Hierarchical knowledge expression method and device for electromagnetic scattering field

Abstract

The invention discloses a hierarchical knowledge expression method and device for the field of electromagnetic scattering, and belongs to the technical field of artificial intelligence. The method comprises the following steps: classifying acquired actual data according to electromagnetic scattering characteristics to obtain an electromagnetic scattering characteristic classification tree; carrying out abstract analysis on the electromagnetic scattering characteristic classification tree to obtain a domain knowledge framework containing model elements; and expanding the domain knowledge framework according to the target identification logic, and establishing a hierarchical knowledge expression model for dynamically representing the electromagnetic domain data. According to the method, hierarchical expression of knowledge in the electromagnetic scattering field can be realized, and the precision and effectiveness of dynamic target recognition are improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a hierarchical knowledge expression method and device for the field of electromagnetic scattering. Background Art

[0002] In the field of electromagnetic scattering, applications for target recognition are mostly static calls to independently stored electromagnetic scattering data, which usually ignore the intrinsic connections between electromagnetic scattering data and between electromagnetic scattering and the target structure itself, resulting in low target recognition accuracy in complex environments.

[0003] In addition, the relevant technologies lack the ability to dynamically adapt to environmental changes, making it difficult for researchers to conduct in-depth horizontal and vertical research in the field of electromagnetic scattering.

[0004] Based on this, there is an urgent need for a hierarchical knowledge expression method and device in the field of electromagnetic scattering to solve the above technical problems. Summary of the invention

[0005] The present invention provides a hierarchical knowledge expression method and device for the field of electromagnetic scattering, which can improve the accuracy and effectiveness of target recognition. The technical solution is as follows:

[0006] On the one hand, a hierarchical knowledge expression method for the field of electromagnetic scattering is provided, the method comprising:

[0007] Classifying the acquired actual data according to the electromagnetic scattering characteristics to obtain an electromagnetic scattering characteristic classification tree;

[0008] Abstract analysis is performed on the classification tree of electromagnetic scattering characteristics to obtain a domain knowledge framework containing model elements;

[0009] The domain knowledge framework is expanded according to the target recognition logic, and a hierarchical knowledge expression model for dynamically representing electromagnetic field data is established.

[0010] On the other hand, a hierarchical knowledge expression device for the field of electromagnetic scattering is provided, the device comprising:

[0011] A classification module is used to classify the acquired actual data according to the electromagnetic scattering characteristics to obtain an electromagnetic scattering characteristic classification tree;

[0012] An analysis module is used to perform abstract analysis on the classification tree of electromagnetic scattering characteristics to obtain a domain knowledge framework containing model elements;

[0013] The modeling module is used to expand the domain knowledge framework according to the target recognition logic and establish a hierarchical knowledge expression model for dynamically representing electromagnetic field data.

[0014] On the other hand, a computer device is provided, which includes a memory and a processor, the memory is used to store computer programs, and the processor is used to execute the computer programs stored in the memory to implement the steps of the above-mentioned hierarchical knowledge expression method for the field of electromagnetic scattering.

[0015] On the other hand, a computer-readable storage medium is provided, wherein a computer program is stored in the storage medium, and when the computer program is executed by a processor, the steps of the above-mentioned hierarchical knowledge expression method for the field of electromagnetic scattering are implemented.

[0016] On the other hand, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the steps of the above-mentioned hierarchical knowledge expression method for the electromagnetic scattering field.

[0017] The technical solution provided by the present invention can at least bring the following beneficial effects: first, the ontology framework structure is determined according to the characteristics and applications of electromagnetic scattering field data, and then, based on the ontology framework structure, an electromagnetic scattering field ontology model including a physical primitive layer, a data dynamic layer and an application requirement layer is established by hierarchically representing the electromagnetic scattering field knowledge. This method provides a hierarchical knowledge expression for the electromagnetic scattering field in view of the low accuracy of target unrecognition and the lack of dynamic adaptability to changes, thereby improving the accuracy and effectiveness of target recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 It is a flow chart of a hierarchical knowledge expression method for the electromagnetic scattering field provided by an embodiment of the present invention;

[0020] Figure 2 is a schematic diagram of an electromagnetic scattering characteristic classification tree provided by an embodiment of the present invention;

[0021] Figure 3 It is a schematic diagram of constructing a knowledge framework in the field of electromagnetic scattering provided by an embodiment of the present invention;

[0022] Figure 4 is a schematic diagram of the structure of a hierarchical knowledge expression model provided by an embodiment of the present invention;

[0023] Figure 5It is a hierarchical knowledge expression structure diagram for the electromagnetic scattering field provided by an embodiment of the present invention;

[0024] Figure 6 It is a hardware architecture diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0026] As mentioned above, most applications for target recognition are static calls to independently stored electromagnetic scattering data, which usually ignore the intrinsic connections between electromagnetic scattering data and between electromagnetic scattering and the target structure itself, resulting in low target recognition accuracy in complex environments.

[0027] Based on this, the concept of the present invention is to provide a hierarchical knowledge expression method for the field of electromagnetic scattering based on prior knowledge in the field of electromagnetic scattering to address the low accuracy of target unrecognition and the lack of dynamic adaptability to changes.

[0028] The specific implementation of the above concept is described below.

[0029] Please refer to Figure 1 , an embodiment of the present invention provides a hierarchical knowledge expression method for the field of electromagnetic scattering, the method comprising:

[0030] Step 100, classifying the acquired actual data according to the electromagnetic scattering characteristics to obtain an electromagnetic scattering characteristic classification tree;

[0031] Step 102, performing abstract analysis on the electromagnetic scattering characteristic classification tree to obtain a domain knowledge framework including model elements;

[0032] Step 104 , expanding the domain knowledge framework according to the target recognition logic, and establishing a hierarchical knowledge expression model for dynamically representing electromagnetic field data.

[0033] In the embodiment of the present invention, the ontology framework structure is first determined according to the characteristics and applications of electromagnetic scattering field data, and then the electromagnetic scattering field ontology model including the physical primitive layer, the data dynamic layer and the application requirement layer is established by hierarchically representing the electromagnetic scattering field knowledge on the basis of the ontology framework structure. This method provides a hierarchical knowledge expression for the electromagnetic scattering field in view of the low accuracy of target unrecognition and the lack of dynamic adaptability to changes, thereby improving the accuracy and effectiveness of target recognition.

[0034] Described below Figure 1 How the various steps are performed.

[0035] First, with respect to step 100, the acquired actual data is classified according to the electromagnetic scattering characteristics to obtain an electromagnetic scattering characteristic classification tree.

[0036] Since hierarchical knowledge expresses dynamic targets and the relationships between them, it is first necessary to obtain the actual electromagnetic scattering data of these targets. The data can come from different data sources, such as electromagnetic scattering data that records the interaction information between targets and electromagnetic waves; sensor data such as one-dimensional range images and SAR images.

[0037] Furthermore, according to the relevant characteristics of electromagnetic scattering, Figure 2 The electromagnetic scattering characteristics classification tree shown can facilitate the subsequent construction of a hierarchical knowledge expression model by analyzing the association relationship of the data in the classification tree.

[0038] Then, with respect to step 102, an abstract analysis is performed on the electromagnetic scattering characteristic classification tree to obtain a domain knowledge framework including model elements.

[0039] In an embodiment of the present invention, the process of determining the model elements includes the following steps: summarizing the electromagnetic scattering characteristic classification tree to define data problems that affect the accuracy of dynamic target recognition; analyzing and studying the data problems to establish an element set for characterizing the characteristics of electromagnetic scattering data; and performing feature abstraction processing on the element set to obtain model elements belonging to different levels.

[0040] like Figure 3 As shown, firstly, target recognition related problems are defined according to the electromagnetic scattering characteristic classification tree, such as what data are needed for target recognition in the field of electromagnetic scattering, what characteristics the data have, and what correlations there are between the data.

[0041] Furthermore, these problems are analyzed and studied, and a set of elements for characterizing the characteristics of electromagnetic scattering data is established. The set includes a data set, a requirement set and a model set. The data set includes the electromagnetic scattering data of all dynamic targets, such as SAR data, RCS data, etc.; the requirement set includes all recognition types, such as single target recognition, multi-target recognition or recognition feature similarities and differences analysis, etc.; the model set includes all interpretation models used to identify dynamic targets, such as data processing models, intelligent perception models, etc.

[0042] Furthermore, after obtaining the element set, its features are abstracted according to the prior knowledge in the field of electromagnetic scattering, and the model elements belonging to different levels that the knowledge ontology in the field of electromagnetic scattering should contain are obtained, including targets, electromagnetic scattering data, data associations, time and space, attributes, states, processes, application requirements, related resources, etc.

[0043] Specifically, the process of feature abstraction is a systematic method to transform specific elements into higher-level ontological concepts. This method first needs to identify and collect identification information related to dynamic targets in the element set, such as sensor data, electromagnetic scattering data, and environmental data; then extract specific features from the collected data, including geometric features: such as shape, size, edge, etc.; spectral features: such as color, reflectivity, etc.; dynamic features: such as speed, acceleration, movement trajectory, etc.

[0044] After identifying specific features, we start to abstract these features into ontology concepts. The ontology concept includes four elements, namely, target, attribute, state, and process. Target refers to a specific object or phenomenon, such as a vehicle, building, etc.; attribute refers to the properties that describe the characteristics of the target, such as size, color, material, etc., and maps specific features (such as length, color value) to attribute concepts. For example, length and width can be mapped to "size" attributes, and color values ​​can be mapped to "color" attributes; state refers to the current state of the target, which may be stationary, moving, damaged, etc. Dynamic features (such as speed, direction of movement) are used to define the state of the target. For example, if the speed of an object is zero, its state is "stationary"; process refers to the process that describes how the target changes or how it interacts with the environment, and feature changes (such as speed changes, shape changes) are converted into process concepts. For example, the change of a target from a "stationary" state to a "moving" state can be described as a "moving process".

[0045] Establish logical associations between the ontology concepts defined above, the relationship between goals and attributes, and the process relationship between states, and combine them with actual application needs to form a systematic knowledge framework, that is, Figure 3 The framework shown on the right consists of model elements at different levels.

[0046] With respect to step 104, the domain knowledge framework is expanded according to the target recognition logic, and a hierarchical knowledge expression model for dynamically representing electromagnetic domain data is established.

[0047] After obtaining the framework composed of model elements, we can use the prior knowledge in the field of electromagnetic scattering to expand and improve the above framework, and divide the elements in the framework according to the target recognition logic to obtain the following: Figure 4 The physical primitive layer model, data dynamic layer model and application requirement layer model shown realize the dynamic characterization of electromagnetic field data, thereby improving the accuracy and effectiveness of target recognition.

[0048] Specifically, the physical primitive layer model includes dynamic targets and the relationship between targets. The physical primitive layer model is used to provide the data dynamic layer model and the application requirement layer model with the relationship between the dynamic targets in the world.

[0049] The data dynamic layer model includes the electromagnetic scattering data of dynamic targets in a certain state and the correlation between the data. The data dynamic layer model is used to characterize the dynamic elements of the electromagnetic field knowledge of the physical primitive layer model.

[0050] The application requirement layer model includes the identification tasks, their attribution and the required related resources. The application requirement layer model is used to complete the corresponding identification tasks based on the information provided by the physical primitive layer model and the data dynamic layer model.

[0051] Please refer to Figure 5 The embodiment of the present invention provides a hierarchical knowledge expression device for the field of electromagnetic scattering, the device comprising:

[0052] A classification module 500 is used to classify the acquired actual data according to the electromagnetic scattering characteristics to obtain an electromagnetic scattering characteristic classification tree;

[0053] An analysis module 502 is used to perform an abstract analysis on the electromagnetic scattering characteristic classification tree to obtain a domain knowledge framework containing model elements;

[0054] The modeling module 504 is used to expand the domain knowledge framework according to the target recognition logic and establish a hierarchical knowledge expression model for dynamically representing electromagnetic field data.

[0055] In the embodiment of the present invention, when the analysis module 502 performs an abstract analysis on the electromagnetic scattering characteristic classification tree to obtain a domain knowledge framework containing model elements, it is specifically used to perform the following operations: summarize the electromagnetic scattering characteristic classification tree to define data problems that affect the accuracy of dynamic target recognition; analyze and study the data problems to establish an element set for characterizing the characteristics of electromagnetic scattering data; and perform feature abstraction processing on the element set to obtain model elements belonging to different levels.

[0056] In an embodiment of the present invention, the element set includes a data set, a requirement set and a model set, wherein: the data set includes electromagnetic scattering data of all dynamic targets; the requirement set includes all identification types; and the model set includes all interpretation models for identifying dynamic targets.

[0057] In an embodiment of the present invention, feature abstraction processing is performed on an element set to obtain model elements belonging to different levels, including: identifying the element set and collecting identification information related to a dynamic target; extracting features from the identification information to obtain feature information of the dynamic target; abstractly transforming the feature information to obtain an ontology concept including four elements: target, attribute, state, and process; and establishing logical relationships between ontology concepts based on prior knowledge in the field of electromagnetic scattering to obtain model elements belonging to different levels.

[0058] In the embodiment of the present invention, the feature information includes geometric features, spectral features and dynamic features.

[0059] In an embodiment of the present invention, the hierarchical knowledge expression model constructed by the modeling module 504 includes a physical primitive layer model, a data dynamic layer model and an application requirement layer model, wherein: the physical primitive layer model includes dynamic targets and the relationship between targets, and the physical primitive layer model is used to provide the data dynamic layer model and the application requirement layer model with the connection between dynamic targets in the world; the data dynamic layer model includes electromagnetic scattering data of dynamic targets in a certain state and the correlation between data, and the data dynamic layer model is used to characterize the dynamic elements of electromagnetic field knowledge of the physical primitive layer model; the application requirement layer model includes identification tasks and the attribution of tasks and the required related resources, and the application requirement layer model is used to complete the corresponding identification tasks according to the information provided by the physical primitive layer model and the data dynamic layer model.

[0060] It should be noted that the hierarchical knowledge expression device for the electromagnetic scattering field provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the hierarchical knowledge expression device for the electromagnetic scattering field provided in the above embodiment and the hierarchical knowledge expression method embodiment for the electromagnetic scattering field belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0061] The embodiment of the present application also provides a computer device, please refer to Figure 6The computer device includes a processor and a memory, in which at least one instruction, at least one program, a code set or an instruction set is stored, and the at least one instruction, at least one program, a code set or an instruction set is loaded and executed by the processor to implement the hierarchical knowledge expression method for the electromagnetic scattering field provided by the above-mentioned method embodiments.

[0062] An embodiment of the present application also provides a computer-readable storage medium, on which is stored at least one instruction, at least one program, code set or instruction set, and the at least one instruction, at least one program, code set or instruction set is loaded and executed by a processor to implement the hierarchical knowledge expression method for the electromagnetic scattering field provided by the above-mentioned method embodiments.

[0063] An embodiment of the present application also provides a computer program product, which includes a computer program. A processor of a computer device reads the computer program from a computer-readable storage medium, and the processor executes the computer program, so that the computer device executes the hierarchical knowledge expression method for the electromagnetic scattering field described in any of the above embodiments.

[0064] For the convenience of description, the above system or device is described by dividing it into various modules or units according to its functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0065] It can be known from the description of the above implementation methods that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be essentially or partly contributed to the prior art in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present application or certain parts of the embodiments.

[0066] Finally, it should be noted that, in this article, relational terms such as first, second, third and fourth are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0067] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A hierarchical knowledge expression method for the field of electromagnetic scattering, characterized in that: The method comprises: Classifying the acquired actual data according to the electromagnetic scattering characteristics to obtain an electromagnetic scattering characteristic classification tree; Abstract analysis is performed on the classification tree of electromagnetic scattering characteristics to obtain a domain knowledge framework containing model elements; The domain knowledge framework is expanded according to the target recognition logic, and a hierarchical knowledge expression model for dynamically representing electromagnetic field data is established.

2. The method according to claim 1, characterized in that The abstract analysis of the electromagnetic scattering characteristics classification tree is performed to obtain a domain knowledge framework containing model elements, including: Summarizing the electromagnetic scattering characteristic classification tree to define data problems that affect the accuracy of dynamic target recognition; Conduct analytical research on the data problem and establish a set of elements for characterizing the characteristics of electromagnetic scattering data; The element set is subjected to feature abstraction processing to obtain a domain knowledge framework including model elements belonging to different levels.

3. The method according to claim 2, characterized in that The element set includes a data set, a requirement set and a model set, wherein: The data set includes electromagnetic scattering data of all dynamic targets; The requirement set includes all identification categories; The model set includes all interpretation models used to identify dynamic targets.

4. The method according to claim 2, characterized in that: The feature abstraction processing is performed on the element set to obtain model elements belonging to different levels, including: Identify the element set and collect identification information related to the dynamic target; Extract features from the recognition information to obtain feature information of the dynamic target; Abstractly transform the feature information to obtain the ontology concept including the four elements of target, attribute, state and process; Based on the prior knowledge in the field of electromagnetic scattering, the logical relationship between ontology concepts is established to obtain model elements belonging to different levels.

5. The method according to claim 4, characterized in that The feature information includes geometric features, spectral features and dynamic features.

6. The method according to claim 2, characterized in that The hierarchical knowledge expression model includes a physical primitive layer model, a data dynamic layer model and an application requirement layer model, wherein: The physical primitive layer model includes dynamic targets and the relationship between targets. The physical primitive layer model is used to provide the dynamic targets existing in the world and the relationship between targets for the data dynamic layer model and the application requirement layer model; The data dynamic layer model includes electromagnetic scattering data of a dynamic target in a certain state and the correlation between the data, and the data dynamic layer model is used to describe the dynamic elements of electromagnetic field knowledge of the physical primitive layer model; The application requirement layer model includes identification tasks, their attribution and required related resources. The application requirement layer model is used to complete corresponding identification tasks according to the information provided by the physical primitive layer model and the data dynamic layer model.

7. A hierarchical knowledge expression device for the field of electromagnetic scattering, characterized in that: The device comprises: A classification module is used to classify the acquired actual data according to the electromagnetic scattering characteristics to obtain an electromagnetic scattering characteristic classification tree; An analysis module is used to perform abstract analysis on the classification tree of electromagnetic scattering characteristics to obtain a domain knowledge framework containing model elements; The modeling module is used to expand the domain knowledge framework according to the target recognition logic and establish a hierarchical knowledge expression model for dynamically representing electromagnetic field data.

8. A computer device, characterized in that: The computer device includes a memory and a processor, the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory to implement the steps of any one of the methods described in claims 1-6.

9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described in any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The method comprises a computer program, wherein when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images