Knowledge ontology construction method and device

Abstract

The invention discloses a knowledge ontology construction method and device. The method comprises the steps of obtaining multi-source information service field data information; the multi-source information service field data information comprises geographical research results, geographical analysis reports and environmental investigation data; processing the multi-source information service field data information to obtain an information service field knowledge ontology; performing ontology quality evaluation on the information service domain knowledge ontology to obtain an ontology quality evaluation result; and according to the ontology quality evaluation result, optimizing the information service domain knowledge ontology to obtain an optimized information service domain knowledge ontology. According to the method, differentiated concept, attribute and relation design is adopted for different features of factual, regular and decision-making knowledge, so that the ontology structure better fits domain business logic, and the accuracy of knowledge expression is improved.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, and in particular to a method and apparatus for constructing a knowledge ontology. Background Technology

[0002] Knowledge ontology, as a standardized description of domain knowledge, can clearly define knowledge concepts and the relationships between them. It is the core foundation for realizing knowledge representation, reasoning, sharing and reuse, and is widely used in many fields such as intelligent question answering, knowledge graph construction and decision support systems.

[0003] Existing knowledge ontology construction methods often have a limited range of node types, focusing primarily on factual knowledge nodes and failing to comprehensively cover complex knowledge types such as rule-based and decision-based knowledge. Furthermore, the attribute definitions for various node types lack uniformity and specificity. Either the attribute settings are too general to meet the refined description requirements of different knowledge types, or the attributes are redundant and disorganized. This results in low construction efficiency and high maintenance costs for the knowledge ontology, and makes it difficult to effectively establish relationships between different types of nodes, affecting the completeness and usability of the knowledge ontology and thus limiting the effectiveness of knowledge applications based on it.

[0004] Therefore, how to design a knowledge ontology construction method that can comprehensively cover multiple knowledge types, standardize attribute definitions, and combine uniformity with specificity has become an urgent technical problem to be solved in the field of knowledge engineering. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide a method and apparatus for constructing a knowledge ontology, which achieves the comprehensiveness, standardization and practicality of the knowledge ontology by clearly dividing the types of knowledge nodes and standardizing the attribute system of various nodes, thereby improving the efficiency of knowledge construction and the ability of knowledge reuse.

[0006] To address the aforementioned technical problems, a first aspect of this invention discloses a knowledge ontology construction method, the method comprising: S1, acquire multi-source information service domain data information; the multi-source information service domain data information includes geographical research results, geopolitical analysis reports and environmental survey data; S2, process the multi-source information service domain data information to obtain the information service domain knowledge ontology; S3, perform ontology quality evaluation on the knowledge ontology of the information service domain to obtain ontology quality evaluation results; S4. Based on the ontology quality evaluation results, optimize the information service domain knowledge ontology to obtain an optimized information service domain knowledge ontology.

[0007] As an optional implementation, in the first aspect of the present invention, processing the multi-source information service domain data information to obtain an information service domain knowledge ontology includes: S21, preprocess the multi-source information service domain data information to obtain preprocessed information service domain data information; S22, Process the preprocessed information service domain data information to obtain an ontology concept model; S23, Process the ontology concept model to obtain the knowledge system of the information service domain; S24, process the knowledge system of the information service domain to obtain the knowledge ontology of the information service domain; the knowledge ontology of the information service domain includes fact-based knowledge ontology, rule-based knowledge ontology and decision-based knowledge ontology.

[0008] As an optional implementation, in the first aspect of the present invention, the preprocessing of the multi-source information service domain data information to obtain preprocessed information service domain data information includes: S211, perform data cleaning on the multi-source information service domain data information to obtain cleaned data information; S212, perform semantic annotation and knowledge extraction on the cleaned data information to obtain core knowledge element information; S213, perform data association and fusion on the core knowledge element information to obtain preprocessed information service domain data information.

[0009] As an optional implementation, in the first aspect of the present invention, the step of cleaning the multi-source information service domain data information to obtain cleaned data information includes: S2111, Process the missing values ​​of the data information in the multi-source information service domain to obtain the first preprocessed data information; S2112, perform outlier processing on the first preprocessed data information to obtain the second preprocessed data information; S2113, perform redundant data processing on the second preprocessed data information to obtain cleaned data information.

[0010] As an optional implementation, in the first aspect of the present invention, the step of semantically annotating and extracting knowledge from the cleaned data information to obtain core knowledge element information includes: S2121, Perform named entity recognition on the cleaning data information to obtain entity information; S2122, perform relation extraction on the entity information to obtain entity relation information; S2123, Extract attributes from the entity information to obtain entity attribute information; S2124, The entity relationship information and the entity attribute information are integrated to obtain core knowledge element information.

[0011] As an optional implementation, in the first aspect of the present invention, the step of data association and fusion of the core knowledge element information to obtain preprocessed information service domain data information includes: S2131, Perform entity alignment on the core knowledge element information to obtain structured entity element information; S2132, Process the structured entity element information to obtain entity relationship attribute graph structure data; S2133, perform spatiotemporal correlation on the entity relationship attribute graph structure data to obtain preprocessed information service domain data information.

[0012] As an optional implementation, in the first aspect of the present invention, processing the information service domain knowledge system to obtain an information service domain knowledge ontology includes: S241, the knowledge system of the information service domain is decomposed to obtain factual knowledge, rule-based knowledge, and decision-based knowledge; the factual knowledge includes information environment knowledge, socio-cultural environment knowledge, natural environment knowledge, general spatiotemporal knowledge, and entity element knowledge; S242, Process the factual knowledge to obtain the factual knowledge ontology; S243, Process the rule-based knowledge to obtain the rule-based knowledge ontology; S244, Process the decision-type knowledge to obtain the decision-type knowledge ontology; S245, integrate the factual knowledge ontology, the rule-based knowledge ontology, and the decision-based knowledge ontology to obtain the information service domain knowledge ontology.

[0013] A second aspect of this invention discloses a knowledge ontology construction apparatus, the apparatus comprising: The data acquisition module is used to acquire data information from the multi-source information service field; the multi-source information service field data information includes geographical research results, geopolitical analysis reports, and environmental survey data; The knowledge ontology construction module is used to process the data information of the multi-source information service domain to obtain the knowledge ontology of the information service domain; The ontology quality evaluation module is used to evaluate the ontology quality of the knowledge ontology in the information service domain and obtain the ontology quality evaluation result. The ontology optimization module is used to optimize the information service domain knowledge ontology based on the ontology quality evaluation results, so as to obtain an optimized information service domain knowledge ontology.

[0014] As an optional implementation, in the second aspect of the present invention, the processing of the multi-source information service domain data information to obtain an information service domain knowledge ontology includes: S21, preprocess the multi-source information service domain data information to obtain preprocessed information service domain data information; S22, Process the preprocessed information service domain data information to obtain an ontology concept model; S23, Process the ontology concept model to obtain the knowledge system of the information service domain; S24, process the knowledge system of the information service domain to obtain the knowledge ontology of the information service domain; the knowledge ontology of the information service domain includes fact-based knowledge ontology, rule-based knowledge ontology and decision-based knowledge ontology.

[0015] As an optional implementation, in the second aspect of the present invention, the preprocessing of the multi-source information service domain data information to obtain preprocessed information service domain data information includes: S211, perform data cleaning on the multi-source information service domain data information to obtain cleaned data information; S212, perform semantic annotation and knowledge extraction on the cleaned data information to obtain core knowledge element information; S213, perform data association and fusion on the core knowledge element information to obtain preprocessed information service domain data information.

[0016] As an optional implementation, in the second aspect of the present invention, the step of cleaning the multi-source information service domain data information to obtain cleaned data information includes: S2111, Process the missing values ​​of the data information in the multi-source information service domain to obtain the first preprocessed data information; S2112, perform outlier processing on the first preprocessed data information to obtain the second preprocessed data information; S2113, perform redundant data processing on the second preprocessed data information to obtain cleaned data information.

[0017] As an optional implementation, in the second aspect of the present invention, the step of semantically annotating and extracting knowledge from the cleaned data information to obtain core knowledge element information includes: S2121, Perform named entity recognition on the cleaning data information to obtain entity information; S2122, perform relation extraction on the entity information to obtain entity relation information; S2123, Extract attributes from the entity information to obtain entity attribute information; S2124, The entity relationship information and the entity attribute information are integrated to obtain core knowledge element information.

[0018] As an optional implementation, in the second aspect of the present invention, the step of data association and fusion of the core knowledge element information to obtain preprocessed information service domain data information includes: S2131, Perform entity alignment on the core knowledge element information to obtain structured entity element information; S2132, Process the structured entity element information to obtain entity relationship attribute graph structure data; S2133, perform spatiotemporal correlation on the entity relationship attribute graph structure data to obtain preprocessed information service domain data information.

[0019] As an optional implementation, in the second aspect of the present invention, processing the information service domain knowledge system to obtain an information service domain knowledge ontology includes: S241, the knowledge system of the information service domain is decomposed to obtain factual knowledge, rule-based knowledge, and decision-based knowledge; the factual knowledge includes information environment knowledge, socio-cultural environment knowledge, natural environment knowledge, general spatiotemporal knowledge, and entity element knowledge; S242, Process the factual knowledge to obtain the factual knowledge ontology; S243, Process the rule-based knowledge to obtain the rule-based knowledge ontology; S244, Process the decision-type knowledge to obtain the decision-type knowledge ontology; S245, integrate the factual knowledge ontology, the rule-based knowledge ontology, and the decision-based knowledge ontology to obtain the information service domain knowledge ontology.

[0020] A third aspect of the present invention discloses another knowledge ontology construction apparatus, the apparatus comprising: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute some or all of the steps in the knowledge ontology construction method disclosed in the first aspect of the present invention.

[0021] The fourth aspect of the present invention discloses a computer-storable medium storing computer instructions, which, when invoked, are used to execute some or all of the steps in the knowledge ontology construction method disclosed in the first aspect of the present invention.

[0022] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: This invention integrates heterogeneous information from multiple sources, including geographical research findings, geopolitical analysis reports, and environmental survey data, overcoming the limitations of single data sources and ensuring the comprehensiveness and accuracy of the knowledge ontology. Through data cleaning, semantic annotation, and entity alignment, it effectively eliminates noise, unifies semantics, and establishes relationships, providing high-quality foundational data for subsequent ontology construction. Differentiated concept, attribute, and relationship designs are employed to address the different characteristics of factual, rule-based, and decision-based knowledge, making the ontology structure more aligned with domain-specific business logic and improving the accuracy of knowledge representation. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a flowchart illustrating a knowledge ontology construction method disclosed in an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of a knowledge ontology construction device disclosed in an embodiment of the present invention; Figure 3 This is a schematic diagram of another knowledge ontology construction device disclosed in an embodiment of the present invention. Detailed Implementation

[0025] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0026] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0027] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0028] In all embodiments of the present invention, the variables involved in all computational expressions or mathematical functions are dimensionless before calculation. The values ​​of the independent variables in all computational expressions or mathematical functions in these embodiments conform to the reasonable requirements of the input range of the computational expression or mathematical function, ensuring that the computational expression or mathematical function can be calculated smoothly without violating physical laws or mathematical rules.

[0029] This invention discloses a method and apparatus for constructing a knowledge ontology. The method includes acquiring multi-source information service domain data, which includes geographical research results, geopolitical analysis reports, and environmental survey data; processing the multi-source information service domain data to obtain an information service domain knowledge ontology; evaluating the ontology quality of the information service domain knowledge ontology to obtain an ontology quality evaluation result; and optimizing the information service domain knowledge ontology based on the ontology quality evaluation result to obtain an optimized information service domain knowledge ontology. Detailed explanations follow.

[0030] Example 1 Please see Figure 1 , Figure 1 This is a flowchart illustrating a knowledge ontology construction method disclosed in an embodiment of the present invention. Figure 1 The described knowledge ontology construction method is applied to the field of artificial intelligence technology, and the embodiments of this invention are not limited thereto. Figure 1 As shown, this knowledge ontology construction method can include the following operations: S1, acquire multi-source information service domain data information; the multi-source information service domain data information includes geographical research results, geopolitical analysis reports and environmental survey data; S2, process the multi-source information service domain data information to obtain the information service domain knowledge ontology; S3, perform ontology quality evaluation on the knowledge ontology of the information service domain to obtain ontology quality evaluation results; S4. Based on the ontology quality evaluation results, optimize the information service domain knowledge ontology to obtain an optimized information service domain knowledge ontology.

[0031] Optionally, the processing of the multi-source information service domain data information to obtain the information service domain knowledge ontology includes: S21, preprocess the multi-source information service domain data information to obtain preprocessed information service domain data information; S22, Process the preprocessed information service domain data information to obtain an ontology concept model; S23, Process the ontology concept model to obtain the knowledge system of the information service domain; S24, process the knowledge system of the information service domain to obtain the knowledge ontology of the information service domain; the knowledge ontology of the information service domain includes fact-based knowledge ontology, rule-based knowledge ontology and decision-based knowledge ontology.

[0032] Optionally, the preprocessing of the multi-source information service domain data information to obtain preprocessed information service domain data information includes: S211, perform data cleaning on the multi-source information service domain data information to obtain cleaned data information; S212, perform semantic annotation and knowledge extraction on the cleaned data information to obtain core knowledge element information; S213, perform data association and fusion on the core knowledge element information to obtain preprocessed information service domain data information.

[0033] Optionally, the step of cleaning the multi-source information service domain data to obtain cleaned data includes: S2111, Process the missing values ​​of the data information in the multi-source information service domain to obtain the first preprocessed data information; S2112, perform outlier processing on the first preprocessed data information to obtain the second preprocessed data information; S2113, perform redundant data processing on the second preprocessed data information to obtain cleaned data information.

[0034] Optionally, the step of semantically annotating and extracting knowledge from the cleaned data information to obtain core knowledge element information includes: S2121, Perform named entity recognition on the cleaning data information to obtain entity information; 1) Perform text preprocessing and feature encoding on the cleaned data; The cleaned data is segmented at the character level to obtain character sequences. , The length of the character sequence; the cleaned data is segmented to obtain a word sequence. , The length of the word sequence records the word position mapping relationship for each character. ; Constructing a multi-dimensional initial feature set: The character sequence C is encoded using the pre-trained Chinese character vector model FastText to obtain character embedding features. ; The word sequence W is encoded using the pre-trained Chinese word vector model Word2Vec, and word embedding features are obtained by combining the positional mapping relationship M. ; Part-of-speech tagging is performed on the vocabulary sequence W to obtain the part-of-speech sequence. After encoding through the part-of-speech embedding layer and combining it with the mapping relationship M, we obtain the character-dimensional part-of-speech embedding features. ; Character embedding features Word embedding features Part-of-speech embedding features The fusion process is performed to obtain the fusion characteristics; The specific fusion method expression is as follows: Norm represents standardization. , express Length; in, express function, and These are preset, learnable model parameters. Initializing with a normal distribution ensures stable variance of the initial output, preventing gradient vanishing or exploding. For bias information, tanh is the hyperbolic tangent function; 2) Input the fused features into a pre-trained Chinese language model to obtain the basic semantic features H; 3) Enhance the long-distance dependency of the basic semantic feature H by introducing a multi-head self-attention mechanism to perform secondary feature extraction on H, focusing on capturing the cross-positional association features of entities in long texts to obtain enhanced semantic features. ; in, This is a weight matrix for attention queries, keys, and values; 4) Enhanced semantic features By performing residual connections and layer normalization, the gradient vanishing problem in deep models is alleviated, and pre-trained fused features are obtained. ; 5) Integrate pre-trained features The input is fed into a bidirectional long short-term memory network (BiLSTM) to further capture the contextual sequence dependencies of the features, thus obtaining the sequence features L. 6) Then, the sequence features L are mapped to the label space through a linear transformation layer to obtain the label probability distribution G for each character; 7) Use conditional random fields to solve for the optimal label sequence Y; 8) Perform entity parsing on the optimal label sequence Y, extract the start position, end position and entity category of the entity, and obtain the final named entity recognition result R.

[0035] S2122, perform relation extraction on the entity information to obtain entity relation information; S2123, Extract attributes from the entity information to obtain entity attribute information; S2124, The entity relationship information and the entity attribute information are integrated to obtain core knowledge element information.

[0036] Optionally, the step of data association and fusion of the core knowledge element information to obtain preprocessed information service domain data information includes: S2131, Perform entity alignment on the core knowledge element information to obtain structured entity element information; S2132, Process the structured entity element information to obtain entity relationship attribute graph structure data; Using weighted directed graphs To characterize the entity-relationship attribute graph structure, where the vertex set Corresponding to the entity set, directed edges Connect any pair of entities with non-zero weights. and Similarity weight matrix Describe the relationships between all entities, where Representing entities right The impact.

[0037] S2133, perform spatiotemporal correlation on the entity relationship attribute graph structure data to obtain preprocessed information service domain data information, including: Z-score standardization is performed on the target attribute data sequence of every two entities in the entity relationship attribute graph structure data. After calculating the difference between the corresponding elements, the difference is multiplied by the coefficient of variation weight of the attribute to obtain the numerical attribute difference data sequence. Statistical processing was performed on the differential data sequences for each attribute category to obtain the corresponding mean and variance. Calculate the skewness (direction of distribution skewness) and kurtosis (degree of clustering of extreme values) of the differential data sequence for each attribute. By using the mean, variance, skewness, and kurtosis of all class attributes, a set of statistical distribution values ​​is constructed. Using the set of statistical distribution values, a spatial distribution vector is constructed to obtain preprocessed information service domain data information; Optionally, the processing of the information service domain knowledge system to obtain the information service domain knowledge ontology includes: S241, the knowledge system of the information service domain is decomposed to obtain factual knowledge, rule-based knowledge, and decision-based knowledge; the factual knowledge includes information environment knowledge, socio-cultural environment knowledge, natural environment knowledge, general spatiotemporal knowledge, and entity element knowledge; S242, Process the factual knowledge to obtain the factual knowledge ontology; S243, Process the rule-based knowledge to obtain the rule-based knowledge ontology; S244, Process the decision-type knowledge to obtain the decision-type knowledge ontology; S245, integrate the factual knowledge ontology, the rule-based knowledge ontology, and the decision-based knowledge ontology to obtain the information service domain knowledge ontology.

[0038] Optionally, the step of integrating the factual knowledge ontology, the rule-based knowledge ontology, and the decision-based knowledge ontology to obtain an information service domain knowledge ontology includes: Step 1: Concept Definition and System Construction Define the scope of concepts: Based on the needs of the geographic information field, define the core concepts of general spatiotemporal knowledge (time / space subcategories) and entity element knowledge (natural / human subcategories); Hierarchical system construction: Using the class-subclass function of ontology modeling tools (such as Protege), a conceptual hierarchy is established (such as spatial concept - provincial administrative region - a certain province, entity element - natural geographical entity - mountain range - a certain mountain range).

[0039] Step 2: Property Design and Binding Attribute definition: In the modeling tool, use the DataProperties module to create common attributes (identifier, name, etc.) and specific attributes (such as geographic location, spatial scale). Attribute binding: Use the Domain tool to bind attributes to corresponding concepts, such as binding geographic location to entity element concept, and binding time granularity to time-based general spatiotemporal concept, to ensure semantic matching between attributes and concepts.

[0040] Step 3: Relationship Design and Association Establishment Relationship definition: In the ObjectProperties module of the modeling tool, create 5 types of relations (Lr / Cr / Tr / Sr / Ar). Relationship constraints: Set the domain and range for each type of relationship (e.g., set the domain of Lr to a general spatiotemporal concept and the range to an entity element concept). Instance association: Based on preprocessed data (such as GIS topological relationships and spatial association data), establish relationships for conceptual instances, such as establishing a spatial relationship between a lake and a province (located in).

[0041] Step 4: Instantiation and Ontology Verification Optimization Node instantiation: Extract specific instances (such as a mountain range or the 2025 flood season) from the processed data and populate them with attribute information (such as latitude and longitude, and time granularity). Verification and optimization: Through completeness verification (checking whether core concepts / attributes are fully covered), consistency verification (checking whether topological relationships / attributes are contradictory), and accuracy verification (verifying whether coordinates / attributes are consistent with reality), issues are corrected in conjunction with expert review in the field of geography (such as supplementing missing wetland entity concepts).

[0042] Step 5: Triple Conversion and Storage Triple conversion: Convert concepts, attributes, and relations into triples using modeling tool plugins (such as OWL2Neo4j); Triple completion: Mapping triples to obtain a low-dimensional semantic space representation; The triples are processed to obtain neighbor information (based on the structural information of the knowledge graph, its multi-hop neighbor entities and relationships are extracted, and a local subgraph is constructed). The neighbor information is then processed to obtain a low-dimensional semantic space representation, including structural semantic embedding representation and text semantic embedding representation. The low-dimensional semantic space representation is processed to obtain matching information; 1) Calculate the semantic similarity score of the text: This is the weight matrix of the neural network (Adaptive Cross-Modal Feedforward Network ACM-MLP). d Let be the dimension of the matrix. r For neighbor information, Embed vectors for predefined task relationships. For the information of the i-th neighbor, This refers to the bias information of the hybrid neural network. Score the semantic similarity of the text; Calculate the text semantic attention weights; For the first The textual semantic attention weights of each neighboring node, For the first Pre-defined task relationship embedding vectors: Text semantic entity embedding is performed to obtain text semantic embedding result e1; Let be the embedding vector of the adjacent entities of the i-th query head node; 2) Calculate the text structure similarity score; Given a node and its neighbor node set Then its population coefficient for: in, l This represents the actual number of edges that exist between a node and its neighboring nodes. d The number of neighboring nodes. Population coefficient. The value ranges from [0,1], and a higher value indicates that the neighbors of the node are more closely connected; Assign a score based on the similarity of the text structure. For query header entities, weight matrix Bias terms are used to learn the relationships between different dimensions. Used to adjust the model's output. Attention weights of the text structure of each neighboring node for: Text structure entity embedding is performed to obtain text structure embedding result e2; The semantic embedding result e1 and the structural embedding result e2 are fused to obtain the entity embedding result; Swish is the activation function of the adaptive cross-modal feedforward network ACM-MLP. For entity embedding results, , , , , and The weight matrices are preset and independent. , ≠ , ).

[0043] The entity embedding results are processed using a Transformer encoder to obtain triple information. ; , For the tail entity embedding result, For relational embedding, This represents the concatenation operation; the calculation methods for tail entity embedding and relation embedding, and The calculation method is the same, and this embodiment does not impose any restrictions.

[0044] The triplet information is processed to obtain the query triplet embedding vector. q ; in This indicates a dynamic routing feedforward network. This indicates domain-aware multi-head attention.

[0045] Query triple embedding vector q The process is performed to obtain matching information; The matching information expression is: Where is the dot product symbol, q To query the triple embedding vector, To match information, The preset balance coefficient, For entities The domain weights are either predefined or learned from domain data; The matching information is processed to obtain normalized matching information; in To normalize matching information, is a preset learnable parameter, and margin is a hyperparameter used to introduce a penalty term for negative samples in the denominator to enhance the ability to distinguish negative samples. The normalized matching information is processed to obtain weighted embedding information: Weighted embedding information; calculation of prediction scores : Select all possible tail entities from a pre-defined entity library to construct candidate triples. Based on the prediction scores, calculate the embedding score of each candidate triple relative to the reference prototype. , This section represents candidate triples. A threshold is set, and candidate triples with scores higher than the threshold are selected. The output is sorted: candidates are arranged in descending order of score, and the Top-N are used as completion suggestions. The selected links are then used to generate new triples.

[0046] Graph database storage: Import triples into a graph database (such as Neo4j) to leverage the advantages of graph structure to achieve spatial association queries and hierarchical tracing; Dynamic updates: Establish a version management mechanism to update based on geographic data (such as adding monitoring points or revising planning data), supplement concept instances, and update attributes / relationships.

[0047] Knowledge acquisition and node instantiation steps: Acquire domain knowledge through multi-source data collection, expert knowledge input, etc., parse and extract the acquired knowledge according to the node type defined in step 1 and the attribute system constructed in step 2, generate corresponding node instances, and fill each node instance with complete attribute information; Steps for constructing node association relationships: Define various types of association relationships between nodes, including spatial relationships (Lr), compositional relationships (Cr), temporal relationships (Tr), semantic relationships (Sr), and association relationships (Ar). The association relationship types correspond one-to-one with the relationship types in the decision knowledge representation model. Based on the attribute information of the nodes, establish association relationships between different node instances. Knowledge ontology verification and optimization steps: The constructed knowledge ontology is verified for completeness, consistency, and accuracy. Problems are identified and corrected through expert review, instance testing, and other methods. Knowledge ontology storage and update steps: The optimized knowledge ontology is converted into a triple (S, P, O) form that adapts to the decision knowledge representation model using ontology modeling tools, stored in a graph database, and a version management mechanism for the knowledge ontology is established to dynamically update the triple form of the knowledge ontology according to the update of domain knowledge.

[0048] As can be seen, this invention integrates heterogeneous information from multiple sources, including geographical research results, geopolitical analysis reports, and environmental survey data, overcoming the limitations of single data sources and ensuring the comprehensiveness and accuracy of the knowledge ontology. Through data cleaning, semantic annotation, and entity alignment, noise is effectively eliminated, semantics are unified, and relationships are established, providing high-quality foundational data for subsequent ontology construction. Differentiated concept, attribute, and relationship designs are employed to address the different characteristics of factual, rule-based, and decision-based knowledge, making the ontology structure more aligned with domain business logic and improving the accuracy of knowledge representation.

[0049] Example 2 Please see Figure 2 , Figure 2 This is a schematic diagram of the structure of a knowledge ontology construction device disclosed in an embodiment of the present invention. Figure 2 The described knowledge ontology construction device is in the field of artificial intelligence technology, and the embodiments of this invention are not limited thereto. Figure 2 As shown, the knowledge ontology construction apparatus may include the following operations: S301, Data Acquisition Module, used to acquire data information from the multi-source information service field; the multi-source information service field data information includes geographical research results, geopolitical analysis reports, and environmental survey data; S302, Knowledge ontology construction module, used to process the multi-source information service domain data information to obtain the information service domain knowledge ontology; S303, Ontology Quality Evaluation Module, used to evaluate the ontology quality of the knowledge ontology in the information service domain and obtain the ontology quality evaluation result; S304, Ontology optimization module, used to optimize the information service domain knowledge ontology based on the ontology quality evaluation results, to obtain an optimized information service domain knowledge ontology.

[0050] Example 3 Please see Figure 3 , Figure 3 This is a schematic diagram of another knowledge ontology construction device disclosed in an embodiment of the present invention. Figure 3 The described knowledge ontology construction device is in the field of artificial intelligence technology, and the embodiments of this invention are not limited thereto. Figure 3 As shown, the knowledge ontology construction apparatus may include the following operations: Memory 401 storing executable program code; Processor 402 coupled to memory 401; The processor 402 calls the executable program code stored in the memory 401 to execute the steps in the knowledge ontology construction method described in Embodiment 1.

[0051] Example 4 This invention discloses a computer-readable storage medium storing a computer program for electronic data interchange, wherein the computer program enables a computer to perform the steps in the knowledge ontology construction method described in Embodiment 1.

[0052] The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0053] Through the detailed description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, including read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0054] Finally, it should be noted that the knowledge ontology construction method and apparatus disclosed in the embodiments of the present invention are merely preferred embodiments of the present invention and are only used to illustrate the technical solutions of the present invention, not to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for constructing a knowledge ontology, characterized in that, The method includes: S1, acquire multi-source information service domain data information; the multi-source information service domain data information includes geographical research results, geopolitical analysis reports and environmental survey data; S2, process the multi-source information service domain data information to obtain the information service domain knowledge ontology; S3, perform ontology quality evaluation on the knowledge ontology of the information service domain to obtain ontology quality evaluation results; S4. Based on the ontology quality evaluation results, optimize the information service domain knowledge ontology to obtain an optimized information service domain knowledge ontology.

2. The knowledge ontology construction method according to claim 1, characterized in that, The process of processing the multi-source information service domain data information to obtain the information service domain knowledge ontology includes: S21, preprocess the multi-source information service domain data information to obtain preprocessed information service domain data information; S22, Process the preprocessed information service domain data information to obtain an ontology concept model; S23, Process the ontology concept model to obtain the knowledge system of the information service domain; S24, process the knowledge system of the information service domain to obtain the knowledge ontology of the information service domain; the knowledge ontology of the information service domain includes fact-based knowledge ontology, rule-based knowledge ontology and decision-based knowledge ontology.

3. The knowledge ontology construction method according to claim 2, characterized in that, The preprocessing of the multi-source information service domain data information to obtain preprocessed information service domain data information includes: S211, perform data cleaning on the multi-source information service domain data information to obtain cleaned data information; S212, perform semantic annotation and knowledge extraction on the cleaned data information to obtain core knowledge element information; S213, perform data association and fusion on the core knowledge element information to obtain preprocessed information service domain data information.

4. The knowledge ontology construction method according to claim 3, characterized in that, The step of cleaning the data information in the multi-source information service domain to obtain cleaned data information includes: S2111, Process the missing values ​​of the data information in the multi-source information service domain to obtain the first preprocessed data information; S2112, perform outlier processing on the first preprocessed data information to obtain the second preprocessed data information; S2113, perform redundant data processing on the second preprocessed data information to obtain cleaned data information.

5. The knowledge ontology construction method according to claim 3, characterized in that, The process of semantic annotation and knowledge extraction of the cleaned data information to obtain core knowledge element information includes: S2121, Perform named entity recognition on the cleaning data information to obtain entity information; S2122, perform relation extraction on the entity information to obtain entity relation information; S2123, Extract attributes from the entity information to obtain entity attribute information; S2124, The entity relationship information and the entity attribute information are integrated to obtain core knowledge element information.

6. The knowledge ontology construction method according to claim 3, characterized in that, The process of associating and fusing the core knowledge element information to obtain preprocessed information service domain data information includes: S2131, Perform entity alignment on the core knowledge element information to obtain structured entity element information; S2132, Process the structured entity element information to obtain entity relationship attribute graph structure data; S2133, perform spatiotemporal correlation on the entity relationship attribute graph structure data to obtain preprocessed information service domain data information.

7. The knowledge ontology construction method according to claim 2, characterized in that, The process of processing the knowledge system of the information service domain to obtain the knowledge ontology of the information service domain includes: S241, the knowledge system of the information service domain is decomposed to obtain factual knowledge, rule-based knowledge, and decision-based knowledge; the factual knowledge includes information environment knowledge, socio-cultural environment knowledge, natural environment knowledge, general spatiotemporal knowledge, and entity element knowledge; S242, Process the factual knowledge to obtain the factual knowledge ontology; S243, Process the rule-based knowledge to obtain the rule-based knowledge ontology; S244, Process the decision-type knowledge to obtain the decision-type knowledge ontology; S245, integrate the factual knowledge ontology, the rule-based knowledge ontology, and the decision-based knowledge ontology to obtain the information service domain knowledge ontology.

8. A knowledge ontology construction device, characterized in that, The device includes: The data acquisition module is used to acquire data information from the multi-source information service field; the multi-source information service field data information includes geographical research results, geopolitical analysis reports, and environmental survey data; The knowledge ontology construction module is used to process the data information of the multi-source information service domain to obtain the knowledge ontology of the information service domain; The ontology quality evaluation module is used to evaluate the ontology quality of the knowledge ontology in the information service domain and obtain the ontology quality evaluation result. The ontology optimization module is used to optimize the information service domain knowledge ontology based on the ontology quality evaluation results, so as to obtain an optimized information service domain knowledge ontology.

9. A knowledge ontology construction device, characterized in that, The device includes: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the knowledge ontology construction method as described in any one of claims 1-7.

10. A computer-storable medium, characterized in that, The computer storage medium stores computer instructions, which, when invoked, are used to execute the knowledge ontology construction method as described in any one of claims 1-7.

Images