A dynamic ontology automatic discovery and generation method based on service semantic alignment
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- BEIJING HAIZHI TECH GRP CO LTD
- Filing Date
- 2026-03-02
- Publication Date
- 2026-07-10
Smart Images
Figure CN122364983A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the fields of artificial intelligence and knowledge engineering, and in particular to a method for automatic discovery and generation of dynamic ontology based on business semantic alignment. Background Technology
[0002] With the deepening of digital transformation, enterprise business systems are becoming increasingly complex, data sources are diversifying, and business rules are frequently changing, posing serious challenges to traditional data modeling and knowledge management methods. Ontologies, as an important tool for knowledge representation and sharing, play a crucial role in knowledge graphs, intelligent question answering, and data governance. However, traditional ontology construction methods mainly rely on manual construction by domain experts, resulting in long construction cycles, high maintenance costs, and difficulty in adapting to rapid business changes. Especially in scenarios such as urban governance and enterprise digital transformation, business models are constantly evolving, and data sources are continuously expanding. Traditional static ontology models cannot reflect business changes in a timely manner, leading to a disconnect between the knowledge system and actual business operations, affecting decision-making quality and the level of system intelligence.
[0003] At the business semantic level, different systems often define the same business concept differently, leading to semantic fragmentation. For example, different systems may define the violating entity differently; System A uses Enterprise ID + Violation Type, while System B uses Responsible Unit Name + Case Number. This semantic inconsistency causes data association failures and distorted analysis results. Even unifying field names through master data management tools cannot resolve ambiguities at the business logic level.
[0004] Existing ontology construction and management technologies mainly focus on three aspects: (1) Rule-based and template-based methods (such as the Protégé tool) assist experts in constructing ontology through predefined rules, but still require manual definition of entities, attributes and relationships, resulting in low automation.
[0005] (2) Machine learning-based automatic extraction methods (such as named entity recognition and relation extraction) focus on extracting information from data, but lack semantic alignment mechanisms with existing ontologies, which can easily lead to semantic conflicts.
[0006] (3) Ontology version management and evolution methods focus on version control and conflict detection, but cannot automatically discover and generate new ontologies, relying on manual intervention.
[0007] These methods generally suffer from the following drawbacks: lack of end-to-end automation, insufficient semantic consistency verification, slow response speed, and inability to adapt to rapid changes in the business environment. In particular, while methods based on predefined ontology models can solve the problem of multi-source data integration, they fail to address the core challenge of how the ontology should automatically evolve with business needs, instead reinforcing the reliance on manual predefinition. Therefore, there is an urgent need for an AI-driven dynamic ontology generation method to achieve automatic discovery and evolution under business semantic alignment. Summary of the Invention
[0008] This invention provides a dynamic ontology automatic discovery and generation method based on business semantic alignment, which addresses the shortcomings of existing technologies such as lack of end-to-end automation, insufficient semantic consistency verification, and inability to automatically discover and generate new ontology. It achieves a fully automated ontology discovery and generation process, reduces manual intervention through AI technology, and improves ontology construction efficiency. Through a semantic alignment mechanism, it ensures the consistency between the new ontology and existing business semantics, thereby enhancing the accuracy and adaptability of the knowledge system.
[0009] This invention provides a method for automatic discovery and generation of dynamic ontology based on business semantic alignment, comprising the following steps.
[0010] By using preset AI technology and change detection functions, feature extraction and business pattern identification are performed on multi-source data to obtain identification results; When a change in business model is detected, similarity calculation and semantic conflict detection are performed based on existing entities and candidate entities to obtain semantic alignment results; By using pattern recognition and knowledge extraction algorithms, ontology recognition is performed based on candidate entities and semantic alignment results to obtain new ontology elements; Based on existing entities and new ontology elements, an ontology model is constructed and its consistency is verified to obtain the ontology model.
[0011] According to the present invention, a dynamic ontology automatic discovery and generation method based on business semantic alignment is provided. Through preset AI technology and change detection functions, feature extraction and business pattern identification are performed on multi-source data to obtain identification results, including: By using pre-set AI technology, feature extraction is performed on multi-source data to obtain data features; these data features include historical data features and current data features. By using a change detection function, changes in business models are identified based on historical and current data characteristics, and the identification results are obtained.
[0012] According to the present invention, a dynamic ontology automatic discovery and generation method based on business semantic alignment is provided. The data features are entity features and / or semantic features. The multi-source data includes structured data and unstructured documents. Through preset AI technology, feature extraction is performed on the multi-source data to obtain data features, including: By using pre-set AI technology, multi-dimensional feature extraction is performed on structured data to obtain entity features; Natural language processing techniques are used to extract semantic features from unstructured documents across multiple dimensions, resulting in semantic features.
[0013] According to the present invention, a dynamic ontology automatic discovery and generation method based on business semantic alignment is provided, which calculates similarity and detects semantic conflicts based on existing entities and candidate entities to obtain semantic alignment results, including: The first similarity value is obtained by calculating name similarity, context similarity, and structural similarity based on existing entities and candidate entities; Using semantic representation functions, semantic computation is performed on existing entities and candidate entities respectively to obtain existing semantic values and candidate semantic values; The semantic conflict detection function performs conflict detection based on the first similarity value, the existing semantic value, and the candidate semantic value, and obtains the semantic alignment result.
[0014] According to the present invention, a dynamic ontology automatic discovery and generation method based on business semantic alignment is provided. The new ontology elements include new entities and new relations. Through pattern recognition and knowledge extraction algorithms, ontology identification is performed based on candidate entities and semantic alignment results to obtain the new ontology elements. The method includes: If a candidate entity is determined to be a new entity by using an entity recognition function, and the semantic alignment result is greater than a preset confidence threshold, then the candidate entity is identified as a new entity. By using a relation identification function, it is determined that the relationship between the first entity and the second entity does not belong to the existing relation set, and the support of the relationship between the first entity and the second entity is greater than a preset support threshold, thus obtaining a new relation.
[0015] According to the present invention, a dynamic ontology automatic discovery and generation method based on business semantic alignment is provided, which constructs and verifies the consistency of an ontology model based on existing entities and new ontology elements to obtain an ontology model, including: Based on the new entities and new relationships, an ontology model is constructed to obtain candidate entity models; The candidate entity model is logically checked using the ontology consistency check function to obtain the logical check results. The semantic conflict detection function is used to detect conflicts based on the candidate ontology model and existing entities, and the conflict detection value is obtained. The semantic consistency check function is used to determine the consistency result based on the logical check results and conflict detection values. Based on the consistency results, the candidate ontology models that pass the verification are determined as ontology models.
[0016] The present invention also provides a dynamic ontology automatic discovery and generation device based on business semantic alignment, comprising: The change detection module is used to extract features and identify business patterns from multi-source data using preset AI technology and change detection functions to obtain the identification results. The semantic alignment module is used to calculate similarity and detect semantic conflicts based on existing entities and candidate entities when a change in business pattern is detected, so as to obtain semantic alignment results. The new ontology element generation module is used to perform ontology recognition based on candidate entities and semantic alignment results through pattern recognition and knowledge extraction algorithms to obtain new ontology elements. The model generation module is used to construct and verify the consistency of the ontology model based on existing entities and new ontology elements, thereby obtaining the ontology model.
[0017] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the dynamic ontology automatic discovery and generation method based on business semantic alignment as described above.
[0018] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the dynamic ontology automatic discovery and generation method based on business semantic alignment as described above.
[0019] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the dynamic ontology automatic discovery and generation method based on business semantic alignment as described above.
[0020] This invention provides a dynamic ontology automatic discovery and generation method based on business semantic alignment. It extracts features and identifies business patterns from multi-source data using pre-set AI technology and change detection functions to obtain identification results. When a change in business pattern is detected, it calculates similarity and detects semantic conflicts between existing and candidate entities to obtain semantic alignment results. Through pattern recognition and knowledge extraction algorithms, it performs ontology identification based on candidate entities and semantic alignment results to obtain new ontology elements. Based on existing entities and new ontology elements, it constructs and verifies the consistency of the ontology model to obtain the ontology model. This achieves a fully automated ontology discovery and generation process, reducing manual intervention and improving ontology construction efficiency through AI technology. The semantic alignment mechanism ensures the consistency between the new ontology and existing business semantics, enhancing the accuracy and adaptability of the knowledge system. Attached Figure Description
[0021] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.
[0022] Figure 1 This is one of the flowcharts of the dynamic ontology automatic discovery and generation method based on business semantic alignment provided by the present invention.
[0023] Figure 2 This is the second flowchart of the dynamic ontology automatic discovery and generation method based on business semantic alignment provided by the present invention.
[0024] Figure 3 This is a schematic diagram of the business semantic alignment process provided by the present invention.
[0025] Figure 4 This is a schematic diagram of the process for dynamic generation and updating of the ontology provided by the present invention.
[0026] Figure 5 This is a schematic diagram of the structure of the dynamic ontology automatic discovery and generation device based on business semantic alignment provided by the present invention.
[0027] Figure 6 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation
[0028] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.
[0029] The following is combined Figures 1 to 6 This invention is described.
[0030] Figure 1 This is one of the flowcharts illustrating the dynamic ontology automatic discovery and generation method based on business semantic alignment provided by the present invention, such as... Figure 1 As shown, the method includes the following: Step 101: Using preset AI technology and change detection functions, feature extraction and business pattern identification are performed on multi-source data to obtain identification results.
[0031] In step 101 above, this invention designs an AI-driven dynamic ontology automatic discovery and generation method and system based on business semantic alignment. It automatically identifies changes in business patterns in business data and documents using AI technology, performs business semantic alignment analysis with existing ontologies, automatically discovers new ontology elements, generates and verifies new ontology models, and updates the ontology knowledge base. Based on traditional ontology construction methods, this invention introduces an AI-driven automatic discovery mechanism and a business semantic alignment engine. It can automatically identify changes in business patterns after changes in business data or documents, and combined with semantic alignment analysis, achieves high accuracy and consistency in the ontology generation method. Simultaneously, semantic consistency verification ensures that the newly generated ontology does not conflict with existing ontologies, improving the information integrity and business adaptability of the ontology knowledge base.
[0032] Ontology: In computer science and information science, an ontology is a formalized representation of knowledge used to describe concepts, entities, and their relationships within a domain. An ontology consists of three elements: entities, relationships, and attributes, which together form a cohesive whole.
[0033] Ontologies, as a core tool for knowledge representation, play a crucial role in fields such as knowledge graphs, intelligent question answering, and data governance. By mining hidden information in business data and documents, they can assist in building and updating ontology models, supporting various intelligent applications. With the deepening of business digital transformation, the dynamic updating and continuous evolution of ontology models are of great significance. This invention enables the automatic generation of ontology in complex and ever-changing business environments, and ensures consistency between the new ontology and existing ontology through a business semantic alignment algorithm. This provides a more accurate and complete ontology knowledge base for other downstream related businesses, such as knowledge graph construction, intelligent question answering, and data governance.
[0034] like Figure 2 As shown, the present invention mainly includes: extracting business pattern features from business data and documents; performing semantic alignment analysis with existing ontology; automatically discovering new ontology elements; generating and validating new ontology models; and updating the ontology knowledge base.
[0035] Optionally, step 101 includes steps A1 to A2: Step A1: Using preset AI technology, feature extraction is performed on multi-source data to obtain data features; among which, data features include historical data features and current data features.
[0036] Step A2: Using a change detection function, identify changes in the business model based on historical and current data characteristics to obtain the identification results.
[0037] Optionally, the data features are entity features and / or semantic features, and the multi-source data includes structured data and unstructured documents. Step A1 includes steps A11 to A12: Step A11: Using preset AI technology, extract features from structured data across multiple dimensions to obtain entity features; Step A12: Using natural language processing techniques, extract semantic features from unstructured documents across multiple dimensions to obtain semantic features.
[0038] In steps A1 to A2 above, business data and documents contain rich business semantic information. Fusion analysis of multi-source data can more effectively utilize the knowledge within the business system. This step first employs AI technology to extract features from business data and documents, identifying changes in business patterns. Assuming a given set of business data... D , including N Data sources and M After preprocessing and feature extraction of each document, a feature matrix is constructed. F .
[0039] For structured data, extract features such as entities, attributes, and relationships. This is done within a specific data source. D_i In the context of entity feature vectors E_i It can be represented as: ; in k Represents the dimension of entity features. e_{ij} represents the first... j eigenvalues.
[0040] For unstructured documents, natural language processing techniques are used to extract semantic features such as business concepts, relationships, and constraints. D_j semantic feature vector S_j It can be represented as: ; Where l represents the semantic feature dimension. s_{jk} represents the first jk. k semantic feature values.
[0041] Changes in business models are identified by comparing historical and current data. (Change detection function) Δ It can be defined as: ; in f For change detection algorithms, *E_{current} and E_{historical}* represents the current and historical entity features respectively, and *S_{current} and S_{historical}* represents the current and historical semantic features, respectively.
[0042] Step 102: When a change in business model is detected, similarity calculation and semantic conflict detection are performed based on existing entities and candidate entities to obtain semantic alignment results.
[0043] In step 102 above, after identifying changes in the business model, semantic alignment analysis needs to be performed with the existing ontology to ensure that the newly discovered ontology elements are semantically consistent with the existing ontology. This step uses semantic similarity calculation and semantic conflict detection methods for semantic alignment.
[0044] Optionally, step 102 includes steps B1 to B3: Step B1: Calculate name similarity, context similarity, and structural similarity based on existing entities and candidate entities to obtain the first similarity value.
[0045] Step B2: Using the semantic representation function, perform semantic calculations on the existing entities and candidate entities respectively to obtain the existing semantic values and candidate semantic values.
[0046] Step B3: Using the semantic conflict detection function, conflict detection is performed based on the first similarity value, the existing semantic value, and the candidate semantic value to obtain the semantic alignment result.
[0047] In steps B1 to B3 above, Figure 3 This is a schematic diagram of the business semantic alignment process provided by the present invention. Assuming an existing ontology... O Contains entity collection E_O Attribute set A_O and relation set R_O Newly discovered candidate entities e_{new} and present Physical e_{existing} semantic similarity Sim can be calculated as: ; Where *Sim_{name}* represents name similarity, and *Sim_{context}* represents context similarity. Sim_ {structure} represents structural similarity, α , β , γ α is the weighting coefficient, and α + β + γ = 1.
[0048] Semantic conflict detection function Conflict Defined as: .
[0049] Sem stands for Semantic Representation Function, which is used to map features such as entities, attributes, and relationships to a semantic space for representation and comparison, such as semantic representation using word embedding or knowledge graph embedding techniques.
[0050] Step 103: Using pattern recognition and knowledge extraction algorithms, perform ontology recognition based on candidate entities and semantic alignment results to obtain new ontology elements.
[0051] Optionally, the new ontology elements include new entities and new relationships; step 103 includes steps C1 to C3: Step C1: If the entity recognition function determines that the candidate entity does not belong to the existing entity set and the semantic alignment result is greater than the preset confidence threshold, then the candidate entity is identified as a new entity.
[0052] Step C2: Using the relation recognition function, determine that the relationship between the first entity and the second entity does not belong to the existing relation set, and that the support of the relationship between the first entity and the second entity is greater than the preset support threshold, thus obtaining a new relation.
[0053] Step 104: Based on existing entities and new ontology elements, construct and verify the ontology model to obtain the ontology model.
[0054] Optionally, step 104 includes steps D1 to D5: Step D1: Construct an ontology model based on the new entities and new relationships to obtain candidate ontology models.
[0055] Step D2: Perform a logical check on the candidate ontology model using the ontology consistency check function to obtain the logical check result.
[0056] Step D3: Using the semantic conflict detection function, perform conflict detection based on the candidate ontology model and existing entities to obtain conflict detection values.
[0057] Step D4: Using the semantic consistency check function, a consistency result is obtained by judging based on the logical check results and conflict detection values.
[0058] Step D5: Based on the consistency results, the candidate ontology models that pass the verification are determined as ontology models.
[0059] In steps 103 and 104 above, Figure 4 This is a schematic diagram illustrating the process of dynamic generation and updating of the ontology provided by the present invention. For example... Figure 4 As shown, based on the extracted business pattern features and semantic alignment analysis results, new ontology elements, including entities, attributes, and relationships, are automatically discovered. This step employs pattern recognition and knowledge extraction algorithms to identify new ontology elements from business changes. Unlike methods that rely on predefined ontology models, this step does not require pre-constructing a complete ontology structure. Instead, it uses an AI-driven automatic discovery mechanism to directly identify new ontology elements from business changes, achieving dynamic generation and evolution of the ontology.
[0060] For new entity discovery, the entity recognition function DiscoverEntity Defined as: ; in Confidence Represents the entity confidence function. θ_2 This is the confidence threshold.
[0061] For new relation discovery, the relation identification function DiscoverRelation Defined as: ; in, Support Represents the relation support function. θ_3 For the support threshold, r(e_1, e_2) represents First entity e_1 and second entity e_2 The relationship between them.
[0062] Based on the discovered new ontology elements, a new ontology model is generated and semantic consistency is verified. This step first constructs a candidate ontology model and then verifies it.
[0063] The candidate ontology model *O_{candidate}* can be represented as: ; Where *O_{existing}* represents the existing ontology. E_{new} , A_{new} , and *R_{new}* represent the newly discovered sets of entities, attributes, and relations, respectively.
[0064] Semantic consistency check function Validate Defined as: ; in Consistency This represents the ontology consistency check function, which checks whether the ontology model is logically consistent.
[0065] The validated new ontology model is updated in the ontology knowledge base, completing the dynamic evolution of the ontology. Update function Update Defined as: ; Where *O_{knowledgebase}* represents the existing ontology knowledge base, and *O_{valid}* represents the new ontology model that has passed validation.
[0066] Version information is recorded during the update process, supporting version tracking and rollback. Version number V It can be represented as: ; Through the above steps, automatic identification of business changes, automatic discovery of new ontology elements, semantic alignment and consistency verification, and dynamic updates of the ontology knowledge base can be achieved, enabling continuous evolution of the ontology and dynamic adaptation of the knowledge system. Compared with existing technologies, this invention, by introducing an AI-driven automatic discovery mechanism and a business semantic alignment engine, creatively proposes an end-to-end dynamic ontology generation process. This process allows the ontology model to automatically evolve with business changes without relying on manually predefined models, solving the problems of traditional methods that rely on manual intervention, have long cycles, high maintenance costs, and cannot automatically adapt to rapid business changes. This demonstrates significant progress and innovation.
[0067] The core of this invention lies in its ability to dynamically evolve the ontology without relying on manually predefined ontology models, through an end-to-end automated process. Specifically, this invention uses AI technology to automatically extract business pattern features from multi-source business data and documents, identify business changes, perform semantic alignment analysis with existing ontologies, automatically discover new entities, attributes, relationships, and other ontology elements, generate candidate ontology models, and perform semantic consistency verification. Finally, the verified new ontology models are updated to the ontology knowledge base, achieving continuous and automatic evolution of the ontology. This technical approach differs fundamentally from predefined ontology methods, automatically adapting to rapid business changes without requiring manual redesign and adjustment of predefined models, significantly reducing maintenance costs and improving response speed.
[0068] This invention provides a dynamic ontology automatic discovery and generation method based on business semantic alignment. It extracts features and identifies business patterns from multi-source data using pre-set AI technology and change detection functions to obtain identification results. When a change in business pattern is detected, it calculates similarity and detects semantic conflicts between existing and candidate entities to obtain semantic alignment results. Using pattern recognition and knowledge extraction algorithms, it identifies new ontology elements based on candidate ontologies and semantic alignment results. Based on existing entities and new ontology elements, it constructs and verifies the consistency of the ontology model to obtain the ontology model. This achieves a fully automated ontology discovery and generation process, reducing manual intervention and improving ontology construction efficiency through AI technology. The semantic alignment mechanism ensures consistency between the new ontology and existing business semantics, enhancing the accuracy and adaptability of the knowledge system.
[0069] The following describes the dynamic ontology automatic discovery and generation apparatus based on business semantic alignment provided by the present invention. The dynamic ontology automatic discovery and generation apparatus based on business semantic alignment described below and the dynamic ontology automatic discovery and generation method based on business semantic alignment described above can be referred to in correspondence.
[0070] Figure 5 This is a flowchart illustrating the dynamic ontology automatic discovery and generation device based on business semantic alignment provided by the present invention, as shown below. Figure 5 As shown, the device includes the following: The change detection module 501 is used to extract features and identify business patterns from multi-source data through preset AI technology and change detection functions to obtain the identification results.
[0071] The semantic alignment module 502 is used to perform similarity calculation and semantic conflict detection based on existing entities and candidate entities when a change in business mode is detected, so as to obtain semantic alignment results.
[0072] The new ontology element generation module 503 is used to perform ontology recognition based on candidate entities and semantic alignment results through pattern recognition and knowledge extraction algorithms to obtain new ontology elements.
[0073] The model generation module 504 is used to construct and verify the consistency of the ontology model based on the existing entities and the new ontology elements, so as to obtain the ontology model.
[0074] This invention provides a dynamic ontology automatic discovery and generation device based on business semantic alignment. Through preset AI technology and change detection functions, it extracts features from multi-source data and identifies business patterns to obtain recognition results. When a change in business pattern is detected, it calculates similarity and detects semantic conflicts between existing entities and candidate entities to obtain semantic alignment results. Using pattern recognition and knowledge extraction algorithms, it performs ontology recognition based on candidate entities and semantic alignment results to obtain new ontology elements. Based on existing entities and new ontology elements, it constructs an ontology model and performs consistency verification to obtain an ontology model. This achieves a fully automated ontology discovery and generation process, reducing manual intervention and improving ontology construction efficiency through AI technology. The semantic alignment mechanism ensures consistency between the new ontology and existing business semantics, enhancing the accuracy and adaptability of the knowledge system.
[0075] Figure 6 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 6 As shown, the electronic device may include a processor 810, a communications interface 820, a memory 830, and a communication bus 840. The processor 810, communications interface 820, and memory 830 communicate with each other via the communication bus 840. The processor 810 can invoke logical instructions from the memory 830 to execute a dynamic ontology auto-discovery and generation method based on business semantic alignment.
[0076] Furthermore, the logical instructions in the aforementioned memory 830 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0077] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to execute the dynamic ontology automatic discovery and generation method based on business semantic alignment provided by the above methods.
[0078] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the dynamic ontology automatic discovery and generation method based on business semantic alignment provided by the above methods.
[0079] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. 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.
[0080] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment 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, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.
[0081] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; 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; and these 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 automatic discovery and generation of dynamic ontology based on business semantic alignment, characterized in that, include: By using preset AI technology and change detection functions, feature extraction and business pattern identification are performed on multi-source data to obtain identification results; When a change in business model is detected, similarity calculation and semantic conflict detection are performed based on existing entities and candidate entities to obtain semantic alignment results; New ontology elements are obtained by performing ontology recognition based on the candidate entities and the semantic alignment results using pattern recognition and knowledge extraction algorithms. Based on the existing entities and the new ontology elements, an ontology model is constructed and its consistency is verified to obtain the ontology model.
2. The method for automatic discovery and generation of dynamic ontology based on business semantic alignment according to claim 1, characterized in that, The process involves using preset AI technology and change detection functions to extract features from multi-source data and identify business patterns, resulting in the following identification results: By using pre-set AI technology, feature extraction is performed on multi-source data to obtain data features; wherein, the data features include historical data features and current data features; The change detection function identifies changes in the business model based on the historical data features and the current data features, and obtains the identification results.
3. The method for automatic discovery and generation of dynamic ontology based on business semantic alignment according to claim 2, characterized in that, The data features are entity features and / or semantic features, the multi-source data includes structured data and unstructured documents, and the data features are obtained by extracting features from the multi-source data using preset AI technology, including: By using pre-set AI technology, multi-dimensional feature extraction is performed on structured data to obtain entity features; Natural language processing techniques are used to extract semantic features from unstructured documents across multiple dimensions, resulting in semantic features.
4. The method for automatic discovery and generation of dynamic ontology based on business semantic alignment according to claim 1, characterized in that, The step of calculating similarity and detecting semantic conflicts based on existing entities and candidate entities to obtain semantic alignment results includes: The first similarity value is obtained by calculating name similarity, context similarity, and structural similarity based on existing entities and candidate entities; Using semantic representation functions, semantic computation is performed on existing entities and candidate entities respectively to obtain existing semantic values and candidate semantic values; The semantic conflict detection function is used to perform conflict detection based on the first similarity value, the existing semantic value, and the candidate semantic value to obtain the semantic alignment result.
5. The method for automatic discovery and generation of dynamic ontology based on business semantic alignment according to claim 1, characterized in that, The new ontology elements include new entities and new relations; the process of obtaining new ontology elements by performing ontology recognition based on the candidate entities and the semantic alignment results using pattern recognition and knowledge extraction algorithms includes: If the candidate entity is determined to be a new entity by means of an entity recognition function, and the semantic alignment result is greater than a preset confidence threshold, the candidate entity is identified as a new entity. By using a relation identification function, it is determined that the relationship between the first entity and the second entity does not belong to the existing relation set, and the support of the relationship between the first entity and the second entity is greater than a preset support threshold, thus obtaining a new relation.
6. The method for automatic discovery and generation of dynamic ontology based on business semantic alignment according to claim 5, characterized in that, The step of constructing and verifying the ontology model based on existing entities and the new ontology elements to obtain the ontology model includes: Based on the new entity and the new relationship, an ontology model is constructed to obtain a candidate ontology model; The candidate ontology model is logically checked using an ontology consistency check function to obtain the logical check result. The semantic conflict detection function is used to perform conflict detection based on the candidate ontology model and the existing entities to obtain conflict detection values. The consistency result is obtained by using the semantic consistency verification function to judge based on the logical check result and the conflict detection value; Based on the consistency results, the candidate ontology models that pass the verification are determined as ontology models.
7. A dynamic ontology automatic discovery and generation device based on business semantic alignment, characterized in that, include: The change detection module is used to extract features and identify business patterns from multi-source data using preset AI technology and change detection functions to obtain the identification results. The semantic alignment module is used to calculate similarity and detect semantic conflicts based on existing entities and candidate entities when a change in business pattern is detected, so as to obtain semantic alignment results. The new ontology element generation module is used to perform ontology recognition based on the candidate entities and the semantic alignment results through pattern recognition and knowledge extraction algorithms to obtain new ontology elements. The model generation module is used to construct and verify the consistency of the ontology model based on the existing entities and the new ontology elements, thereby obtaining the ontology model.
8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the dynamic ontology automatic discovery and generation method based on business semantic alignment as described in any one of claims 1 to 6.
9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the dynamic ontology automatic discovery and generation method based on business semantic alignment as described in any one of claims 1 to 6.
10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the dynamic ontology automatic discovery and generation method based on business semantic alignment as described in any one of claims 1 to 6.