∈{F, E, M, W}, respectively expressed as:

[0010] F represents the flight parameter knowledge base, F∈{f1, f2, f3, f4…f|F|}, which is defined as an N-tuple according to the UAV flight capability, where fi represents the i-th flight capability description, fi∈{Attribution[n], expression[n], paramater[n1]};

[0011] E represents the equipment knowledge base, E∈{e1, e2, e3, e4…f|E|}, which is defined as an N-tuple according to the flight capability of the drone, where ei represents the i-th equipment knowledge description, ei∈{Attribution[n], expression[n], state[n1], paramater[n2]};

[0012] M represents the mission load knowledge base, M∈{m1, m2, m3, m4…f|M|}, which is defined as an N-tuple according to the UAV flight capability, where mi represents the i-th mission load knowledge description, mi∈{Attribution[n], expression[n], state[n1], paramater[n2]};

[0013] W represents the weapon knowledge base, W∈{w1,w2,w3,w4…f|W|}, which is defined as N-tuples according to the UAV flight capability, where wi represents the knowledge description of the i-th mission payload, mi∈{Attribution[n],expression[n],state[n1],paramater[n2]}.

[0014] In at least one embodiment of the present application, the situation entity S is a two-layer graph structure, defined as S∈{T[nt×mt], TR[ntr×mtr], WE[nwe×mwe], AP[nap×map]}.

[0015] In at least one embodiment of the present application, the command domain intention I is a three-layer graph structure, defined as I∈{IF, IB}, IF is the flight operation intention, and IB is the tactical intention.

[0016] In at least one embodiment of the present application, the flight operation intention IF∈{LP[nlp], FC[nfc], EC[nec], MC[nec], WC[nec], WS[nws]}, LP is route planning, FC is flight control, EC is equipment operation, MC is payload operation, WC is weapon operation, and WS is special situation handling.

[0017] In at least one embodiment of the present application, the tactical intention IB∈{IB1, IB2, ..., IBn}, wherein IBi∈{SER / AT / CO / EC×R|A, S}, SER is search, ATT is attack, CO is coordination, EC is reactance, and R is a relationship network.

[0018] In at least one embodiment of the present application, the relationship chain R in the knowledge base exists in the form of a node in the graph database, which is defined as R∈{R[n]|A|S|times}, indicating that the relationship set is based on the platform entity and the situation entity, and the action time series is associated to finally form the entire time-sensitive graph network.

[0019] The invention has at least the following beneficial technical effects:

[0020] The knowledge graph-based drone command and control intention understanding method of this application stratifies, summarizes and counts drone data, which can support the command and control system in supporting decision-making, speech recognition, natural language understanding and other aspects of intention understanding, greatly improving the level of intelligence in the field of drone command and control. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This is a flowchart of understanding drone command intention based on knowledge graph according to one embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical scheme and advantages of the implementation of this application clearer, the technical scheme in the embodiment of this application will be described in more detail below in conjunction with the drawings in the embodiment of this application. In the drawings, the same or similar reference numerals throughout represent the same or similar elements or elements with the same or similar functions. The described embodiments are part of the embodiments of this application, not all of them. The embodiments described below with reference to the drawings are exemplary and are intended to be used to explain this application, and should not be construed as limitations on this application. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application. The embodiments of this application are described in detail below in conjunction with the drawings.

[0023] In the description of the present application, it should be understood that the terms "center", "longitudinal", "lateral", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the scope of protection of the present application.

[0024] The following is combined with Figure 1 This application is described in further detail.

[0025] This application provides a method for understanding drone command intention based on knowledge graph, including:

[0026] Obtain the general knowledge graph in the field of drone command and control. The general knowledge graph in the field of drone command and control is G∈(A, S, I, R), where A represents the platform entity, S represents the situation entity, I represents the command and control domain intention, and R represents the relationship chain in the knowledge base;

[0027] Understand drone command intentions based on the general knowledge graph in the drone command field.

[0028] In the preferred implementation scheme of the present application, the platform entity A is a three-layer graph structure, defined as A∈{F, E, M, W}, which are respectively represented as:

[0029] F represents the flight parameter knowledge base, F∈{f1, f2, f3, f4…f|F|}, which is defined as an N-tuple according to the UAV flight capability, where fi represents the i-th flight capability description, fi∈{Attribution[n], expression[n], paramater[n1]};

[0030] E represents the equipment knowledge base, E∈{e1, e2, e3, e4…f|E|}, which is defined as an N-tuple according to the flight capability of the drone, where ei represents the i-th equipment knowledge description, ei∈{Attribution[n], expression[n], state[n1], paramater[n2]};

[0031] M represents the mission load knowledge base, M∈{m1, m2, m3, m4…f|M|}, which is defined as an N-tuple according to the UAV flight capability, where mi represents the i-th mission load knowledge description, mi∈{Attribution[n], expression[n], state[n1], paramater[n2]};

[0032] W represents the weapon knowledge base, W∈{w1,w2,w3,w4…f|W|}, which is defined as N-tuples according to the UAV flight capability, where wi represents the knowledge description of the i-th mission payload, mi∈{Attribution[n],expression[n],state[n1],paramater[n2]}.

[0033] In this embodiment, the i-th flight capability description fi includes, see Table 1:

[0034] Table 1

[0035]

[0036] In this embodiment, the i-th device knowledge description ei includes, see Table 2:

[0037] Table 2

[0038]

[0039] In this embodiment, the i-th task load knowledge description mi includes, see Table 3:

[0040] Table 3

[0041]

[0042]

[0043] In this embodiment, the definition method of the weapon is defined, and the specific format is added according to the specific mounted weapons, see Table 4:

[0044] Table 4

[0045]

[0046] In the preferred embodiment of the present application, the situation entity S is a two-layer graph structure, defined as S∈{T[nt×mt], TR[ntr×mtr], WE[nwe×mwe], AP[nap×map]}, respectively expressed as, see Table 5:

[0047] Table 5

[0048]

[0049]

[0050] In a preferred embodiment of the present application, the command domain intention I is a three-layer graph structure, defined as I∈{IF, IB}, IF is the flight operation intention, IB is the tactical intention, and based on the flight operation intention, the tactical goal is achieved through load control and weapon control.

[0051] In this embodiment, the flight operation intention IF∈{LP[nlp], FC[nfc], EC[nec], MC[nec], WC[nec], WS[nws]}, LP is route planning, FC is flight control, EC is equipment operation, MC is load operation, WC is weapon operation, and WS is special situation handling. Among them, the special situation handling WS can be represented as WS∈{(LP, FC, EC)×R(A, S)}, which means that the intention is actively pushed through platform parameters and alarms. The other four specific definitions include, see Table 6:

[0052] Table 6

[0053]

[0054]

[0055]

[0056] In this embodiment, tactical intent IB∈{IB1, IB2, …, IBn} represents a tactical intent knowledge base, where IBi∈{SER / AT / CO / EC×R|A, S} indicates making decisions based on the platform knowledge base and the situation knowledge base, SER stands for search, ATT stands for strike, CO stands for coordination, EC stands for reactance, and R stands for the relationship network, to calculate the final intent.

[0057] In a preferred embodiment of the present application, the relationship chain R in the knowledge base is used to associate the A and S entities in the graph, and exists in the form of a node in the graph database, defined as R∈{R[n]|A|S|times}, which means that the relationship set is based on the platform entity and the situation entity, and associates the action time series to finally form the entire time-sensitive graph network.

[0058] In this embodiment, several types of relationships commonly used in the field of UAV command and control are defined, see Table 7:

[0059] Table 7

[0060]

[0061]

[0062] The knowledge graph-based method for understanding drone command and control intentions of the present application defines the data model and relationship network model of the drone command and control field knowledge graph, can establish a structured data network through a graph database, and at the same time build the logical relationship between nodes according to the knowledge system of the intention, and retrieve and feature count the nodes of the database through graph theory, and finally realize the understanding of drone command and control intentions based on the knowledge graph.

[0063] Traditional drone command and control systems are data-oriented control systems, where humans respond to and operate on data. This application is used to construct the correlation between drone parameters, status and other information and situation information and the causal relationship between human-in-the-loop control intentions, and to achieve human-machine intention understanding through multi-slot interlocking. Through the knowledge graph-based drone command and control intention understanding method of this application, drone data is layered, summarized and knowledge counted, which can support the command and control system's intention understanding support in auxiliary decision-making, speech recognition, natural language understanding and other aspects, greatly improving the level of intelligence in the field of drone command and control.

[0064] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for understanding drone command intention based on knowledge graph, It is characterized in that include: Obtain a general knowledge graph in the field of drone command and control, where the general knowledge graph in the field of drone command and control is G∈(A, S, I, R), where A represents the platform entity, S represents the situation entity, I represents the command and control domain intention, and R represents the relationship chain in the knowledge base; Understand the drone command intention based on the general knowledge graph in the drone command field; The platform entity A is a three-layer graph structure, defined as A∈{F, E, M, W}, which are respectively expressed as: F represents the flight parameter knowledge base, F∈{f1, f2, f3, f4…f|F|}, which is defined as an N-tuple according to the UAV flight capability, where fi represents the i-th flight capability description, fi∈{Attribution[n], expression[n], paramater[n1]}; E represents the equipment knowledge base, E∈{e1, e2, e3, e4…f|E|}, which is defined as an N-tuple according to the flight capability of the drone, where ei represents the i-th equipment knowledge description, ei∈{Attribution[n], expression[n], state[n1], paramater[n2]}; M represents the mission load knowledge base, M∈{m1, m2, m3, m4…f|M|}, which is defined as an N-tuple according to the UAV flight capability, where mi represents the i-th mission load knowledge description, mi∈{Attribution[n], expression[n], state[n1], paramater[n2]}; W represents the weapon knowledge base, W∈{w1,w2,w3,w4…f|W|}, which is defined as an N-tuple according to the UAV flight capability, where wi represents the knowledge description of the i-th mission payload, wi∈{Attribution[n], expression[n], state[n1], paramater[n2]}; The situation entity S is a two-layer graph structure, defined as S∈{T[nt×mt], TR[ntr×mtr], WE[nwe×mwe], AP[nap×map]}; The command domain intention I is a three-layer graph structure, defined as I∈{IF, IB}, where IF is the flight operation intention and IB is the tactical intention; The relationship chain R in the knowledge base exists in the form of nodes in the graph database, which is defined as R∈{R[n]|A|S|times}, indicating that the relationship set is based on the platform entity and the situation entity, and the action time series is associated to finally form the entire time-sensitive graph network; The drone command and control intention is understood based on the general knowledge graph in the drone command and control field. By defining the data model and relationship network model of the drone command and control field knowledge graph, a structured data network is established through a graph database. At the same time, the logical relationship between nodes is constructed according to the knowledge system of the intention. The nodes in the database are retrieved and feature counted through graph theory, and finally the drone command and control intention understanding based on the knowledge graph is realized.

2. According to the knowledge graph-based drone command intention understanding method of claim 1, It is characterized in that The flight operation intention IF∈{LP[nlp], FC[nfc], EC[nec], MC[nec], WC[nec], WS[nws]}, LP is route planning, FC is flight control, EC is equipment operation, MC is payload operation, WC is weapon operation, and WS is special situation handling.

3. According to the knowledge graph-based drone command intention understanding method of claim 1, It is characterized in that The tactical intention IB∈{IB1, IB2, …, IBn}, where IBi∈{SER / AT / CO / EC×R|A, S}, SER is search, AT is attack, CO is coordination, EC is reactance, and R is the relationship network.

Images