High-confidence unmanned aerial vehicle game decision intelligent sensing system

Abstract

The invention discloses a high-confidence unmanned aerial vehicle game decision intelligent sensing system. The system comprises a user dialogue and input module, a multi-task integrated intelligent agent module, an unmanned aerial vehicle radiation source identification knowledge graph module, an unmanned aerial vehicle radiation source waveform feature extraction module and an identification result game decision research and judgment module. Receiving an unmanned aerial vehicle radiation source identification problem and unmanned aerial vehicle radiation source waveform data through a user dialogue and input module; the multi-task integrated intelligent agent module performs comprehensive intelligent analysis based on a large language model technology, disassembles tasks, coordinates execution of sub-tasks, and calls each sub-module to complete automatic intelligent analysis; the unmanned aerial vehicle radiation source identification knowledge graph module constructs a dynamic knowledge base and realizes structured representation and rapid retrieval; an unmanned aerial vehicle radiation source waveform feature extraction module performs feature analysis on the waveform signal, generates a feature description text and converts the feature description text into an embedded vector; and the recognition result game decision research and judgment module evaluates radiation source characteristics and threat levels, outputs information and threat situations, and is used for research and judgment analysis of game decision, so that the game decision effect is improved. The method has the advantages that the recognition accuracy and generalization ability are improved, the method adapts to the dynamic electromagnetic environment, the self-learning and optimization ability is achieved, the electronic countermeasure requirement is effectively supported, the command decision information support ability is enhanced, and the game decision effect is improved.

Description

Technical Field

[0001] The present invention belongs to the field of multi-task intelligent identification game decision-making of unmanned aerial vehicle radiation sources, and in particular relates to a high-confidence unmanned aerial vehicle game decision-making intelligent perception system. Background Art

[0002] In modern electronic environments, mastering the advantage of electromagnetic space is one of the key factors that determine environmental game decisions. With the continuous advancement of technology, the electromagnetic environment has become increasingly complex, especially the emergence of highly dynamic and variable electromagnetic interference and a large number of heterogeneous radiation sources, which has made traditional UAV radiation source identification methods face severe challenges. Traditional methods usually rely on pulse descriptors (such as frequency, pulse width, arrival time, etc.) for target identification, but in complex electromagnetic environments, these single-dimensional data can no longer meet the needs of rapid and accurate identification of radiation sources. First, these methods are difficult to accurately identify signals in high-density electromagnetic environments. Due to the static characteristics of parameters, they cannot effectively adapt to the dynamic changes of the environment. Secondly, when faced with multi-source signal interference, traditional methods often perform poorly due to their lack of ability to process complex data associations. Finally, these technologies cannot achieve rapid adaptation and learning of unknown or emerging signal types, which limits their application effects in fast-paced electronic countermeasure scenarios.

[0003] Knowledge graphs can integrate and understand a large amount of scattered, unstructured electromagnetic data by constructing a rich semantic network of entities, attributes, relationships, and events. This technology can provide a structured and dynamically updated knowledge base by identifying and linking information scattered across multiple data sources, enabling electronic countermeasure game decision support systems to conduct more in-depth analysis and understanding of complex electromagnetic scenarios. Through knowledge graphs, the system can associate information based on known radiation source knowledge, and the embedding of auxiliary knowledge greatly improves recognition accuracy, especially when dealing with unknown signals and dynamically changing electromagnetic environments.

[0004] Intelligent agent technology based on large language models has introduced an unprecedented level of intelligence to the identification of UAV radiation sources. In the UAV radiation source identification system, the intelligent agent can parse the operator's instructions, automatically extract task-related information and perform complex analysis tasks, realizing multi-task integrated intelligent solution. The large language model has good generalization performance. Combined with the domain knowledge of the UAV radiation source knowledge graph, it can further enhance its reasoning ability, adapt to new electronic environment conditions through the continuous updating of the knowledge graph, and improve the overall flexibility of game decision-making.

[0005] Through this technical integration, the present invention aims to overcome the limitations of traditional UAV radiation source identification methods in complex electromagnetic environments, provide a comprehensive, adaptive and highly intelligent solution, effectively support the electronic countermeasure needs in complex electromagnetic environments, further enhance the information support capabilities of command decision-making, and achieve improved game decision-making effects. Summary of the invention

[0006] The purpose of the present invention is to provide a high-confidence drone game decision-making intelligent perception system to address the deficiencies of the prior art.

[0007] The object of the present invention is achieved through the following technical solutions: a high-confidence UAV game decision intelligent perception system, the system comprising: a user dialogue and input module, a multi-task integrated intelligent agent module, a UAV radiation source identification knowledge graph module, a UAV radiation source waveform feature extraction module and an identification result game decision analysis module;

[0008] The user dialogue and input module is used to receive the problem of drone radiation source identification and drone radiation source waveform data input by the user, convert the problem of drone radiation source identification into a problem query vector, and package the drone radiation source waveform data into a waveform data file that meets the system requirements;

[0009] The multi-task integrated intelligent agent module performs comprehensive intelligent analysis on the problem of drone radiation source identification based on the large language model technology, decomposes and analyzes multiple tasks, manages and coordinates the execution of each subtask, calls the drone radiation source identification knowledge graph module and the drone waveform feature extraction module to perform subtask execution processing, integrates the results of each subtask, generates prompt words suitable for input into the large language model, and inputs the output of the large language model into the recognition result game decision-making and judgment module to generate a detailed report or real-time feedback;

[0010] The UAV radiation source identification knowledge graph module is used to build and maintain a dynamic knowledge base of UAV radiation sources, including data preprocessing and entity annotation, knowledge extraction and relationship inference, storage and call of graph knowledge; through these functions, the module can realize structured representation and rapid retrieval of UAV radiation source knowledge data;

[0011] The UAV radiation source waveform feature extraction module is used to perform accurate and comprehensive feature analysis on the received UAV radiation source waveform data, including a comprehensive UAV waveform feature analysis tool library, which performs diversified feature analysis on the received UAV waveform, which is conducive to more accurate UAV radiation source identification and judgment;

[0012] The identification result game decision analysis module is used to evaluate the characteristics and threat level of the drone radiation source, comprehensively apply the drone waveform characteristics and radiation source knowledge graph information, and output the drone radiation source information and game decision threat situation.

[0013] Furthermore, the user dialogue and input module is used to receive the problem of drone radiation source identification and drone radiation source waveform data input by the user, and convert the problem of drone radiation source identification into a question query vector, and package the drone radiation source waveform data into a waveform data file that meets the system requirements, specifically:

[0014] The user dialogue and input module is used to receive the problem of drone radiation source identification and drone radiation source waveform data input by the user, and convert the problem of drone radiation source identification input by the user into a question query vector through a conversion operation using a pre-trained language embedding model; and call the Python interpreter to package the drone radiation source waveform data into a waveform data file in the .pkl format that meets the system requirements.

[0015] Furthermore, the conversion operation of the pre-trained language embedding model specifically includes the following sub-steps:

[0016] a.1) First, the input text Text is tokenized by the tokenization tool Tokenizator, and the text Text is converted into a basic symbol unit token token: token = Tokenizator (Text), where Tokenizator (·) is a symbolization processing operation;

[0017] a.2) Then, the basic unit token is embedded through the embedding layer Embedding and mapped to an embedding vector e of a fixed size: e = Embedding(token), where Embedding(·) is the embedding operation;

[0018] a.3) In order to maintain the sequence order of the input, it is necessary to add the position code PE to the embedding vector e to obtain the embedding vector E: E = e + PE;

[0019] The calculation formula of position encoding PE is:

[0020] Among them, pos is the position index of the symbol basic unit in the input sequence, i is the dimension index of the embedding vector e, and d model Dimensionality of the pre-trained language embedding model.

[0021] Furthermore, the multi-task integrated intelligent agent module performs a comprehensive intelligent analysis of the problem of drone radiation source identification based on the large language model technology, decomposes and analyzes multiple tasks, manages and coordinates the execution of each subtask, calls the drone radiation source identification knowledge graph module and the drone waveform feature extraction module to perform subtask execution processing, integrates the results of each subtask, generates prompt words suitable for input into the large language model, and inputs the output of the large language model into the recognition result game decision-making and judgment module to generate a detailed report or real-time feedback, which is specifically implemented through the following sub-steps:

[0022] b.1) Task decomposition and scheduling: The intelligent agent decomposes the problem of drone radiation source identification into multiple subtasks based on the complexity of the input content and user needs. The subtasks are knowledge graph construction, waveform feature extraction, or threat level assessment. Based on the thinking chain, these subtasks are prioritized and the corresponding modules are assigned for processing.

[0023] b.2) Subtask execution and coordination: Call the UAV radiation source identification knowledge graph module, the UAV waveform feature extraction module and the identification result game decision-making module according to the task requirements; the UAV radiation source identification knowledge graph module is used to construct the knowledge graph and perform data association and reasoning, the UAV waveform feature extraction module is used to extract waveform features from the UAV radiation source waveform data, and the identification result game decision-making module is used for information induction and threat level assessment of the UAV radiation source waveform data; the intelligent agent checks the execution results of each subtask to ensure that all subtasks are completed according to actual needs and that the output content meets actual needs;

[0024] b.3) Result integration and output: The intelligent agent integrates the running results of each subtask, generates prompt words suitable for input into the large language model, analyzes the results according to the output of the large language model, and inputs them into the recognition result game decision-making module to generate detailed reports or real-time feedback, providing intuitive operation and decision support;

[0025] b.4) Continuous learning and updating: The multi-task identification system of drone radiation sources based on intelligent agent knowledge graph uses user feedback and operation results to continuously optimize the performance of the large language model, update the knowledge graph and adjust the processing strategy to adapt to environmental changes and new threat types.

[0026] Furthermore, the UAV radiation source identification knowledge graph module is used to build and maintain a dynamic knowledge base of UAV radiation sources, including data preprocessing and entity annotation, knowledge extraction and relationship inference, storage and call of graph knowledge; through these functions, the module can realize the structured representation and rapid retrieval of UAV radiation source knowledge data, specifically:

[0027] The knowledge graph module for drone radiation source identification calls the multi-task integrated intelligent agent module to perform named entity recognition on the problem of drone radiation source identification, and obtains the entity name and attribute name related to the drone radiation source in the problem of drone radiation source identification; then, based on the multi-task integrated intelligent agent module, knowledge extraction and relationship inference are performed on the identified entity name and attribute name, and each entity and corresponding attribute are matched, and stored in the format of triples, with the storage type of [entity A, attribute name of entity A, attribute value of entity A]; the relationship between different entities is also matched and stored in the format of triples, with the storage type of [entity A, relationship between entity A and entity B, entity B]; each triple is then converted into a knowledge embedding vector through a pre-trained language embedding model and stored in the dynamic knowledge base of drone radiation sources.

[0028] Furthermore, the UAV radiation source waveform feature extraction module is used to perform accurate and comprehensive feature analysis on the received UAV radiation source waveform data, including a comprehensive UAV waveform feature analysis tool library, which performs diversified feature analysis on the received UAV waveform, which is conducive to more accurate UAV radiation source identification and judgment, specifically:

[0029] The UAV waveform feature extraction module reads a waveform data file packaged in a .pkl format that meets system requirements; the UAV waveform feature analysis tool library in the UAV waveform feature extraction module first calls the pulse description word feature analysis tool to extract the frequency, power, pulse width, modulation mode, arrival angle, arrival time and other radiation source characteristic attributes of each waveform in the waveform data file, and calls the multi-task integrated intelligent agent module to perform entity matching and behavior analysis of the UAV radiation source, and constructs the feature information of each waveform in the form of a triple [waveform number k, attribute name of waveform number k, attribute value of waveform number k], and combines the triples under the same waveform number into a feature description text, which is then converted into a feature query vector through a pre-trained language embedding model.

[0030] Furthermore, the identification result game decision analysis module is used to evaluate the characteristics and threat level of the drone radiation source, comprehensively apply the drone waveform characteristics and radiation source knowledge graph information, and output the drone radiation source information and game decision threat situation, specifically:

[0031] The recognition result game decision-making module first performs a similarity search on the question query vector in the dynamic knowledge base of the drone radiation source to find the K knowledge embedding vectors with the largest Gaussian weighted cosine similarity; then performs a similarity search on any feature query vector in the drone waveform feature extraction module in the dynamic knowledge base of the drone radiation source to find the K knowledge embedding vectors with the largest Gaussian weighted cosine similarity; then, the question query vector and its corresponding K knowledge embedding vectors and the feature query vector and its corresponding K knowledge embedding vectors construct a context, and the context constructed by 2K+2 embedding vectors is used as the prompt word of the large language model, which is input into the multi-task integrated intelligent agent module, and finally the information summary and threat level assessment of the drone radiation source waveform data are obtained; wherein, the construction method of the prompt word Prompt of the large language model is as follows:

[0032] Prompt=E question ||E feature ||E knowledge ;

[0033] Among them, E question is the question query vector, E feature is the feature query vector, E knowledge is the knowledge embedding vector.

[0034] Furthermore, the similarity search process is specifically as follows:

[0035] Given any query vector E query For each knowledge embedding vector E in the dynamic knowledge base of the drone radiation source K , calculate the corresponding Gaussian weighted cosine similarity WGC (E query ,E K ,γ):

[0036]

[0037] Among them, γ is the bandwidth parameter of the Gaussian function, which controls the influence of distance; ||E query -E K || 2 Represents the Euclidean distance between two vectors; E query ·E K is the vector dot product; ||E query || and ||E K || are the moduli of the two vectors respectively.

[0038] The beneficial effects of the present invention are:

[0039] 1) By integrating large language model intelligent agents and knowledge graph technology, this system can accurately process and analyze complex drone radiation source data and improve the accuracy and generalization ability of radiation source identification. The intelligent agent uses advanced large language model technology to achieve in-depth understanding and accurate answers to drone radiation source questions, while automatically adjusting the identification strategy to adapt to the dynamic changes of the electromagnetic environment. In addition, the application of knowledge graphs enables the system to integrate and utilize prior knowledge of drone radiation sources to build a structured and continuously updated drone radiation source knowledge base.

[0040] 2) This system also has the ability of self-learning and optimization. As time goes by and data accumulates, the system's performance and recognition accuracy will continue to improve; this learning mechanism is particularly suitable for processing unknown signals and highly dynamic electromagnetic interference, ensuring the application effect in fast-paced electronic confrontation scenarios; through this adaptive learning and optimization, this system can effectively support the needs of electronic confrontation in complex electromagnetic environments, provide strong information support for command and decision-making, and achieve improved game decision-making effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 This is a structural diagram of a high-confidence UAV game decision-making intelligent perception system;

[0042] In the figure, 1-user dialogue and input module; 2-multi-task integrated intelligent agent module; 3-UAV radiation source identification knowledge graph module; 4-UAV radiation source waveform feature extraction module; 5-identification result game decision-making module. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical scheme and advantages of the present invention more clear, the present invention is further described in detail 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, rather than all embodiments. Based on the embodiments of 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.

[0044] Example 1

[0045] like Figure 1 As shown, the present invention provides a high-confidence UAV game decision intelligent perception system, the system comprising: a user dialogue and input module 1, a multi-task integrated intelligent agent module 2, a UAV radiation source identification knowledge graph module 3, a UAV radiation source waveform feature extraction module 4 and an identification result game decision analysis module 5.

[0046] The user dialogue and input module 1 is used to receive the problem of drone radiation source identification and drone radiation source waveform data input by the user, and convert the problem of drone radiation source identification into a problem query vector, and package the drone radiation source waveform data into a waveform data file that meets the system requirements, specifically:

[0047] The user dialogue and input module is used to receive the problem of drone radiation source identification and drone radiation source waveform data input by the user, and use the pre-trained language embedding model (BERT, Bidirectional EncoderRepresentations from Transformers) to convert the problem of drone radiation source identification input by the user into a question query vector through a conversion operation; and call the Python interpreter to package the drone radiation source waveform data into a waveform data file in the .pkl format that meets the system requirements.

[0048] The conversion operation of the pre-trained language embedding model specifically includes the following sub-steps:

[0049] a.1) First, the input text Text is tokenized by the tokenization tool Tokenizator, and the text Text is converted into a basic symbol unit token token: token = Tokenizator (Text), where Tokenizator (·) is a symbolization processing operation;

[0050] a.2) Then, the basic unit token is embedded through the embedding layer Embedding and mapped to an embedding vector e of a fixed size: e = Embedding(token), where Embedding(·) is the embedding operation;

[0051] a.3) In order to maintain the sequence order of the input, it is necessary to add the position code PE to the embedding vector e to obtain the embedding vector E: E = e + PE;

[0052] The calculation formula of position encoding PE is:

[0053] Among them, pos is the position index of the symbol basic unit in the input sequence, i is the dimension index of the embedding vector e, and d model Dimensionality of the pre-trained language embedding model.

[0054] The multi-task integrated intelligent agent module 2 performs comprehensive intelligent analysis on the problem of drone radiation source identification based on the large language model technology, decomposes and analyzes multiple tasks, manages and coordinates the execution of each subtask, calls the drone radiation source identification knowledge graph module and the drone waveform feature extraction module to perform subtask execution processing, integrates the results of each subtask, generates prompt words suitable for input into the large language model, and inputs the output of the large language model into the recognition result game decision-making and judgment module to generate a detailed report or real-time feedback, which is specifically implemented through the following sub-steps:

[0055] b.1) Task decomposition and scheduling: The intelligent agent decomposes the problem of drone radiation source identification into multiple subtasks based on the complexity of the input content and user needs. The subtasks are knowledge graph construction, waveform feature extraction, or threat level assessment. Based on the thinking chain, these subtasks are prioritized and the corresponding modules are assigned for processing.

[0056] b.2) Subtask execution and coordination: Call the UAV radiation source identification knowledge graph module, the UAV waveform feature extraction module and the identification result game decision-making module according to the task requirements; the UAV radiation source identification knowledge graph module is used to construct the knowledge graph and perform data association and reasoning, the UAV waveform feature extraction module is used to extract waveform features from the UAV radiation source waveform data, and the identification result game decision-making module is used for information induction and threat level assessment of the UAV radiation source waveform data; the intelligent agent checks the execution results of each subtask to ensure that all subtasks are completed according to actual needs and that the output content meets actual needs;

[0057] b.3) Result integration and output: The intelligent agent integrates the running results of each subtask, generates prompt words suitable for input into the large language model, analyzes the results according to the output of the large language model, and inputs them into the recognition result game decision-making module to generate detailed reports or real-time feedback, providing intuitive operation and decision support;

[0058] b.4) Continuous learning and updating: The multi-task identification system of drone radiation sources based on intelligent agent knowledge graph uses user feedback and operation results to continuously optimize the performance of the large language model, update the knowledge graph and adjust the processing strategy to adapt to environmental changes and new threat types.

[0059] The UAV radiation source identification knowledge graph module 3 is used to build and maintain a dynamic knowledge base of UAV radiation sources, including data preprocessing and entity annotation, knowledge extraction and relationship inference, storage and call of graph knowledge; through these functions, the module can realize the structured representation and rapid retrieval of UAV radiation source knowledge data, specifically:

[0060] The knowledge graph module for drone radiation source identification calls the multi-task integrated intelligent agent module to perform named entity recognition on the problem of drone radiation source identification, and obtains the entity name and attribute name related to the drone radiation source in the problem of drone radiation source identification; then, based on the multi-task integrated intelligent agent module, knowledge extraction and relationship inference are performed on the identified entity name and attribute name, and each entity and corresponding attribute are matched, and stored in the format of triples, with the storage type of [entity A, attribute name of entity A, attribute value of entity A]; the relationship between different entities is also matched and stored in the format of triples, with the storage type of [entity A, relationship between entity A and entity B, entity B]; each triple is then converted into a knowledge embedding vector through a pre-trained language embedding model and stored in the dynamic knowledge base of drone radiation sources.

[0061] The UAV radiation source identification knowledge graph module 3 will also ask questions to the multi-task integrated intelligent agent module 2 to extract knowledge and infer relationships of the identified entity names and attribute names. The questioning method is as follows: "Please construct a knowledge graph triple between named entities and attributes in the sentence, in the format of: [entity A, relationship, entity B], [entity, attribute, attribute value]; [JYL-1 UAV, mobile 3D surveillance UAV, S band]", the multi-task integrated intelligent agent module 2 will output "[JYL-1 UAV, band, S band], [JYL-1 UAV, type, mobile 3D surveillance UAV]", thereby achieving the matching between entities and attributes, obtaining the relationship between entities and entities, and storing them in the format of triples; each triple is then converted into a knowledge embedding vector through the pre-trained language model BERT and stored in the same database, so as to construct an embedding vector knowledge base based on the knowledge graph.

[0062] The UAV radiation source waveform feature extraction module 4 is used to perform accurate and comprehensive feature analysis on the received UAV radiation source waveform data, including a comprehensive UAV waveform feature analysis tool library, which performs diversified feature analysis on the received UAV waveform, which is conducive to more accurate UAV radiation source identification and judgment, specifically:

[0063] The UAV waveform feature extraction module reads a waveform data file packaged in a .pkl format that meets system requirements; the UAV waveform feature analysis tool library in the UAV waveform feature extraction module first calls the pulse description word feature analysis tool to extract the frequency, power, pulse width, modulation mode, arrival angle, arrival time and other radiation source characteristic attributes of each waveform in the waveform data file, and calls the multi-task integrated intelligent agent module to perform entity matching and behavior analysis of the UAV radiation source, and constructs the feature information of each waveform in the form of a triple [waveform number k, attribute name of waveform number k, attribute value of waveform number k], and combines the triples under the same waveform number into a feature description text, which is then converted into a feature query vector through a pre-trained language embedding model.

[0064] For example, if a user uploads a waveform data file "wave.pkl", the multi-task integrated intelligent agent module 2 will call the UAV waveform feature analysis tool library to read the waveform data file, obtain the pulse description word features corresponding to the UAV radiation source waveform in the waveform data file, and organize these feature information together according to the same waveform serial number to form a feature description text of the input waveform, such as "[waveform 1, frequency, 3100MHz], [waveform 1, pulse width, 10μs], [waveform 1, modulation mode, LFM]", and then use the pre-trained language embedding model to convert the feature description text of the input waveform into an embedding vector to construct a feature query vector.

[0065] The identification result game decision analysis module 5 is used to evaluate the characteristics and threat level of the drone radiation source, comprehensively apply the drone waveform characteristics and radiation source knowledge graph information, and output the drone radiation source information and game decision threat situation, specifically:

[0066] The recognition result game decision-making module first performs a similarity search on the question query vector in the dynamic knowledge base of the drone radiation source to find the K knowledge embedding vectors with the largest Gaussian weighted cosine similarity; then performs a similarity search on any feature query vector in the drone waveform feature extraction module in the dynamic knowledge base of the drone radiation source to find the K knowledge embedding vectors with the largest Gaussian weighted cosine similarity; then, the question query vector and its corresponding K knowledge embedding vectors and the feature query vector and its corresponding K knowledge embedding vectors construct a context, and the context constructed by 2K+2 embedding vectors is used as the prompt word of the large language model, which is input into the multi-task integrated intelligent agent module, and finally the information summary and threat level assessment of the drone radiation source waveform data are obtained; wherein, the construction method of the prompt word Prompt of the large language model is as follows:

[0067] Prompt=E question ||E feature||E knowledge ;

[0068] Among them, E question is the question query vector, E feature is the feature query vector, E knowledge is the knowledge embedding vector.

[0069] The similarity search process is as follows:

[0070] Given any query vector E query For each knowledge embedding vector E in the dynamic knowledge base of the drone radiation source K , calculate the corresponding Gaussian weighted cosine similarity WGC (E query ,E K ,γ):

[0071]

[0072] Among them, γ is the bandwidth parameter of the Gaussian function, which controls the influence of distance; ||E query -E K || 2 Represents the Euclidean distance between two vectors; E query ·E K is the vector dot product; ||E query || and ||E K || are the moduli of the two vectors respectively.

[0073] Compared with the traditional method of calculating the similarity of query vectors based on cosine similarity, Gaussian weighted cosine similarity is calculated by Gaussian term exp(-γ||E query -E K || 2 ), the distance factor is introduced, which can more accurately reflect the similarity between vectors, thus ensuring that the system is more inclined to retrieve and query vector E query Knowledge embedding vector E that is similar in both direction and distance K , which helps the system retrieve more relevant data, thereby achieving high-confidence intelligent perception and game decision-making.

[0074] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A high-confidence UAV game decision-making intelligent perception system, characterized by: The system includes: a user dialogue and input module, a multi-task integrated intelligent agent module, a UAV radiation source identification knowledge graph module, a UAV radiation source waveform feature extraction module and an identification result game decision-making module; The user dialogue and input module is used to receive the problem of drone radiation source identification and drone radiation source waveform data input by the user, convert the problem of drone radiation source identification into a problem query vector, and package the drone radiation source waveform data into a waveform data file that meets the system requirements; The multi-task integrated intelligent agent module performs comprehensive intelligent analysis on the problem of drone radiation source identification based on the large language model technology, decomposes and analyzes multiple tasks, manages and coordinates the execution of each subtask, calls the drone radiation source identification knowledge graph module and the drone waveform feature extraction module to perform subtask execution processing, integrates the results of each subtask, generates prompt words suitable for input into the large language model, and inputs the output of the large language model into the recognition result game decision-making and judgment module to generate a detailed report or real-time feedback; The UAV radiation source identification knowledge graph module is used to build and maintain a dynamic knowledge base of UAV radiation sources, including data preprocessing and entity annotation, knowledge extraction and relationship inference, storage and call of graph knowledge; through these functions, the module can realize structured representation and rapid retrieval of UAV radiation source knowledge data; The UAV radiation source waveform feature extraction module is used to perform accurate and comprehensive feature analysis on the received UAV radiation source waveform data, including a comprehensive UAV waveform feature analysis tool library, which performs diversified feature analysis on the received UAV waveform, which is conducive to more accurate UAV radiation source identification and judgment; The identification result game decision analysis module is used to evaluate the characteristics and threat level of the drone radiation source, comprehensively apply the drone waveform characteristics and radiation source knowledge graph information, and output the drone radiation source information and game decision threat situation.

2. According to claim 1, a high-confidence UAV game decision-making intelligent perception system is characterized in that: The user dialogue and input module is used to receive the problem of drone radiation source identification and drone radiation source waveform data input by the user, and convert the problem of drone radiation source identification into a question query vector, and package the drone radiation source waveform data into a waveform data file that meets the system requirements, specifically: The user dialogue and input module is used to receive the problem of drone radiation source identification and drone radiation source waveform data input by the user, and convert the problem of drone radiation source identification input by the user into a question query vector through a conversion operation using a pre-trained language embedding model; And call the Python interpreter to package the drone radiation source waveform data into a .pkl format waveform data file that meets the system requirements.

3. The high-confidence UAV game decision-making intelligent perception system according to claim 2 is characterized in that: The conversion operation of the pre-trained language embedding model specifically includes the following sub-steps: a.1) First, the input text Text is tokenized by the tokenization tool Tokenizator, and the text Text is converted into a basic symbol unit token token: token = Tokenizator (Text), where Tokenizator (·) is a symbolization processing operation; a.2) Then, the basic unit token is embedded through the embedding layer Embedding and mapped to an embedding vector e of a fixed size: e = Embedding(token), where Embedding(·) is the embedding operation; a.3) In order to maintain the sequence order of the input, it is necessary to add the position code PE to the embedding vector e to obtain the embedding vector E: E = e + PE; The calculation formula of position encoding PE is: Among them, pos is the position index of the symbol basic unit in the input sequence, i is the dimension index of the embedding vector e, and d model Dimensionality of the pre-trained language embedding model.

4. The high-confidence UAV game decision-making intelligent perception system according to claim 3 is characterized in that: The multi-task integrated intelligent agent module performs comprehensive intelligent analysis on the problem of drone radiation source identification based on the large language model technology, decomposes and analyzes multiple tasks, manages and coordinates the execution of each subtask, calls the drone radiation source identification knowledge graph module and the drone waveform feature extraction module to execute the subtasks, integrates the results of each subtask, generates prompt words suitable for input into the large language model, and inputs the output of the large language model into the recognition result game decision-making module to generate a detailed report or real-time feedback, which is specifically implemented through the following sub-steps: b.1) Task decomposition and scheduling: The intelligent agent decomposes the problem of drone radiation source identification into multiple subtasks based on the complexity of the input content and user needs. The subtasks are knowledge graph construction, waveform feature extraction, or threat level assessment. Based on the thinking chain, these subtasks are prioritized and the corresponding modules are assigned for processing. b.2) Subtask execution and coordination: Call the UAV radiation source identification knowledge graph module, the UAV waveform feature extraction module and the identification result game decision-making and judgment module according to the task requirements; the UAV radiation source identification knowledge graph module is used to construct the knowledge graph and perform data association and reasoning, the UAV waveform feature extraction module is used to extract waveform features from the UAV radiation source waveform data, and the identification result game decision-making and judgment module is used for information induction and threat level assessment of the UAV radiation source waveform data; intelligent The agent verifies the execution results of each subtask to ensure that all subtasks are completed as required and that the output content meets actual requirements; b.3) Result integration and output: The intelligent agent integrates the running results of each subtask, generates prompt words suitable for input into the large language model, analyzes the results according to the output of the large language model, and inputs them into the recognition result game decision-making module to generate detailed reports or real-time feedback, providing intuitive operation and decision support; b.4) Continuous learning and updating: The multi-task identification system of drone radiation sources based on intelligent agent knowledge graph uses user feedback and operation results to continuously optimize the performance of the large language model, update the knowledge graph and adjust the processing strategy to adapt to environmental changes and new threat types.

5. The high-confidence UAV game decision-making intelligent perception system according to claim 4 is characterized in that: The UAV radiation source identification knowledge graph module is used to build and maintain a dynamic knowledge base of UAV radiation sources, including data preprocessing and entity annotation, knowledge extraction and relationship inference, storage and call of graph knowledge; through these functions, the module can realize the structured representation and rapid retrieval of UAV radiation source knowledge data, specifically: The knowledge graph module for drone radiation source identification calls the multi-task integrated intelligent agent module to perform named entity recognition on the problem of drone radiation source identification, and obtains the entity names and attribute names related to drone radiation sources in the problem of drone radiation source identification; Then, based on the multi-task integrated intelligent agent module, knowledge extraction and relationship inference are performed on the recognized entity names and attribute names, and each entity and corresponding attribute are matched and stored in the format of triples, with the storage type being [entity A, attribute name of entity A, attribute value of entity A]. The relationships between different entities are also matched and stored in the triple format, with the storage type being [entity A, the relationship between entity A and entity B, entity B]; Each triplet is then converted into a knowledge embedding vector through a pre-trained language embedding model and stored in the dynamic knowledge base of the drone radiation source.

6. The high-confidence UAV game decision-making intelligent perception system according to claim 5 is characterized in that: The UAV radiation source waveform feature extraction module is used to perform accurate and comprehensive feature analysis on the received UAV radiation source waveform data, including a comprehensive UAV waveform feature analysis tool library, which performs diversified feature analysis on the received UAV waveform, which is conducive to more accurate UAV radiation source identification and judgment, specifically: The UAV waveform feature extraction module reads a waveform data file packaged in a .pkl format that meets system requirements; the UAV waveform feature analysis tool library in the UAV waveform feature extraction module first calls the pulse description word feature analysis tool to extract the frequency, power, pulse width, modulation mode, arrival angle, arrival time and other radiation source characteristic attributes of each waveform in the waveform data file, and calls the multi-task integrated intelligent agent module to perform entity matching and behavior analysis of the UAV radiation source, and constructs the feature information of each waveform in the form of a triple [waveform number k, attribute name of waveform number k, attribute value of waveform number k], and combines the triples under the same waveform number into a feature description text, which is then converted into a feature query vector through a pre-trained language embedding model.

7. The high-confidence UAV game decision-making intelligent perception system according to claim 6 is characterized in that: The identification result game decision analysis module is used to evaluate the characteristics and threat level of the drone radiation source, comprehensively apply the drone waveform characteristics and radiation source knowledge graph information, and output the drone radiation source information and game decision threat situation, specifically: The recognition result game decision-making module first performs a similarity search on the problem query vector in the dynamic knowledge base of the drone radiation source to find the K knowledge embedding vectors with the largest Gaussian weighted cosine similarity; then performs a similarity search on any feature query vector in the drone waveform feature extraction module in the dynamic knowledge base of the drone radiation source to find the K knowledge embedding vectors with the largest Gaussian weighted cosine similarity; Then, the question query vector and its corresponding K knowledge embedding vectors and the feature query vector and its corresponding K knowledge embedding vectors are used to construct a context. The context constructed by 2K+2 embedding vectors is used as the prompt word of the large language model and input into the multi-task integrated intelligent agent module. Finally, the information summary and threat level assessment of the waveform data of the UAV radiation source are obtained. Among them, the construction method of the prompt word Prompt of the large language model is as follows: Prompt=And question ||And feature ||And knowledge ; Among them, E question is the question query vector, E feature is the feature query vector, E knowledge is the knowledge embedding vector.

8. The high-confidence UAV game decision-making intelligent perception system according to claim 7 is characterized in that: The similarity search process is as follows: Given any query vector E query For each knowledge embedding vector E in the dynamic knowledge base of the drone radiation source K , calculate the corresponding Gaussian weighted cosine similarity WGC (E query ,E K ,γ): Among them, γ is the bandwidth parameter of the Gaussian function, which controls the influence of distance; ||E query -E K || 2 Represents the Euclidean distance between two vectors; E query ·E K is the vector dot product; ||E query || and ||E K || are the moduli of the two vectors respectively.

Images