A ship behavior formalization expression method and system for knowledge reasoning
By abstracting ship objects into attributes, relationships, and spatiotemporal elements, and expressing them using a resource description framework and set theory, this method solves the problem of ship behavior identification and prediction in existing technologies, realizes structured modeling and semantic understanding of ship behavior, and supports intelligent control and situational awareness.
Patent Information
- Application Number
- CN202210073519.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-01-21
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2042-01-21
AI Technical Summary
Existing technologies struggle to accurately identify and express the state of ship behavior in real time. In particular, they are unable to detect abnormal behavior in macroscopic analysis, while microscopic analysis ignores the intrinsic evolution of ship behavior patterns, making accurate identification and prediction difficult.
We adopt a knowledge-based reasoning-oriented formal expression method for ship behavior. Through the ShipObject={Attribute,Relation,Space_Time} model, we abstract ship objects into elements containing attributes, relationships, and spatiotemporal factors. We use resource description frameworks and set theory for abstract expression, and use function mapping and set description methods to express ship behavior in characterization and formulaic form.
It achieves structured modeling and semantic understanding of ship behavior, enabling automatic identification and reasoning of current ship behavior, providing a theoretical basis for intelligent ship control and intelligent perception of maritime traffic situation.
Smart Images

Figure CN114443978B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of artificial intelligence knowledge expression technology, and in particular to a ship behavior formalization expression method and system oriented to knowledge reasoning. Background Art
[0002] Ships are the main actors in water transportation. The formal description and expression of ship behavior characteristics is the basis for modeling, intelligent cognition and reasoning of ship behavior characteristics, and is also an important basic research for realizing intelligent control of ships and intelligent perception of water transportation situations. To study ship behavior characteristics, it is necessary to effectively organize the information elements of water transportation scenes, analyze and clearly and completely express the relationship between the various elements of ship behavior, and discover the laws of ship behavior; to realize the formal expression of ship behavior, it is necessary to discover the constraints of ship behavior based on the dynamic changes of ship attributes and relationships between ships in the space-time elements, so as to analyze and express ship behavior.
[0003] At present, many experts and scholars have conducted a lot of research on ship behavior. In terms of studying ship behavior characteristics, they mainly analyze the macro behavior and micro behavior of ships. Macro behavior mainly uses classical algorithms to cluster ship trajectories, uses AIS data clustering to analyze ship behavior characteristics, obtains typical ship motion trajectories, combines Kalman filtering, long short-term memory neural network (LSTM) and other methods to predict ship navigation trajectories and real-time data status of ships, and finds the movement law of ships in a certain section, which has certain guiding significance for the navigation of ships in this section. However, macro analysis cannot detect and analyze the abnormal behavior of a certain ship, nor can it express the current behavior status of the ship in real time. Micro analysis describes the behavior of individual ships. Scholars have successively proposed k-means clustering algorithm and Bayesian network, consistency detection, recurrent neural network and other methods to identify abnormal behavior of ships, but these methods ignore the internal evolution of ship behavior patterns, so it is difficult to accurately identify and predict ship behavior. Summary of the invention
[0004] The technical problem to be solved by the present invention is to provide a method and system for formalizing the expression of ship behavior for knowledge reasoning in view of the defects in the prior art, which provides a theoretical and methodological basis for realizing structured modeling and semantic understanding of ship behavior.
[0005] The technical solution adopted by the present invention to solve its technical problem is:
[0006] The present invention provides a ship behavior formalization expression method oriented to knowledge reasoning, the method comprising the following steps:
[0007] Step 1: Analyze the basic characteristics of the ship entity and its behavior, express the ship abstractly as a ship object to describe the ship in detail, and model the ship object to form a ship object conceptual model: ShipObject = {Attribute, Relation, Space_Time}, that is, the ship object contains attribute elements, relationship elements and space-time elements;
[0008] Step 2: Use the resource description framework method and set theory method to abstractly express the attribute elements, relationship elements and time and space elements of the ship;
[0009] Step 3: Abstractly express the dynamic changes of ship attribute elements and relationship elements in time and space elements into ship behavior, and classify ship behavior into ship attribute behavior and ship relationship behavior according to the type of element change. Use function mapping and set description method to characterize and formulate ship behavior; that is, ShipBehavior={Attribute(t),Relation(t)}, where t∈[t i-1 ,t i ], i≥1;
[0010] Step 4: The ship behavior formalization expression method is applied to a computer to identify and understand the ship behavior and to reason about the ship behavior knowledge.
[0011] Furthermore, the method in step 1 of the present invention specifically includes:
[0012] Using the idea of object-oriented programming in Java computer language, the ship entity is abstracted into an object. In the water traffic scene, each ship object has corresponding attributes, time and space, and relationships with other objects. The ship is abstracted into a conceptual model:
[0013] ShipObject={Attribute,Relation,Space_Time}
[0014] That is, the ship object includes the attribute element Attribute, the relationship element Relation and the time and space element Space_Time.
[0015] Furthermore, the method in step 2 of the present invention specifically includes:
[0016] Attribute elements are used to provide descriptive data for ship objects and their behaviors and events. Attribute elements are divided into parameter attributes and functional attributes. Parameter attributes describe the attribute information of ship objects for further analysis and calculation. Parameter attributes are further divided into inherent attributes and dynamic attributes. Inherent attributes describe the inherent information of ships, including ship name, ship type, and ship size information. Dynamic attributes are attribute information of ship objects that changes with ship behaviors or events, including ship position, heading, speed, and ship draft information. Functional attributes describe the functional information of ship objects, including the ship's maneuverability and the ship's ability to detect and avoid obstacles.
[0017] Relationship elements are used to describe the association between ship objects. The relationship elements between ship objects will change with the changes in the attribute characteristics, scenes, and observation dimensions of the ship objects. The relationship elements between ship objects include spatial relationships, temporal relationships, and semantic relationships.
[0018] The space-time elements are used to describe the topological relationship between ships, ships and the environment, and the environment and the environment. They are described using the regional link calculation model, including separation, inclusion, intersection, overlap, intangency and circumtangency.
[0019] Furthermore, the method in step 2 of the present invention specifically includes:
[0020] Spatial relationship, used to describe the distance between two ship objects, including quantitative description and qualitative description; quantitative description refers to the Euclidean distance between the two ship objects. Qualitatively describe the distance between ship objects:
[0021]
[0022] Among them, (x A ,y A ), (x B ,y B ) represents the coordinates of two points, D t Indicates safe distance, D n The threshold value of the safety distance, D i The distance threshold indicating the presence of collision risk, D m The distance threshold indicating the existence of an urgent situation;
[0023] Time relations are used to describe the behavior and events of ships in the time dimension. According to the different time dimensions, time relations are divided into time points and time periods. A time point describes a certain moment or time, including the moment when the ship turns left and the moment when two ships collide. A time period describes a time range, including the time when the ship is anchored in the anchorage and the time when the ship crosses the narrow waterway. The expression of time elements is as follows: Figure 4shown.
[0024] Semantic relations are used to describe the relationships between concepts, concepts and instances, and instances and instances.
[0025] Furthermore, the method of abstract expression in step 2 of the present invention specifically includes:
[0026] The ship is abstracted into a space-time object in cyberspace, and this space-time object is composed of many attributes. The attributes expressed only from the object itself are called attribute elements, and the attributes that need to rely on another object to be expressed are called relationship elements. The minimum expression unit of these elements is shown in the following formula:
[0027] parameter=(Object,Type i ,Value i , t i ), (i∈N + ),
[0028] Among them, parameter is the smallest unit describing a ship object, Object is a specific ship object, Type represents the specific element type of a specific ship object; Value is the specific value of the specific element type of a specific ship object, and N+ represents a positive integer;
[0029] The ship object is expressed as:
[0030] ShipObject = {Parameter}
[0031] ={Parameter Attribute ,Parameter Relation}
[0032] ={Attribute elements, Relational elements, Time_Space}
[0033] Among them, ShipObject represents the ship object; Parameter Atttribute Indicates the attribute elements of the ship object, Parameter Relation It represents the relationship element of the ship, and Time_Space represents the time-space element.
[0034] Furthermore, the method in step three of the present invention specifically includes:
[0035] The ship behavior is expressed in characters and formulas using function mapping and set description methods, that is, ShipBehavior = {Attribute(t), Relation(t)}, where t∈[t i -1, ti ], i≥1;
[0036] Attribute behavior refers to the change of ship attribute information; the ship attribute behavior refers to the change of the ship's position, heading, speed, signal light type and other attribute values; attribute behavior is expressed by the following formula: AttributeBehavior = {Attribute(t), ChangeType}, where: Attribute(t) represents the function of the ship attribute value changing over time, and ChangeType represents the type of attribute change;
[0037] Relation behavior refers to the change of ship relationship elements over time, including spatial relationship, temporal relationship and semantic relationship, and also includes the generation, change and disappearance of relationship; relationship behavior often occurs with the occurrence of attribute behavior; a four-tuple is used to represent the change of relationship, RelationBehavior = {Relation i ,ChangeType,Relation j , T}, where: Relation i and Relation j It is the relationship before and after the change; ChangeType is the type of change that occurs in the association relationship, which can be a change in the spatial topological relationship, distance relationship and orientation relationship, or a change in the time relationship and semantic relationship. T represents time.
[0038] Furthermore, the method in step three of the present invention specifically includes:
[0039] Ship behavior is a dynamic change in space. The expression of ship behavior is:
[0040] ShipBehavior = {Behavior Attribute , Behavior Relation}
[0041] =f(Parameter),(i∈N + )
[0042] Among them, Behavior Attribute Ship's attribute behavior, Behavior Relation The relational behavior of ships, f(·) is a value about comparing the same element of the same object at different times, N+ represents a positive integer;
[0043] The input parameters are:
[0044] Parameter={(shipA, speed, 10, t i-1 ), (shipA, speed, 15, ti )}
[0045] The ship behavior is expressed as:
[0046]
[0047] The specific ship behavior semantics are shown in the following table:
[0048]
[0049] Among them, the attribute elements include velocity and course elements, which represent the speed and course of the ship respectively; the relationship elements include relative distance, relative bearing, and topology elements, which represent the relative distance, relative orientation, and topological relationship between two water traffic objects respectively. out = -1 means that when the ship is outside a certain water area, R in =1 means the ship is within a certain water area;
[0050] Value ti -Value ti-1 The corresponding meaning is the numerical difference of the corresponding feature types at different times.
[0051] Furthermore, the expression of the attribute behavior and relationship behavior of the ship in step 3 of the present invention is:
[0052] 1) Specific expression of attribute behavior:
[0053] The specific formula of attribute behavior is expressed as:
[0054] Behavior Attribute =f(Parameter Attribute )
[0055] Parameter Attribute ={(Object, Type j ,Value j , t j )},(j∈Z,j≥2),
[0056] For ship A:
[0057]
[0058] Then the attribute behavior of ship A is:
[0059] Behavior Attribute =f(Parameter Attribute )
[0060] ={f(parameter1), f(parameter2)}
[0061] ={(v2-v1),(c2-c1)}
[0062] ={"slow down","turn right"}, t∈[t i-1 , t i ]
[0063] 2) Specific expressions of relational behavior:
[0064] The specific formula of relational behavior is expressed as:
[0065] Behavior Relation =f(Parameter Relation )
[0066] Parameter Relation ={(Object, Type k ,Value k , t k )},(k∈Z + , k≥2),
[0067] For Ship A and Ship B:
[0068]
[0069] Then the relationship behavior between ships A and B is:
[0070] Behavior Relation =f(Parameter Relation )
[0071] ={f(parameter1), f(parameter2)}
[0072] ={(d2-d1),(c2-c1)}
[0073] = {“approach”, “move towards the bow”}, t∈[t i-1 , t i ]
[0074] Furthermore, the method in step 4 of the present invention specifically includes:
[0075] By programming in Java, ship objects are defined, encapsulated and called, and the attributes, relationships and time and space elements of the ship objects are input, the current behavior of the ship and the behavior that the ship should take can be automatically identified and output.
[0076] The present invention provides a ship behavior formalization expression system oriented to knowledge reasoning, the system comprising:
[0077] Data input interface, used to connect ship sensor data to the system;
[0078] The data formalization processing module is used to analyze the basic characteristics of ship entities and their behaviors, abstractly express ships into ship objects to describe ships in detail, and model ship objects to form ship object conceptual models, that is, ship objects contain attribute elements, relationship elements, and time and space elements; use the resource description framework method and the set theory method to abstractly express the ship's attribute elements, relationship elements, and time and space elements; abstractly express the dynamic changes of ship attribute elements and relationship elements in time and space elements into ship behaviors, and classify ship behaviors into ship attribute behaviors and ship relationship behaviors according to the type of element changes, and use function mapping and set description methods to characterize and formulate ship behaviors; obtain ship behavior formalized knowledge data;
[0079] A storage module for storing formally expressed ship behavior data;
[0080] The knowledge reasoning module is used to apply the knowledge formally expressed in the ship, use Java language for programming, define, encapsulate and call the ship object, input the attributes, relationships and time and space elements of the ship object, and automatically identify and infer the current behavior of the ship and the behavior that the ship should take.
[0081] The beneficial effects of the present invention are as follows: the ship behavior formalization expression method and system for knowledge reasoning of the present invention abstractly expresses the ship entity object, explores the relationship between the ship behavior and the ship attribute elements, relationship elements and time and space elements, and classifies the ship behavior according to the type of change in the characteristics of the ship elements. A method for dynamically expressing the ship behavior oriented to the changes in the ship object entity and its characteristic elements is proposed, which provides a theoretical and methodological basis for realizing the structured modeling and semantic understanding of the ship behavior. BRIEF DESCRIPTION OF THE DRAWINGS
[0082] The present invention will be further described below with reference to the accompanying drawings and embodiments, in which:
[0083] Figure 1 This is a flow chart of a ship behavior formalization expression method oriented to knowledge reasoning of the present invention;
[0084] Figure 2 It is an abstract flow chart of ship behavior of the present invention;
[0085] Figure 3 A schematic diagram of an application device for formalizing the behavior of a ship according to the present invention;
[0086] Figure 4 It is an expression of the time element of the present invention. DETAILED DESCRIPTION
[0087] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.
[0088] This paper proposes a ship behavior formalization expression method oriented to knowledge reasoning. Figure 1 to Figure 2 The present invention provides an embodiment of a method for formalizing ship behavior for knowledge reasoning.
[0089] Reference Figure 1 , Figure 1 The flowchart of an embodiment of a ship behavior formal expression method for knowledge reasoning of the present invention includes:
[0090] The S101 system sorts out the basic characteristics of ship entities and their behaviors, and abstractly expresses ships as ship objects. It realizes the specific description of ships in the information space constructed by computers, and expresses them in the form of data, models, rules, logic, knowledge, etc. The modeling of ship objects forms a ship object conceptual model: ShipObject = {Attribute, Relation, Space_Time}, that is, the ship object contains attribute elements, relationship elements, and time and space elements.
[0091] S102 uses the resource description framework method and set theory method to abstractly express ship elements;
[0092] S103 abstractly expresses the dynamic changes of ship attribute elements and relationship elements in time and space elements into ship behavior. According to the type of element change, ship behavior is classified into ship attribute behavior and ship relationship behavior, and the ship behavior is expressed in characters and formulas using function mapping and set description methods; that is, ShipBehavior={Attribute(t),Relation(t)}, where t∈[t i-1 ,t i ],(i≥1);
[0093] S104 applies the ship behavior formal expression method to computer recognition and understanding of ship behavior, and based on this, realizes reasoning of ship behavior knowledge.
[0094] Reference Figure 2 , Figure 2 The abstract flow chart of ship behavior of the present invention includes:
[0095] The resource description framework method and the set theory method are used to abstractly express the ship elements; the dynamic changes of ship attribute elements and relationship elements in time and space elements are abstractly expressed as ship behavior. According to the type of element change, the ship behavior is classified into ship attribute behavior and ship relationship behavior, and the function mapping and set description method are used to characterize and express the ship behavior; that is, ShipBehavior={Attribute(t),Relation(t)}, where t∈[t i-1 ,t i ],(i≥1);
[0096] 1. Abstraction of ship behavior. The basic characteristics of ship entities and their behaviors are sorted out, and ships are abstractly expressed as ship objects. A specific description of ships is achieved in the information space constructed by computers, and expressed in the form of data, models, rules, logic, knowledge, etc. Modeling of ship objects forms a ship object conceptual model: ShipObject = {Attribute, Relation, Space_Time}, that is, the ship object contains attribute elements, relationship elements, and space-time elements. Use the resource description framework method and set theory method to abstractly express ship elements; abstractly express the dynamic changes of ship attribute elements and relationship elements in space-time elements into ship behavior. And classify ship behavior into ship attribute behavior and ship relationship behavior according to the type of element change, and use function mapping and set description methods to characterize and formulate ship behavior; that is, ShipBehavior = {Attribute(t), Relation(t)}, where t∈[t i-1 ,t i ],(i≥1);
[0097] 2. Formal expression of ship behaviors. Ship behaviors are formed into a set and expressed as Behavior. Ship attribute behaviors and relationship behaviors are expressed as Behavior. Attribute 、Behavior Relation express.
[0098] The ship behavior is expressed as:
[0099] ShipBehavior = {Behavior Attribute , Behavior Relation}
[0100] =f(Parameter),(i∈N + )
[0101] Attribute behavior affects the attribute information of the ship, that is, the attribute behavior will change or update the attributes of the ship. Its parameter input set should include attribute type (CH Types), attribute field (bfields), field type (bfieldsTypes), attribute value (bfValues), and attribute type, attribute field, field type, and attribute value after the behavior. Taking the heading and speed of ship A as an example, the formal expression of ship attribute behavior is as follows:
[0102] The specific formula of attribute behavior is expressed as:
[0103] Behavior Attribute =f(Parameter Attribute )
[0104] Parameter Attribute ={(Object, Type j ,Value j , t j )},(j∈Z,j≥2),
[0105] For ship A:
[0106]
[0107] Then the attribute behavior of ship A is:
[0108] Behavior Attribute =f(Parameter Attribute )
[0109] ={f(parameter1), f(parameter2)}
[0110] ={(v2-v1),(c2-c1)}
[0111] ={"slow down","turn right"}, t∈[t i-1 , t i ]
[0112] Relationship behavior reflects the relationship changes between multiple entity elements. Ship relationship behavior changes the relationship types and relationship strengths such as spatial relationship, temporal relationship, and semantic relationship between two or more ships. The spatial distance and orientation of ships A and B are used as examples to illustrate the formal expression of ship relationship behavior.
[0113] The specific formula of relational behavior is expressed as:
[0114] Behavior Relation =f(Parameter Retation )
[0115] Parameter Relation ={(Object, Type k ,Value k , t k )},(k∈Z + , k≥2),
[0116] For Ship A and Ship B:
[0117]
[0118] Then the relationship behavior between ships A and B is:
[0119] Behavior Relation =f(Parameter Relation )
[0120] ={f(parameter1),f(parameter2)}
[0121] ={(d2-d1),(c2-c1)}
[0122] = {“approach”, “move towards the bow”}, t∈[t i-1 , t i ]
[0123] 3. Application of formal expression of ship behavior.
[0124] By programming in Java, ship objects are defined, encapsulated and called, and the attributes, relationships and time and space elements of the ship objects are input, the current behavior of the ship and the behavior that the ship should take can be automatically identified and output.
[0125] Reference Figure 3 , a schematic diagram of an application device for formalizing the ship behavior of the present invention, comprising:
[0126] Data input interface, used to connect ship sensor data to the system;
[0127] The data formalization processing module is used to analyze the basic characteristics of ship entities and their behaviors, abstractly express ships into ship objects to describe ships in detail, and model ship objects to form ship object conceptual models, that is, ship objects contain attribute elements, relationship elements, and time and space elements; use the resource description framework method and the set theory method to abstractly express the ship's attribute elements, relationship elements, and time and space elements; abstractly express the dynamic changes of ship attribute elements and relationship elements in time and space elements into ship behaviors, and classify ship behaviors into ship attribute behaviors and ship relationship behaviors according to the type of element changes, and use function mapping and set description methods to characterize and formulate ship behaviors; obtain ship behavior formalized knowledge data;
[0128] A storage module for storing formally expressed ship behavior data;
[0129] The knowledge reasoning module is used to apply the knowledge formally expressed in the ship, use Java language for programming, define, encapsulate and call the ship object, input the attributes, relationships and time and space elements of the ship object, and automatically identify and infer the current behavior of the ship and the behavior that the ship should take.
[0130] It should be understood that those skilled in the art can make improvements or changes based on the above description, and all these improvements and changes should fall within the scope of protection of the appended claims of the present invention.
Claims
1. A ship behavior formalization method for knowledge reasoning, characterized in that: The method comprises the following steps: Step 1: Analyze the basic characteristics of the ship entity and its behavior, express the ship abstractly as a ship object to describe the ship in detail, and model the ship object to form a ship object conceptual model: ShipObject = {Attribute, Relation, Space_Time}, that is, the ship object contains attribute elements, relationship elements and space-time elements; Step 2: Use the resource description framework method and set theory method to abstractly express the attribute elements, relationship elements and time and space elements of the ship; Step 3: Abstractly express the dynamic changes of ship attribute elements and relationship elements in time and space elements into ship behavior, and classify ship behavior into ship attribute behavior and ship relationship behavior according to the type of element change. Use function mapping and set description method to characterize and formulate ship behavior; that is, ShipBehavior={Attribute(t),Relation(t)}, where t∈[t i-1 ,t i ], i≥1; t represents time, i represents time node; Step 4: The ship behavior formalization expression method is applied to a computer to identify and understand the ship behavior, so as to realize reasoning of the ship behavior knowledge; The method in step 2 specifically includes: Attribute elements are used to provide descriptive data for ship objects and their behaviors and events. Attribute elements are divided into parameter attributes and functional attributes. Parameter attributes describe the attribute information of ship objects for further analysis and calculation. Parameter attributes are further divided into inherent attributes and dynamic attributes. Inherent attributes describe the inherent information of ships, including ship name, ship type, and ship size information. Dynamic attributes are attribute information of ship objects that changes with ship behaviors or events, including ship position, heading, speed, and ship draft information. Functional attributes describe the functional information of ship objects, including the ship's maneuverability and the ship's ability to detect and avoid obstacles. Relationship elements are used to describe the association between ship objects. The relationship elements between ship objects will change with the changes in the attribute characteristics, scenes, and observation dimensions of the ship objects. The relationship elements between ship objects include spatial relationships, temporal relationships, and semantic relationships. Spatiotemporal elements are used to describe the topological relationship between ships, ships and the environment, and the environment and the environment. They are described using a regional link calculation model, including separation, inclusion, intersection, overlap, intangent, and circumtangent. The method in step 2 specifically includes: Spatial relationship, used to describe the distance between two ship objects, including quantitative description and qualitative description; quantitative description refers to the Euclidean distance between the two ship objects. Qualitatively describe the distance between ship objects: Among them, (x A ,y A ), (x B ,y B ) represents the coordinates of two points, D t Indicates safe distance, D n The threshold value of the safety distance, D i The distance threshold indicating the presence of collision risk, D m The distance threshold indicating the existence of an urgent situation; Time relations are used to describe the behavior and events of ships in the time dimension. According to the different time dimensions, time relations are divided into time points and time periods. A time point describes a certain moment or time, including the moment when a ship turns left and the moment when two ships collide. A time period describes a time range, including the time when a ship is anchored in an anchorage and the time when a ship crosses a narrow waterway. Semantic relations are used to describe the relationships between concepts, concepts and instances, and instances and instances; The method of abstract expression in step 2 specifically includes: The ship is abstracted into a space-time object in cyberspace, and this space-time object is composed of many attributes. The attributes expressed only from the object itself are called attribute elements, and the attributes that need to rely on another object to be expressed are called relationship elements. The minimum expression unit of these elements is shown in the following formula: parameter=(Object,Type i ,Value i ,t i ),(i∈Z + ), Among them, parameter is the smallest unit describing a ship object, Object is a specific ship object, Type represents the specific element type of a specific ship object; Value is the specific value of the specific element type of a specific ship object, and Z+ represents a positive integer; The ship object is expressed as: ShipObject = {Parameter} ={Parameter Attribute ,Parmeter Relation } ={Attribute elements,Relational elements,Time_Space} Among them, ShipObject represents the ship object; Parameter Atttribute Indicates the attribute elements of the ship object, Parameter Relation It represents the relationship element of the ship, and Time_Space represents the time-space element.
2. The ship behavior formalization expression method for knowledge reasoning according to claim 1 is characterized in that: The method in step 1 specifically includes: Using the idea of object-oriented programming in Java computer language, the ship entity is abstracted into an object. In the water traffic scene, each ship object has corresponding attributes, time and space, and relationships with other objects. The ship is abstracted into a conceptual model: ShipObject={Attribute,Relation,Space_Time} That is, the ship object includes the attribute element Attribute, the relationship element Relation and the time and space element Space_Time.
3. The ship behavior formalization expression method for knowledge reasoning according to claim 1 is characterized in that: The method in step 3 specifically includes: The ship behavior is expressed in characters and formulas using function mapping and set description methods, that is, ShipBehavior = {Attribute(t), Relation(t)}, where t∈[t i-1 ,t i ], i≥1; Attribute behavior refers to the change of ship attribute information; the ship attribute behavior refers to the change of the ship's position, heading, speed, signal light type and other attribute values; attribute behavior is expressed by the following formula: AttributeBehavior = {Attribute(t), ChangeType}, where: Attribute(t) represents the function of the ship attribute value changing over time, and ChangeType represents the type of attribute change; Relation behavior refers to the change of ship relationship elements over time, including spatial relationship, temporal relationship and semantic relationship, and also includes the generation, change and disappearance of relationship; relationship behavior often occurs with the occurrence of attribute behavior; a four-tuple is used to represent the change of relationship, RelationBehavior = {Relation i ,ChangeType,Relation j ,T}, where: Relation i and Relation j It is the relationship before and after the change; ChangeType is the type of change that occurs in the association relationship, which can be a change in the spatial topological relationship, distance relationship and orientation relationship, or a change in the time relationship and semantic relationship. T represents time.
4. The ship behavior formalization expression method for knowledge reasoning according to claim 3 is characterized in that: The method in step 3 specifically includes: Ship behavior is a dynamic change in space. The expression of ship behavior is: ShipBehavior={Behavior Attribute ,Behavior Relation } =f(Parameter),(∈N + ) Among them, Behavior Attribute Ship's attribute behavior,Behavior Relation The relational behavior of ships, f(·) is a comparison of the values of the same element of the same object at different times, N+ represents a positive integer; The input parameters are: Parameter={(shipA,speed,v1,t i-1 ),(shipA,speed,v2,t i )} The ship behavior is expressed as: The specific semantics of ship behavior are shown in the following table: Among them, the attribute elements include velocity and course elements, which represent the speed and course of the ship respectively; the relationship elements include relative distance, relative bearing, and topology elements, which represent the relative distance, relative orientation, and topological relationship between two water traffic objects respectively. out = -1 means that when the ship is outside a certain water area, R in =1 means the ship is within a certain water area; Value ti -Value ti-1 The corresponding meaning is the numerical difference of the corresponding feature types at different times.
5. The ship behavior formalization expression method for knowledge reasoning according to claim 4 is characterized in that: The expression of the attribute behavior and relationship behavior of the ship in step 3 is: 1) Specific expression of attribute behavior: The specific formula of attribute behavior is expressed as: Behavior Attribute =f(Parameter Attribute ) Parameter Attribute ={(Object,Typej,Value j ,t j )},(j∈Z,j≥2), For ship A: Then the attribute behavior of ship A is: Behavior Attribute =f(Parameter Attribute ) ={f(parameter1),f(parameter2)} ={(υ2-υ1),(c2-c1)} ={"slow down","turn right"},t∈[t i-1 ,t i ] 2) Specific expressions of relational behavior: The specific formula of relational behavior is expressed as: Behaior Relation =f(Parameter Relation ) Parameter Relation ={(Object,Type k ,Value k ,t k )},(k∈Z + ,k≥2), For Ship A and Ship B: Then the relationship behavior between ships A and B is: Behavior Relation =f(Parameter Relation ) ={f(parameter1),f(parameter2)} ={(d2-d1),(c2-c1)} ={"approach","move toward the bow"},t∈[t i-1 ,t i ].
6. The ship behavior formalization expression method for knowledge reasoning according to claim 1 is characterized in that: The method in step 4 specifically includes: By programming in Java, ship objects are defined, encapsulated and called, and the attributes, relationships and time and space elements of the ship objects are input, the current behavior of the ship and the behavior that the ship should take can be automatically identified and output.
7. A ship behavior formal expression system for knowledge reasoning, using the ship behavior formal expression method for knowledge reasoning according to claim 1, characterized in that: The system includes: Data input interface, used to connect ship sensor data to the system; The data formalization processing module is used to analyze the basic characteristics of ship entities and their behaviors, abstractly express ships into ship objects to describe ships in detail, and model ship objects to form ship object conceptual models, that is, ship objects contain attribute elements, relationship elements, and time and space elements; use the resource description framework method and the set theory method to abstractly express the ship's attribute elements, relationship elements, and time and space elements; abstractly express the dynamic changes of ship attribute elements and relationship elements in time and space elements into ship behaviors, and classify ship behaviors into ship attribute behaviors and ship relationship behaviors according to the type of element changes, and use function mapping and set description methods to characterize and formulate ship behaviors; obtain ship behavior formalized knowledge data; A storage module for storing formally expressed ship behavior data; The knowledge reasoning module is used to apply the knowledge formally expressed in the ship, use Java language for programming, define, encapsulate and call the ship object, input the attributes, relationships and time and space elements of the ship object, and automatically identify and infer the current behavior of the ship and the behavior that the ship should take.
Citation Information
Patent Citations
Navigation environment visualization representation method for ship visual navigation
CN105160942A
Unmanned ship scene understanding method based on navigation situation ontology modeling
CN111240325A
Ship collision avoidance rule scene knowledge formalized expression method
CN114443979A
Methods and systems for relating data structures and object-oriented elements for distributed computing
US20020016954A1
