A Method for Extracting Multi-Parameter Ocean Information Based on Terminology Semantics

Abstract

This invention relates to the field of marine multi-parameter information extraction technology, specifically to a method for extracting marine multi-parameter information based on terminology semantics. It introduces advanced clustering and classification algorithms to perform deep learning and optimization of marine terms; utilizes terminology expressive power and Chinese phrase structure rules to optimize the K-nearest neighbor algorithm to identify marine entities and their attributes in the text; performs entity and attribute extraction and standardizes the extracted entities and attributes; designs a maximum correlation algorithm to assess the importance of different parameters in specific marine events or processes; and matches the extracted parameter information with marine structured data through multi-dimensional correlation analysis to achieve multi-dimensional information association. Based on the analysis results, it outputs the optimized extracted content. By combining the ecosystem characteristics and seasonal changes of the sea area, it selects the parameters with the greatest impact on water quality, generating intuitive reports and recommendations to provide decision-making basis for managers.

Description

Technical Field

[0001] This invention relates to the field of marine multi-parameter information extraction technology, and in particular to a method for marine multi-parameter information extraction based on terminology semantics. Background Technology

[0002] With the advancement of marine observation technology and the advent of the big data era, the amount of marine data collected has exploded. This data covers multiple dimensions, including physical, chemical, and biological data, and is of great significance for understanding marine ecosystems, predicting marine disasters, and optimizing the development of marine resources.

[0003] However, the complexity, heterogeneity, and specialized terminology of marine data pose significant challenges to the effective extraction and analysis of information.

[0004] Current multi-parameter information extraction methods often face shortcomings when dealing with complex scenarios such as marine data, including scarce and unbalanced data sources, insufficient algorithm generalization ability, and low accuracy in entity and attribute recognition. These shortcomings affect the extraction speed and accuracy of marine multi-parameter information, limiting their effectiveness in marine scientific research, environmental monitoring, and resource management. Summary of the Invention

[0005] The purpose of this invention is to provide a method for extracting marine multi-parameter information based on terminology semantics. This method solves the problems that multi-parameter information extraction methods often face when processing complex scenarios such as marine data, including scarce and unbalanced data sources, insufficient algorithm generalization ability, and low accuracy of entity and attribute recognition, which affect the extraction speed and accuracy of marine multi-parameter information.

[0006] To achieve the above objectives, this invention provides a method for extracting multi-parameter marine information based on terminology semantics, comprising the following steps:

[0007] Based on the existing semantic knowledge system of marine terminology, advanced clustering and classification algorithms are introduced to conduct deep learning and optimization of marine terminology;

[0008] By leveraging terminology expressiveness and Chinese phrase structure rules, the K-nearest neighbor algorithm is optimized to identify marine entities and their attributes in text.

[0009] By combining domain-specific dictionaries and contextual information, entities and attributes are extracted, and the extracted entities and attributes are standardized.

[0010] By combining scene semantic information, a maximum correlation algorithm is designed to evaluate the importance of different parameters in specific ocean events or processes;

[0011] By using multi-dimensional correlation analysis, the extracted parameter information is matched with ocean structured data to achieve multi-dimensional correlation of information.

[0012] Based on the analysis results, the optimized extracted content is output, including key parameters, trend prediction, and anomaly detection.

[0013] Specifically, in the section "Based on the existing semantic knowledge system of marine terminology, advanced clustering and classification algorithms are introduced to perform deep learning and optimization of marine terminology," the method includes the following steps:

[0014] Collect marine terminology and its related descriptions, integrate the data into a database, and perform data cleaning and preprocessing to remove duplicate, erroneous, or irrelevant information;

[0015] Based on the existing marine terminology semantic knowledge system, clustering and classification algorithms are used to initially apply the algorithms to preprocessed data, and the performance of the algorithms is evaluated through cross-validation.

[0016] Based on the preliminary algorithm results, a deep learning model was constructed to extract and classify deep features of marine terms, and the model was trained using preprocessed data.

[0017] By combining the output of deep learning models with the existing semantic knowledge system of marine terminology, the terminology database can be updated and improved, and new relationships between terms can be discovered.

[0018] Specifically, in the section "Optimizing the K-nearest neighbor algorithm to identify marine entities and their attributes in text by utilizing terminological expressiveness and Chinese phrase structure rules," the method includes the following steps:

[0019] We analyze the phrase structure in Chinese, extract common phrase structure rules from a large corpus, and form a rule base to serve as the grammatical basis for identifying marine entities and their attributes.

[0020] Combining terminology expressiveness and Chinese phrase structure rules, we designed feature selection and representation methods to convert text data into feature vectors that can be processed by the algorithm. At the same time, we adjusted the parameters of the K-nearest neighbor algorithm and introduced a weighting mechanism.

[0021] Using preprocessed text data and labeled marine entities and their attribute information, an optimized KNN model is trained. The model is then used to identify and extract marine entities and their attributes from new text data, forming structured information that provides a foundation for subsequent analysis and applications.

[0022] The recognition results are manually verified, and the algorithm and model are iteratively optimized based on the verification results.

[0023] Specifically, the step of "extracting entities and attributes by combining domain-specific dictionaries and contextual information, and standardizing the extracted entities and attributes" includes the following steps:

[0024] Based on the target domain data, construct a domain-specific dictionary containing key entities and attributes. The dictionary will serve as a reference benchmark for entity and attribute extraction.

[0025] The input text is preprocessed, including removing punctuation and special characters, word segmentation, and part-of-speech tagging.

[0026] By utilizing a pre-constructed domain-specific dictionary and combining it with the contextual information of the text, entities and attributes are extracted. By matching keywords and phrases in the dictionary and analyzing the grammatical structure and semantic relationships in the text, target entities and attributes are identified.

[0027] The extracted entities and attributes are standardized, including unifying naming conventions, removing synonyms and near-synonyms, and determining the type and value range of attributes, to ensure that the extracted entities and attributes are consistent and comparable in subsequent analysis and application.

[0028] Specifically, in the section on "combining scene semantic information to design a maximum correlation algorithm to evaluate the importance of different parameters in a specific ocean event or process," the method further includes the following steps:

[0029] Define the contextual semantic information of the specific marine events or processes that need to be evaluated, including the type of event, the geographical environment in which it occurs, the temporal context, related elements and their interrelationships, as the basis for subsequent algorithm design and parameter evaluation;

[0030] Based on the defined scene semantic information, relevant marine observation data, historical records, and experimental data are collected, preprocessed, and analyzed to obtain a reliable dataset for algorithm training and parameter evaluation.

[0031] Based on scene semantic information and collected data, a maximum correlation algorithm is designed. This algorithm quantifies the correlation of different parameters in a specific ocean event or process and identifies the key parameters that have the greatest impact on the event or process.

[0032] The maximum correlation algorithm was trained using the preprocessed dataset, and the accuracy and reliability of the algorithm were verified by cross-validation and model evaluation methods.

[0033] By using a trained maximum correlation algorithm, the importance of different parameters in a specific ocean event or process is assessed. By calculating the correlation score and contribution index of the parameters, the key parameters with the greatest impact on the event or process are identified.

[0034] Specifically, in the section "Matching extracted parameter information with ocean structured data through multi-dimensional correlation analysis to achieve multi-dimensional correlation of information," the method includes the following steps:

[0035] The sources of the extracted parameter information should be clearly identified, as well as the sources of the marine structured data, including marine environmental databases, historical records, and professional research reports;

[0036] Relevant parameter information is extracted and preprocessed, including data cleaning, data format conversion and data standardization. The preprocessed parameter information is then matched with ocean structured data.

[0037] A framework for constructing structured ocean data is established, which includes all relevant ocean data fields, including time, location, temperature, salinity, and current velocity. Each field has a clearly defined data type and value range.

[0038] After extracting and preprocessing parameter information and constructing a structured ocean data framework, multi-dimensional correlation analysis is performed, including identifying common features between parameter information and structured ocean data, establishing correlation rules, and calculating correlation degree. Through multi-dimensional correlation analysis, the intrinsic connection between parameter information and structured ocean data is revealed.

[0039] Based on the results of multi-dimensional correlation analysis, the extracted parameter information is matched with marine structured data to achieve multi-dimensional correlation of information, including mapping parameter information to corresponding fields in the marine structured data framework and establishing correlation tables or databases.

[0040] Specifically, in the section "Based on the analysis results, output the optimized extracted content, including key parameters, trend prediction, and anomaly detection," the method includes the following steps:

[0041] Organize the results obtained from all previous analysis steps, including the outputs of data preprocessing, multi-dimensional correlation analysis, and parameter evaluation steps;

[0042] From the compiled analysis results, extract the key parameters that have the greatest impact on the target ocean event or process;

[0043] By utilizing the extracted key parameters and combining time series analysis and machine learning, a trend prediction model is constructed.

[0044] Based on trend prediction, by real-time monitoring of key parameters and comparative analysis with historical data, possible outliers or abnormal situations can be identified.

[0045] The extracted key parameters, trend prediction results, and anomaly detection results are integrated into a complete report or dataset.

[0046] This invention presents a method for extracting multi-parameter marine information based on terminology semantics. It introduces advanced clustering and classification algorithms to perform deep learning and optimization of marine terms, building upon existing marine terminology semantic knowledge systems. Utilizing terminology expressive power and Chinese phrase structure rules, it optimizes the K-nearest neighbor algorithm to identify marine entities and their attributes in text. By combining domain-specific dictionaries and contextual information, it extracts entities and attributes, and standardizes the extracted entities and attributes. Combining scene semantic information, it designs a maximum relevance algorithm to assess the importance of different parameters in specific marine events or processes. Through multi-dimensional association analysis, it matches the extracted parameter information with structured marine data to achieve multi-dimensional information association. Based on the analysis results, it outputs optimized extraction content, including key parameters, trend predictions, and anomaly detection. An optimized clustering algorithm performs preliminary classification of water quality parameters: temperature, salinity, and dissolved oxygen. Then, the K-nearest neighbor algorithm combined with Chinese phrase structure rules is used to extract key entities and attributes from the text. Finally, using the maximum relevance algorithm, combined with the ecosystem characteristics and seasonal changes of the sea area, it selects the parameters with the greatest impact on water quality, generating intuitive reports and recommendations to provide decision-making support for managers. Attached Figure Description

[0047] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below.

[0048] Figure 1 This is a flowchart of a method for extracting marine multi-parameter information based on terminology semantics according to the present invention.

[0049] Figure 2 This invention is a flowchart illustrating the process of deep learning and optimization of marine terms by introducing advanced clustering and classification algorithms based on the existing semantic knowledge system of marine terms.

[0050] Figure 3 This invention utilizes the expressive power of terminology and the structural rules of Chinese phrases to optimize the K-nearest neighbor algorithm and identify marine entities and their attributes in text.

[0051] Figure 4 This is a flowchart of the present invention, which extracts entities and attributes by combining domain-specific dictionaries and contextual information, and then standardizes the extracted entities and attributes.

[0052] Figure 5 This is a flowchart of the present invention that combines scene semantic information to design a maximum correlation algorithm to evaluate the importance of different parameters in a specific ocean event or process.

[0053] Figure 6This invention is a flowchart illustrating how the extracted parameter information is matched with structured marine data through multi-dimensional correlation analysis to achieve multi-dimensional correlation of information.

[0054] Figure 7 This invention outputs optimized extracted content based on the analysis results, including flowcharts for key parameters, trend prediction, and anomaly detection. Detailed Implementation

[0055] The embodiments of the present invention are described in detail below. Examples of the embodiments are shown in the accompanying drawings. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, but should not be construed as limiting the present invention.

[0056] Please see Figures 1 to 7 , Figure 1 This is a flowchart of a method for extracting multi-parameter marine information based on terminology semantics according to the present invention. Figure 2 This invention, based on the existing semantic knowledge system of marine terminology, introduces advanced clustering and classification algorithms to perform deep learning and optimization of marine terminology. (Flowchart) Figure 3 This is a flowchart illustrating how the present invention optimizes the K-nearest neighbor algorithm to identify marine entities and their attributes in text by utilizing terminological expressiveness and Chinese phrase structure rules. Figure 4 This is a flowchart illustrating how the present invention extracts entities and attributes by combining domain-specific dictionaries and contextual information, and then standardizes the extracted entities and attributes. Figure 5 This is a flowchart illustrating how the present invention combines scene semantic information to design a maximum correlation algorithm to evaluate the importance of different parameters in a specific ocean event or process. Figure 6 This invention presents a flowchart illustrating how, through multi-dimensional correlation analysis, extracted parameter information is matched with structured ocean data to achieve multi-dimensional information correlation. Figure 7 This invention outputs optimized extracted content based on the analysis results, including flowcharts for key parameters, trend prediction, and anomaly detection.

[0057] A method for extracting multi-parameter marine information based on terminology semantics includes the following steps:

[0058] S1: Based on the existing semantic knowledge system of marine terminology, advanced clustering and classification algorithms are introduced to conduct deep learning and optimization of marine terminology;

[0059] S11: Collect marine terms and their related descriptions, integrate the data into the database, and perform data cleaning and preprocessing to remove duplicate, erroneous or irrelevant information;

[0060] S12: Based on the existing marine terminology semantic knowledge system, clustering and classification algorithms are used to initially apply the algorithms to the preprocessed data, and the performance of the algorithms is evaluated through cross-validation.

[0061] S13: Based on the preliminary algorithm results, construct a deep learning model to extract and classify deep features of marine terms, and train the model using preprocessed data;

[0062] S14: Combine the output of deep learning models with the existing marine terminology semantic knowledge system to update and improve the terminology database and explore new relationships between terms.

[0063] In this embodiment:

[0064] Step 1: Data Preparation and Preprocessing

[0065] Data collection and integration: We extensively collect marine terminology and its related descriptions from various marine science literature, databases, and professional websites, including the definition, classification, and contextual usage of the terms.

[0066] Data cleaning and standardization: Clean the collected data to remove duplicate, erroneous, or irrelevant information, and establish unified data formats and standards, such as spelling rules and definition formats for terms.

[0067] Constructing an initial terminology database: Organizing the cleaned data into an initial marine terminology semantic knowledge system, including terms and their attributes and relationships.

[0068] Step 2: Algorithm Selection and Optimization

[0069] Research advanced algorithms: Research current advanced clustering algorithms (such as DBSCAN, spectral clustering, hierarchical clustering) and classification algorithms (such as support vector machines, random forests, deep learning models) to understand their principles, advantages and applicable scenarios.

[0070] Algorithm Selection and Preliminary Testing: Based on the characteristics and requirements of marine terminology, appropriate clustering and classification algorithms were selected for preliminary testing. During testing, cross-validation, precision, and recall metrics were used to evaluate the algorithm's performance.

[0071] Algorithm optimization: Based on the results of the preliminary tests, parameter adjustments and feature selection optimizations were performed on the algorithm to improve its performance and accuracy.

[0072] Step 3: Deep Learning Model Training

[0073] Build deep learning models: Based on optimized clustering and classification algorithms, build deep learning models, such as convolutional neural networks (CNN), recurrent neural networks (RNN), or Transformers, for deep learning and feature extraction of marine terms.

[0074] Model Training: The deep learning model is trained using preprocessed marine terminology data to learn the semantic relationships and features between terms. During training, the model's parameters and learning rate need to be continuously adjusted to improve its generalization ability.

[0075] Model Evaluation and Tuning: The trained model is evaluated using a test dataset, and its performance is measured by metrics such as accuracy, recall, and F1 score. Based on the evaluation results, the model is further tuned and optimized.

[0076] Step 4: Optimization of Terminology Knowledge System

[0077] Update the terminology database: Integrate the features and relationships extracted by the deep learning model into the existing marine terminology semantic knowledge system to update and improve the terminology database.

[0078] Terminology Relationship Mining: Utilizing the output of deep learning models, new relationships between terms are mined, such as similarity, relevance, and causal relationships, to further enrich the terminology knowledge system.

[0079] Knowledge system verification: The optimized terminology knowledge system is verified through expert review, domain testing and other methods to ensure its accuracy and reliability.

[0080] Step 5: Continuous updates and maintenance

[0081] Real-time monitoring and updates: Establish a real-time monitoring system to track newly emerging marine terms and semantic relationships, and update the terminology knowledge system in a timely manner.

[0082] Model Iteration and Optimization: With the development of marine science and the continuous increase of data, deep learning models are regularly iterated and optimized to adapt to new data and needs.

[0083] User feedback and interaction: Encourage users to participate in the process of improving the terminology knowledge system and optimizing the model, and further enhance the accuracy and practicality of the terminology semantic knowledge system through user feedback.

[0084] S2: Utilizing terminological expressiveness and Chinese phrase structure rules, optimize the K-nearest neighbor algorithm to identify marine entities and their attributes in text:

[0085] S21: Analyze the phrase structure in Chinese, extract common phrase structure rules based on a large corpus, form a rule base, and use it as a grammatical basis for identifying marine entities and their attributes;

[0086] S22: Combining terminology expressiveness and Chinese phrase structure rules, design feature selection and representation methods to convert text data into feature vectors that can be processed by the algorithm. At the same time, adjust the parameters of the K-nearest neighbor algorithm and introduce a weighting mechanism.

[0087] S23: Using preprocessed text data and labeled marine entities and their attribute information, train the optimized KNN model. The model is then used to identify and extract marine entities and their attributes from new text data, forming structured information to provide a foundation for subsequent analysis and applications.

[0088] S24: Manually verify the recognition results, and iteratively optimize the algorithm and model based on the verification results.

[0089] In this embodiment:

[0090] Step 1: Terminology Database Construction and Preprocessing

[0091] Collect marine terminology: Collect marine-related terms extensively from authoritative marine science literature, databases, and professional websites, including marine organisms, marine phenomena, marine resources, and the marine environment.

[0092] Terminology standardization: The collected terms are standardized, including standardized spelling, definition, and classification, to ensure the accuracy and consistency of the terminology.

[0093] Enhanced Terminology Expressiveness: Based on the frequency of terminology use and contextual information, the expressiveness of terms is evaluated and improved, providing rich features for subsequent algorithm applications.

[0094] Step 2: Extraction of Chinese Phrase Structure Rules

[0095] Analyze Chinese phrase structure: Conduct in-depth research on Chinese phrase structure, including subject-predicate structure, verb-object structure, and modifier-head structure, and understand the manifestation and rules of these structures in texts.

[0096] Extracting structural rules: Based on a large Chinese text corpus, common Chinese phrase structural rules are extracted to form a rule base, providing grammatical basis for subsequent identification of marine entities and their attributes.

[0097] Step 3: Optimization of the K-Nearest Neighbors Algorithm

[0098] Feature selection and representation: Combining the expressive power of terms and the structural rules of Chinese phrases, we design appropriate feature selection and representation methods to convert text data into feature vectors that can be processed by the algorithm.

[0099] Algorithm parameter adjustment: Based on the characteristics of marine entity recognition, adjust the parameters of the K-nearest neighbor algorithm, such as the selection of the K value and the distance measurement method, to improve the recognition accuracy and efficiency of the algorithm.

[0100] Introducing a weighting mechanism: Considering the impact of different features on the recognition results, a weighting mechanism is introduced to weight important features, thereby further improving the algorithm's recognition ability.

[0101] Step 4: Identification of marine entities and their attributes

[0102] Training the model: The optimized KNN model was trained using preprocessed text data and labeled marine entities and their attribute information.

[0103] Model evaluation and optimization: The model's performance is evaluated using cross-validation, accuracy, and recall metrics, and the model is further optimized based on the evaluation results.

[0104] Identification and Extraction: Using the trained model, marine entities and their attributes are identified and extracted from new text data to form structured information.

[0105] Step 5: Result Verification and Feedback

[0106] Manual verification: The recognition results are manually verified to ensure their accuracy and reliability.

[0107] Feedback and iteration: Based on the verification results, the algorithm and model are iteratively optimized to improve recognition accuracy and generalization ability.

[0108] Continuous updates: As marine science develops and text data continues to increase, the terminology database and phrase structure rule database are continuously updated to ensure the timeliness and accuracy of the algorithm.

[0109] S3: By combining domain-specific dictionaries and contextual information, entities and attributes are extracted, and the extracted entities and attributes are standardized.

[0110] S31: Based on the target domain data, construct a domain-specific dictionary containing key entities and attributes. The dictionary will serve as a reference benchmark for entity and attribute extraction.

[0111] S32: Preprocess the input text, including removing noise from punctuation marks and special characters, word segmentation, and part-of-speech tagging;

[0112] S33: Utilize the constructed domain-specific dictionary and combine it with the contextual information of the text to extract entities and attributes. By matching keywords and phrases in the dictionary and analyzing the grammatical structure and semantic relationships in the text, the target entities and attributes are identified.

[0113] S34: Standardize the extracted entities and attributes, including unifying naming conventions, removing synonyms and near-synonyms, and determining the type and value range of attributes to ensure that the extracted entities and attributes are consistent and comparable in subsequent analysis and application.

[0114] In this embodiment:

[0115] Step 1: Constructing a Domain-Specific Dictionary. First, based on expertise in the target domain, construct a domain-specific dictionary containing key entities and attributes. This dictionary will serve as a benchmark for entity and attribute extraction, ensuring accuracy and professionalism.

[0116] Step Two: Text Preprocessing and Tokenization. The input text is preprocessed, including noise removal (such as punctuation and special characters), tokenization, and part-of-speech tagging. This step forms the basis for subsequent entity and attribute extraction, ensuring the cleanliness and readability of the text data.

[0117] Step 3: Extracting Entities and Attributes Using a Domain-Specific Dictionary and Contextual Information. This involves extracting entities and attributes by combining the constructed domain-specific dictionary with the contextual information of the text. Target entities and attributes are identified by matching keywords and phrases in the dictionary and analyzing the grammatical structure and semantic relationships in the text.

[0118] Step 4: Entity and Attribute Standardization. The extracted entities and attributes are standardized, including unifying naming conventions, removing synonyms and near-synonyms, and determining attribute types and value ranges. The purpose of this step is to ensure the consistency and comparability of the extracted entities and attributes in subsequent analysis and applications.

[0119] Step 5: Verification and Correction Finally, the standardized entities and attributes are verified and corrected. This is done through manual review or comparison with other reliable data sources to ensure the accuracy and completeness of the extraction and standardization. Any errors or omissions discovered are promptly corrected and supplemented.

[0120] S4: Combine scene semantic information to design a maximum correlation algorithm to evaluate the importance of different parameters in specific ocean events or processes;

[0121] S41: Define the contextual semantic information of the specific marine event or process that needs to be evaluated, including the type of event, the geographical environment in which it occurs, the temporal context, related elements and their interrelationships, as the basis for subsequent algorithm design and parameter evaluation;

[0122] S42: Based on the defined scene semantic information, collect relevant ocean observation data, historical records, and experimental data, and perform preprocessing and analysis to obtain a reliable dataset for algorithm training and parameter evaluation;

[0123] S43: Based on scene semantic information and collected data, design a maximum correlation algorithm. This algorithm quantifies the correlation of different parameters in a specific ocean event or process and identifies the key parameters that have the greatest impact on the event or process.

[0124] S44: Train the maximum correlation algorithm using the preprocessed dataset, and verify the accuracy and reliability of the algorithm through cross-validation and model evaluation methods;

[0125] S45: Using a trained maximum correlation algorithm, the importance of different parameters in a specific ocean event or process is assessed. By calculating the correlation score and contribution index of the parameters, the key parameters with the greatest impact on the event or process are identified.

[0126] In this embodiment,

[0127] Step 1: Define Scene Semantic Information. First, define the scene semantic information of the specific marine event or process to be evaluated, including the type of event, the geographical environment in which it occurs, the temporal context, relevant elements (such as ocean temperature, salinity, and current velocity), and their interrelationships. This information will serve as the basis for subsequent algorithm design and parameter evaluation.

[0128] Step Two: Data Collection and Analysis. Based on the defined scene semantic information, relevant ocean observation data, historical records, and experimental data are collected, and preprocessed and analyzed. This step aims to obtain a reliable dataset for algorithm training and parameter evaluation, ensuring the accuracy and effectiveness of subsequent evaluations.

[0129] Step 3: Design the Maximum Correlation Algorithm. Based on the scene semantic information and the collected data, design the maximum correlation algorithm. This algorithm should be able to quantify the correlation of different parameters in a specific ocean event or process, and identify the key parameters that have the greatest impact on the event or process. The algorithm design should consider the weights of the parameters, their interrelationships, and the dynamic changes in their impact on the event or process.

[0130] Step 4: Algorithm Training and Validation. The maximum correlation algorithm is trained using the preprocessed dataset, and its accuracy and reliability are validated through cross-validation and model evaluation. This step aims to ensure the applicability and robustness of the algorithm in different scenarios, providing a solid foundation for subsequent parameter evaluation.

[0131] Step 5: Assessing Parameter Importance Finally, using the trained maximum correlation algorithm, the importance of different parameters in a specific marine event or process is assessed. By calculating the correlation score and contribution index of the parameters, the key parameters with the greatest impact on the event or process are identified, providing decision support for subsequent marine scientific research, disaster early warning, and resource management. Simultaneously, based on the assessment results, the algorithm is adjusted and optimized as necessary to improve the accuracy and practicality of the assessment.

[0132] S5: Through multi-dimensional correlation analysis, the extracted parameter information is matched with marine structured data to achieve multi-dimensional correlation of information.

[0133] S51: Clearly identify the source of the extracted parameter information, and at the same time, clearly identify the source of the marine structured data, including marine environmental databases, historical records, and professional research reports;

[0134] S52: Extract relevant parameter information and perform preprocessing, including data cleaning, data format conversion and data standardization. The preprocessed parameter information is then matched with ocean structured data.

[0135] S53: Construct a framework for structured ocean data, which includes all relevant ocean data fields, including time, location, temperature, salinity, and current velocity. Each field has a clearly defined data type and value range.

[0136] S54: After extracting and preprocessing parameter information and constructing a structured ocean data framework, conduct multi-dimensional correlation analysis, including identifying common features between parameter information and structured ocean data, establishing correlation rules, and calculating correlation degree. Through multi-dimensional correlation analysis, reveal the intrinsic connection between parameter information and structured ocean data.

[0137] S55: Based on the results of multi-dimensional correlation analysis, the extracted parameter information is matched with marine structured data to achieve multi-dimensional correlation of information, including mapping parameter information to corresponding fields in the marine structured data framework and establishing correlation tables or databases.

[0138] In this embodiment,

[0139] Step 1: Clarify the sources of parameter information and ocean structured data

[0140] First, it is necessary to clarify the source of the extracted parameter information, which may originate from sensor data, remote sensing observations, or laboratory analysis results. Simultaneously, it is also necessary to clarify the source of the marine structured data, which typically includes marine environmental databases, historical records, and professional research reports. Clarifying the data source is fundamental for subsequent matching and correlation analysis.

[0141] Step 2: Extract and preprocess parameter information

[0142] Next, relevant parameter information is extracted from various sources and preprocessed. This includes data cleaning (removing outliers and filling in missing values), data format conversion (ensuring data format consistency), and data standardization (converting data into a comparable form). The preprocessed parameter information will be easier to match with ocean structured data.

[0143] Step 3: Constructing a Structured Data Framework for the Ocean

[0144] To match the parameter information, a framework for structured ocean data needs to be constructed. This framework should include all relevant ocean data fields, such as time, location, temperature, salinity, and current velocity, ensuring that each field has a clearly defined data type and value range. The constructed data framework will serve as the basis for subsequent matching and correlation analysis.

[0145] Step 4: Multi-dimensional correlation analysis

[0146] After extracting and preprocessing parameter information and constructing a structured ocean data framework, multi-dimensional correlation analysis is performed. This includes identifying common features between parameter information and structured ocean data, establishing correlation rules, and calculating the correlation degree. Through multi-dimensional correlation analysis, the intrinsic relationship between parameter information and structured ocean data can be revealed, providing guidance for subsequent information matching.

[0147] Step 5: Achieve multi-dimensional information association

[0148] Finally, based on the results of the multi-dimensional correlation analysis, the extracted parameter information is matched with marine structured data to achieve multi-dimensional information correlation. This includes mapping the parameter information to corresponding fields in the marine structured data framework and establishing correlation tables or databases. By achieving multi-dimensional information correlation, these data can be queried, analyzed, and utilized more conveniently, providing strong support for marine scientific research, environmental protection, and disaster early warning.

[0149] S6: Based on the analysis results, output the optimized extracted content, including key parameters, trend prediction, and anomaly detection.

[0150] S61: Organize the results obtained from all previous analysis steps, including the outputs of data preprocessing, multi-dimensional correlation analysis, and parameter evaluation steps;

[0151] S62: Extract the key parameters that have the greatest impact on the target ocean event or process from the organized analysis results;

[0152] S63: Utilize the extracted key parameters, combined with time series analysis and machine learning, to construct a trend prediction model;

[0153] S64: Based on trend prediction, identify possible outliers or abnormal situations by real-time monitoring of key parameters and comparative analysis with historical data.

[0154] S65: Integrate the extracted key parameters, trend prediction results, and anomaly detection results into a complete report or dataset.

[0155] In this embodiment:

[0156] Step 1: Organize and analyze the results

[0157] First, organize the results obtained from all previous analysis steps. This includes, but is not limited to, data preprocessing, multi-dimensional correlation analysis, and the output of parameter evaluation steps. Ensure the accuracy and completeness of all analysis results to lay the foundation for subsequent extraction of optimal content.

[0158] Step 2: Extract key parameters

[0159] From the compiled analysis results, key parameters with the greatest impact on the target marine event or process are extracted using importance assessment and correlation analysis methods. These parameters should be representative and able to reflect the main characteristics and changing trends of the marine environment.

[0160] Step 3: Build a trend prediction model

[0161] By utilizing extracted key parameters and combining time series analysis and machine learning methods, a trend prediction model is constructed. This model should be able to predict the changing trends of key parameters over a future period, providing decision support for marine scientific research and disaster early warning.

[0162] Step 4: Implement anomaly detection

[0163] Based on trend forecasting, anomaly detection is implemented. By monitoring key parameters in real time and comparing them with historical data, potential outliers or anomalies are identified. These outliers may indicate sudden changes or potential risks in the marine environment, requiring special attention.

[0164] Step 5: Output the optimized extracted content

[0165] Finally, integrate the extracted key parameters, trend prediction results, and anomaly detection results into a complete report or dataset. Ensure that the report or dataset is clear, accurate, and easy to understand. Furthermore, present the optimized extracted content in an appropriate format (such as tables, charts, or reports) according to actual needs to facilitate subsequent analysis and application.

[0166] The above-disclosed embodiments are merely one or more preferred embodiments of this application and should not be construed as limiting the scope of this application. Those skilled in the art can understand that all or part of the processes for implementing the above embodiments and equivalent changes made in accordance with the claims of this application still fall within the scope of this application.

Claims

1. A method for extracting multi-parameter marine information based on terminology semantics, characterized in that, Includes the following steps: Based on the existing semantic knowledge system of marine terminology, advanced clustering and classification algorithms are introduced to conduct deep learning and optimization of marine terminology; By leveraging terminology expressiveness and Chinese phrase structure rules, the K-nearest neighbor algorithm is optimized to identify marine entities and their attributes in text. By combining domain-specific dictionaries and contextual information, entities and attributes are extracted, and the extracted entities and attributes are standardized. By combining scene semantic information, a maximum correlation algorithm is designed to evaluate the importance of different parameters in specific ocean events or processes; Through multi-dimensional correlation analysis, the extracted parameter information is matched with ocean structured data to achieve multi-dimensional correlation of information; Based on the analysis results, the optimal extracted content is output, including key parameters, trend prediction, and anomaly detection. The section on "Designing a maximum correlation algorithm by combining scene semantic information to evaluate the importance of different parameters in specific ocean events or processes" includes the following steps: Define the scene semantic information of the specific marine event or process to be evaluated, including the type of event, the geographical environment in which it occurs, the temporal context, related elements and their interrelationships, as the basis for subsequent algorithm design and parameter evaluation; based on the defined scene semantic information, collect relevant marine observation data, historical records and experimental data, and perform preprocessing and analysis to obtain a reliable dataset for algorithm training and parameter evaluation; Based on scene semantic information and collected data, a maximum correlation algorithm is designed. This algorithm quantifies the correlation of different parameters in a specific ocean event or process and identifies the key parameters that have the greatest impact on the event or process. The maximum correlation algorithm was trained using a preprocessed dataset, and its accuracy and reliability were verified through cross-validation and model evaluation. The trained maximum correlation algorithm was then used to assess the importance of different parameters in a specific ocean event or process. By calculating the correlation score and contribution index of the parameters, the key parameters with the greatest impact on the event or process were identified. The step of "matching extracted parameter information with ocean structured data through multi-dimensional correlation analysis to achieve multi-dimensional correlation of information" includes the following steps: The process involves clearly identifying the sources of extracted parameter information, as well as the sources of marine structured data, including marine environmental databases, historical records, and professional research reports. Relevant parameter information is extracted and preprocessed, including data cleaning, data format conversion, and data standardization. The preprocessed parameter information is then matched with the marine structured data. A framework for the marine structured data is constructed, containing all relevant marine data fields, including time, location, temperature, salinity, and current velocity, each with a clearly defined data type and value range. After extracting and preprocessing the parameter information and constructing the marine structured data framework, multi-dimensional correlation analysis is performed. This includes identifying common features between the parameter information and the marine structured data, establishing correlation rules, and calculating the correlation degree. Through multi-dimensional correlation analysis, the intrinsic connections between the parameter information and the marine structured data are revealed. Based on the results of the multi-dimensional correlation analysis, the extracted parameter information is matched with the marine structured data to achieve multi-dimensional information correlation, including mapping the parameter information to corresponding fields in the marine structured data framework and establishing correlation tables or databases.

2. The method for extracting multi-parameter marine information based on terminology semantics as described in claim 1, characterized in that, In the section "Based on the existing semantic knowledge system of marine terminology, advanced clustering and classification algorithms are introduced to perform deep learning and optimization of marine terminology," the method includes the following steps: Collect marine terminology and its related descriptions, integrate the data into a database, and perform data cleaning and preprocessing to remove duplicate, erroneous, or irrelevant information; Based on the existing marine terminology semantic knowledge system, clustering and classification algorithms are used to initially apply the algorithms to preprocessed data, and the performance of the algorithms is evaluated through cross-validation. Based on the preliminary algorithm results, a deep learning model was constructed to extract and classify deep features of marine terms, and the model was trained using preprocessed data. By combining the output of deep learning models with the existing semantic knowledge system of marine terminology, the terminology database can be updated and improved, and new relationships between terms can be discovered.

3. The method for extracting marine multi-parameter information based on terminology semantics as described in claim 2, characterized in that, In "Optimizing the K-Nearest Neighbor Algorithm to Identify Marine Entities and Their Attributes in Text by Utilizing Terminology Expressiveness and Chinese Phrasal Structure Rules", the method includes the following steps: We analyze the phrase structure in Chinese, extract common phrase structure rules from a large corpus, and form a rule base to serve as the grammatical basis for identifying marine entities and their attributes. Combining terminology expressiveness and Chinese phrase structure rules, we designed feature selection and representation methods to convert text data into feature vectors that can be processed by the algorithm. At the same time, we adjusted the parameters of the K-nearest neighbor algorithm and introduced a weighting mechanism. Using preprocessed text data and labeled marine entities and their attribute information, an optimized KNN model is trained. The model is then used to identify and extract marine entities and their attributes from new text data, forming structured information that provides a foundation for subsequent analysis and applications. The recognition results are manually verified, and the algorithm and model are iteratively optimized based on the verification results.

4. The method for extracting multi-parameter marine information based on terminology semantics as described in claim 1, characterized in that, The step of "extracting entities and attributes by combining domain-specific dictionaries and contextual information, and standardizing the extracted entities and attributes" includes the following steps: Based on the target domain data, construct a domain-specific dictionary containing key entities and attributes. The dictionary will serve as a reference benchmark for entity and attribute extraction. The input text is preprocessed, including removing punctuation and special characters, word segmentation, and part-of-speech tagging. By utilizing a pre-constructed domain-specific dictionary and combining it with the contextual information of the text, entities and attributes are extracted. By matching keywords and phrases in the dictionary and analyzing the grammatical structure and semantic relationships in the text, target entities and attributes are identified. The extracted entities and attributes are standardized, including unifying naming conventions, removing synonyms and near-synonyms, and determining the type and value range of attributes, to ensure that the extracted entities and attributes are consistent and comparable in subsequent analysis and application.

5. The method for extracting multi-parameter marine information based on terminology semantics as described in claim 1, characterized in that, In the section "Based on the analysis results, output the optimized extracted content, including key parameters, trend prediction, and anomaly detection," the method includes the following steps: Organize the results obtained from all previous analysis steps, including the outputs of data preprocessing, multi-dimensional correlation analysis, and parameter evaluation steps; From the compiled analysis results, extract the key parameters that have the greatest impact on the target ocean event or process; By utilizing the extracted key parameters and combining time series analysis and machine learning, a trend prediction model is constructed. Based on trend prediction, by real-time monitoring of key parameters and comparative analysis with historical data, possible outliers or abnormal situations can be identified. The extracted key parameters, trend prediction results, and anomaly detection results are integrated into a complete report or dataset.

Images