A method, system, device, and storage medium for triggering dynamic ontology evolution based on the intensity of semantic change.
By constructing a dynamic ontology model and calculating the intensity of semantic changes, the problem of unreasonable ontology updates in earthquake disaster scenarios is solved, achieving accurate ontology optimization and efficient data processing.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHONGQING UNIV
- Filing Date
- 2026-04-05
- Publication Date
- 2026-06-30
AI Technical Summary
Existing technologies cannot accurately capture the intensity of semantic changes in earthquake disaster scenarios, resulting in unreasonable timing and frequency of ontology updates. Furthermore, the evolution mechanism of fixed rules cannot adapt to complex and ever-changing real-world scenarios, leading to problems of over-updating or delayed updates.
By acquiring new data, a dynamic ontology model is constructed and semantically mapped. Semantic units are extracted, the weights of semantic change information are calculated, and the strengths are split into instance layer and concept layer. Optimization actions are performed based on threshold comparisons, triggering updates or evolutions at the corresponding levels.
It enables accurate updates to the ontology model, reduces false triggers and missed triggers, lowers computational resource consumption, and improves the system's operating efficiency in a continuous data input environment.
Smart Images
Figure CN122311218A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of semantic modeling technology, and in particular to a dynamic ontology evolution triggering method, system, device, and storage medium based on the intensity of semantic changes. Background Technology
[0002] Ontologies, as an important means of knowledge representation and semantic modeling, have been widely used in fields such as disaster management, intelligent decision-making, and knowledge reasoning. In earthquake disaster scenarios, ontology can provide a structured description of earthquake events, secondary disasters, affected objects, and their interrelationships, providing semantic support for disaster analysis and decision support.
[0003] With the continuous growth of earthquake disaster information, ontologies face the challenge of dynamic updating and expansion when representing and processing real-time data. To address this issue, researchers have proposed dynamic ontologies and ontology evolution methods. In existing technologies, dynamic ontology evolution triggering methods are mainly based on triggering rules, time-driven approaches, or manual intervention, but these methods mostly have certain limitations. On the one hand, existing methods cannot accurately capture the intensity of semantic changes, resulting in unreasonable timing and frequency of ontology updates; on the other hand, evolution mechanisms based on fixed rules fail to effectively adapt to complex and ever-changing real-world scenarios, often resulting in over-updating or delayed updates. Summary of the Invention
[0004] This application aims to at least solve the technical problems existing in the prior art, and to provide a method, system, device and storage medium for triggering dynamic ontology evolution based on the intensity of semantic change.
[0005] In a first aspect, the present invention provides a dynamic ontology evolution triggering method based on the intensity of semantic change, comprising: Acquire new data in the current knowledge domain; Construct a dynamic ontology model and perform semantic mapping on the new data based on the dynamic ontology model to obtain standardized semantic elements; Semantic units are extracted from standardized semantic elements to obtain semantic change information of the new data. This semantic change information is used to represent the amount of semantic change at different levels of the new data. Obtain the weights corresponding to each semantic change quantity in the semantic change information, and perform weighted calculations on each type of semantic change measure according to the preset weights to obtain the overall semantic change intensity of the new data. The overall semantic change intensity is broken down into instance layer semantic change intensity and concept layer semantic change intensity. The instance layer semantic change intensity is compared with a preset instance layer threshold, and the concept layer semantic change intensity is compared with a preset concept layer threshold to obtain the comparison results. The optimization actions for the dynamic ontology model are determined based on the comparison results; Based on the optimization actions, the concept layer evolution and / or instance layer update operations of the ontology are performed to complete the optimization of the dynamic ontology model.
[0006] Optionally, determining the optimization action instructions for the dynamic ontology model based on the comparison results includes: If the semantic change intensity of the instance layer is greater than the instance layer threshold, then the instance layer update operation is triggered; If the intensity of semantic change at the conceptual layer exceeds the conceptual layer threshold, a conceptual layer evolution operation is triggered.
[0007] Optionally, semantic change information includes instance change measures, attribute change measures, relation change measures, and concept change measures.
[0008] Optionally, the calculation steps for the instance change metric include: Calculate the semantic similarity between the newly added instance in the newly added data and each instance in the existing instance set to obtain a semantic similarity set, wherein the semantic similarity is a weighted sum of attribute similarity and relation similarity; If the maximum semantic similarity in the semantic similarity set is less than the instance change threshold, then the newly added instance is determined to be a new instance; The number of all new instances is counted, and the ratio of this count to the total number of new instances is used as a measure of instance change.
[0009] Optionally, the calculation steps for the attribute change measure include: Attributes are categorized into numerical attributes and discrete attributes; The ratio of the number of numerical attributes that have changed significantly to the total number of numerical attributes is used as a measure of change in numerical attributes. Numerical attributes whose relative change exceeds a preset threshold are considered to be significant change attributes. The ratio of the number of discrete attributes that have changed to the total number of discrete attributes is used as a measure of the change in discrete attributes. The attribute change measure is obtained by weighted summation of the numerical attribute change measure and the discrete attribute change measure.
[0010] Optionally, the calculation steps for the relational change measure include: Obtain the set of relations of the ontology before evolution, and the set of relations obtained by mapping the new data; Calculate the sum of the number of newly added relation types and the number of disappeared relation types; The ratio of the sum of the number of newly added relation types and the number of disappeared relation types to the total number of relation types in the ontology before evolution is used as the measure of relation change.
[0011] Optionally, the calculation steps for the concept change measure include: Calculate the similarity between the newly added semantic unit and each existing concept in the ontology, where the similarity is a weighted sum of word similarity and attribute similarity; Obtain the maximum value among the similarities; If the maximum value is less than the concept coverage threshold, then the newly added semantic unit is determined to represent a new concept; The number of all new concepts is counted, and the ratio of this count to the total number of newly added semantic units is used as a measure of the change in the concept.
[0012] Secondly, the present invention provides a dynamic ontology evolution triggering system based on the intensity of semantic change, the system comprising: The acquisition module is used to acquire new data in the current knowledge domain; The semantic mapping module is used to construct a dynamic ontology model and perform semantic mapping on new data based on the dynamic ontology model to obtain standardized semantic elements. The semantic unit extraction module is used to extract semantic units from standardized semantic elements to obtain semantic change information of the new data. The semantic change information is used to represent the amount of semantic change at different levels of the new data. The semantic change intensity calculation module is used to obtain the weights corresponding to each semantic change quantity in the semantic change information, and to perform weighted calculations on each type of semantic change measure according to preset weights to obtain the overall semantic change intensity of the new data. The comparison module is used to break down the overall semantic change intensity into instance layer semantic change intensity and concept layer semantic change intensity, compare the instance layer semantic change intensity with a preset instance layer threshold, and compare the concept layer semantic change intensity with a preset concept layer threshold to obtain the comparison results. The first processing module is used to determine the optimization actions for the dynamic ontology model based on the comparison results. The second processing module is used to perform concept layer evolution and / or instance layer update operations on the ontology based on the optimization actions, thereby completing the optimization of the dynamic ontology model.
[0013] Thirdly, the present invention provides an electronic device, the electronic device comprising: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to execute the dynamic ontology evolution triggering method based on semantic change intensity described above.
[0014] Fourthly, the present invention also provides a computer-readable storage medium storing at least one computer program, which is executed by a processor in an electronic device to implement the above-described dynamic ontology evolution triggering method based on semantic change intensity.
[0015] In summary, this application includes the following beneficial technical effects: This application extracts semantic change information at different levels from new data and calculates the overall semantic change intensity by weighting it. Compared with traditional fixed rules or time-driven triggering methods, it can more accurately reflect the actual impact of data changes on the ontology model and effectively reduce false triggering and missed triggering. By decomposing the overall intensity into instance layer and concept layer intensity and comparing them with preset thresholds respectively, it can perform instance layer updates or trigger concept layer evolution only according to the essential level of change, thereby avoiding high-cost structural reconstruction, significantly reducing computing resource consumption and improving the system's operating efficiency in a continuous data input environment. Attached Figure Description
[0016] Figure 1 This is a flowchart illustrating a dynamic ontology evolution triggering method based on semantic change intensity, provided in an embodiment of the present invention. Figure 2 This is a schematic diagram illustrating the evolution triggering decision of the concept layer and instance layer according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the semantic change intensity calculation model provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of the structure of an electronic device that implements the dynamic ontology evolution triggering method based on semantic change intensity, according to an embodiment of the present invention.
[0017] Reference numerals: 10, processor; 11, memory; 12, communication bus; 13, communication interface.
[0018] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation
[0019] Embodiments of the present invention are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.
[0020] In the description of this invention, it should be understood that the terms "longitudinal", "lateral", "up", "down", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.
[0021] In the description of this invention, unless otherwise specified and limited, it should be noted that the terms "installation", "connection" and "linking" should be interpreted broadly. For example, they can refer to mechanical or electrical connections, or internal connections between two components. They can be direct connections or indirect connections through an intermediate medium. Those skilled in the art can understand the specific meaning of the above terms according to the specific circumstances.
[0022] Reference Figure 1 The diagram shown is a flowchart illustrating a dynamic ontology evolution triggering method based on semantic change intensity according to an embodiment of the present invention. In this embodiment, the dynamic ontology evolution triggering method based on semantic change intensity includes: S1. Obtain new data in the current knowledge domain.
[0023] Specifically, new data in the current knowledge domain is obtained from external data sources, which may come from different sensors, online data streams, or external databases.
[0024] In this embodiment, the current knowledge domain is the earthquake disaster domain, and the newly added data in the current knowledge domain is the newly added data in the earthquake disaster domain. New data in the earthquake disaster domain is obtained from external data sources, including but not limited to earthquake network data, disaster reports issued by emergency management departments, official news, and social media. The newly added data includes the earthquake's occurrence time, magnitude, epicenter location, affected area, casualties, building damage, and information on potential secondary disasters such as landslides and mudslides.
[0025] S2. Construct a dynamic ontology model and perform semantic mapping on the newly added data based on the dynamic ontology model to obtain standardized semantic elements.
[0026] Dynamic ontology models are knowledge representations that introduce a time dimension and adaptive evolution capabilities on the basis of traditional static ontology. They can continuously receive new data and automatically determine and trigger lightweight updates at the instance layer or structural evolution at the concept layer by quantifying the semantic change intensity at four levels: instance, attribute, relation, and concept. This ensures that the ontology always remains consistent with the dynamically changing domain knowledge. In rapidly changing scenarios such as earthquake disasters, this model achieves adaptive and intelligent knowledge management, avoiding frequent manual intervention.
[0027] Preliminary semantic analysis and feature identification are performed on these new data, mapping the key entities, attributes, and relationships in the new data to standardized concept instances in the constructed earthquake disaster dynamic ontology model.
[0028] Preliminary semantic analysis and feature identification are performed on this new data, and then semantic mapping is performed on it using a pre-built dynamic ontology model. The purpose of semantic mapping is to transform the key elements in the new data into standardized concepts, relationships, and attributes in the dynamic ontology model, so as to ensure that the new data is compatible with the existing ontology structure.
[0029] S3. Extract semantic units from standardized semantic elements to obtain semantic change information of newly added data.
[0030] Semantic change information is used to represent the amount of semantic change at different levels in the newly added data. Semantic units are extracted from the newly added data to obtain semantic units such as instances, attributes, relationships, and potential new concepts. Semantic changes at different levels refer to: Instance Change: Indicates a new event or instance that does not overlap with or resemble an existing instance; Attribute change: Indicates that the attribute values of the newly added data instances have changed significantly; Changes in relationships: This indicates that new data has introduced new conceptual associations or eliminated relationships that are no longer applicable, resulting in a change in the semantic relationship structure; Concept change: This indicates that new data has been added, introducing new concepts that were not previously covered in the dynamic ontology model, or that the concept layer structure has changed.
[0031] In this embodiment, semantic change information includes instance change measure, attribute change measure, relation change measure, and concept change measure.
[0032] Specifically, the calculation steps for the instance change metric include: Calculate the semantic similarity between the newly added instance in the newly added data and each instance in the existing instance set to obtain a semantic similarity set. The semantic similarity is a weighted sum of attribute similarity and relation similarity. If the maximum semantic similarity in the semantic similarity set is less than the instance change threshold, the newly added instance is determined to be a new instance. Count the number of all new instances and use the ratio of the number of new instances to the total number of newly added instances as the instance change measure.
[0033] The instance change metric measures the proportion of new data that cannot be mapped to existing ontology instances. First, define instance semantic similarity:
[0034] when:
[0035] This instance is considered a new instance.
[0036] in, For adding a new collection of instances; For an existing collection of instances; For adding a new instance With existing examples Semantic similarity between them; For adding a new instance With existing examples Attribute similarity between them; For adding a new instance With existing examples Similarity between relationships; , which is the weighting coefficient, controls the relative importance of attribute similarity and relationship similarity; For adding a new instance With existing instance collection The maximum semantic similarity among all instances; This is the instance change threshold used to determine whether it is a new instance.
[0037] Define the formula for measuring instance change: ; in, This represents the number of instances in the newly added instance set that cannot be matched with existing instances. This represents the total number of new instances. Changes in the instance layer are measured by calculating the ratio of new instances to existing instances.
[0038] The calculation steps for attribute change measurement include: Attributes are divided into numerical attributes and discrete attributes. The ratio of the number of numerical attributes that have changed significantly to the total number of numerical attributes is calculated as the measure of change in numerical attributes. Numerical attributes whose relative change exceeds a preset threshold are considered as significant change attributes. The ratio of the number of discrete attributes that have changed to the total number of discrete attributes is calculated as the measure of change in discrete attributes. The numerical attribute change measure and the discrete attribute change measure are weighted and summed to obtain the attribute change measure.
[0039] When calculating attribute changes, the attributes are first categorized into numerical attributes and discrete attributes. Change measures for numerical attributes are used to assess changes in numerical attributes, while change measures for discrete attributes are used to assess changes in discrete attributes. The formula for the change measure of numerical attributes is defined as follows: ; in, It is a collection of numerical attributes; For example At the present moment ,property The value; For example In the previous moment ,property The value; For attributes The threshold for change.
[0040] Define the formula for measuring the change of discrete attributes: ; A comprehensive attribute change measure is provided, combining changes in both numerical and discrete attributes, to offer an overall measure of attribute change. The formula for this overall attribute change measure is defined as follows: ; in, For measuring changes in numerical attributes; For measuring the change of discrete attributes; The weighting coefficient controls the relative importance of changes in numerical and discrete attributes.
[0041] The calculation steps for the relational change metric include: Obtain the set of relations of the ontology before evolution, and the set of relations obtained by mapping the new data; calculate the sum of the number of newly added relation types and the number of lost relation types; use the ratio of the sum of the number of newly added relation types and the number of lost relation types to the total number of relation types of the ontology before evolution as a measure of relation change.
[0042] Relationship change is used to determine whether new data introduces a new relation schema or invalidates an existing relation schema. The relation change measurement formula is defined as follows: ; in, This is the set of relationships of the entity before evolution; The set of relations obtained by mapping new data; Indicates a newly added relation type; A relation type that indicates that the relationship has disappeared or no longer appears.
[0043] The calculation steps for the concept change metric include: Calculate the similarity between the newly added semantic unit and each existing concept in the ontology. The similarity is a weighted sum of word similarity and attribute similarity. Obtain the maximum value of the similarity. If the maximum value is less than the concept coverage threshold, it is determined that the newly added semantic unit represents a new concept. Count the number of all new concepts and use the ratio of the number of new concepts to the total number of newly added semantic units as a measure of concept change.
[0044] First, calculate the similarity between the newly added semantic unit and the existing concept, and define the concept similarity formula: ; in, This is a newly added semantic unit; These are concepts already present in the ontology; Indicates the addition of a semantic unit With the concepts already existing in the ontology Word similarity; Indicates the addition of a semantic unit With the concepts already existing in the ontology Attribute similarity; , which is the weighting coefficient, controls the relative importance of word similarity and attribute similarity.
[0045] Define the formula for measuring concept change: ; in, For the newly added semantic unit set; The set of concepts already existing in the ontology; The similarity between the newly added semantic unit and the most similar concept; This is the concept coverage threshold. It's a concept change metric, measuring the ratio of semantic units not covered by existing concepts to the total number of newly added semantic units.
[0046] S4. Obtain the weights corresponding to each semantic change quantity in the semantic change information, and perform weighted calculations on each type of semantic change measure according to the preset weights to obtain the overall semantic change intensity of the newly added data.
[0047] Reference Figure 2The semantic change metrics in the semantic change information are weighted according to preset weights. First, different weights are assigned to the four types of semantic changes—instance change, attribute change, relation change, and concept change—based on their importance in specific domains or applications. In this embodiment, the instance change metric... Attribute change measurement Measurement of Relationship Change Concept change measurement The weights of the impact of these four semantic changes on the dynamic ontology of earthquake disaster domain are as follows: , , , and satisfy Then, the various semantic change measures are weighted according to preset weights to obtain the overall semantic change intensity of the new data, and the formula for the overall semantic change measure is defined as follows: ; in, For instance change intensity; The intensity of the attribute change; The intensity of the relationship change; The intensity of conceptual change.
[0048] S5. Decompose the overall semantic change intensity into instance layer semantic change intensity and concept layer semantic change intensity, compare the instance layer semantic change intensity with the preset instance layer threshold, and compare the concept layer semantic change intensity with the preset concept layer threshold to obtain the comparison results.
[0049] S6. Determine the optimization actions for the dynamic ontology model based on the comparison results.
[0050] Reference Figure 3 Based on the comparison results, the optimization action instructions for the dynamic ontology model are determined, including: If the semantic change intensity of the instance layer is greater than the instance layer threshold, then the instance layer update operation is triggered; If the intensity of semantic change at the conceptual layer exceeds the conceptual layer threshold, a conceptual layer evolution operation is triggered.
[0051] Semantic changes are divided into instance-level changes and concept-level changes, and preset thresholds are set for instance-level and concept-level changes respectively. and The semantic change intensity of the instance layer and the concept layer are calculated separately, and the semantic change measurement formula of the instance layer is defined: ; Formula for measuring semantic change at the conceptual level: ; like This triggers an instance layer update operation; if This triggers the conceptual layer evolution process.
[0052] S7. Perform concept layer evolution and / or instance layer update operations on the ontology based on the optimization actions to complete the optimization of the dynamic ontology model.
[0053] Based on the results of the evolution trigger, the ontology undergoes either concept layer evolution or instance layer update operations. Specifically: if the concept layer evolution process is triggered based on the results of step S6, new concepts and attributes are added to the existing ontology based on the new data, the hierarchical structure between concepts is adjusted, and relationships between concepts are added, modified, or deleted. If the instance layer update operation is triggered, new instances conforming to their definitions are added to existing concepts based on the new data, and the attribute values of existing instances are updated. This achieves the adjustment and optimization of the dynamic ontology model.
[0054] By calculating the semantic change intensity at different levels, intelligent management of the dynamic ontology evolution triggering mechanism is achieved, reducing false triggering and missed triggering. The dynamic ontology model is divided into a concept layer and an instance layer. Based on the change intensity of the concept layer and the instance layer, the evolution level of the ontology is precisely controlled, avoiding the high computational cost of full ontology updates and improving the robustness of the system. The dynamic ontology evolution triggering method in this application is applicable to various complex domains that require continuous ontology evolution in scenarios with continuous input of dynamic data, providing an effective solution for the intelligent maintenance of large-scale knowledge bases.
[0055] Based on the same inventive concept, one embodiment of the present invention provides a dynamic ontology evolution triggering system based on the intensity of semantic change.
[0056] The dynamic ontology evolution triggering system based on semantic change intensity described in this invention can be installed in an electronic device. Depending on the functions implemented, the dynamic ontology evolution triggering system based on semantic change intensity includes: The acquisition module is used to acquire new data in the current knowledge domain; The semantic mapping module is used to construct a dynamic ontology model and perform semantic mapping on new data based on the dynamic ontology model to obtain standardized semantic elements. The semantic unit extraction module is used to extract semantic units from standardized semantic elements to obtain semantic change information of the new data. The semantic change information is used to represent the amount of semantic change at different levels of the new data. The semantic change intensity calculation module is used to obtain the weights corresponding to each semantic change quantity in the semantic change information, and to perform weighted calculations on each type of semantic change measure according to preset weights to obtain the overall semantic change intensity of the new data. The comparison module is used to break down the overall semantic change intensity into instance layer semantic change intensity and concept layer semantic change intensity, compare the instance layer semantic change intensity with a preset instance layer threshold, and compare the concept layer semantic change intensity with a preset concept layer threshold to obtain the comparison results. The first processing module is used to determine the optimization actions for the dynamic ontology model based on the comparison results. The second processing module is used to perform concept layer evolution and / or instance layer update operations on the ontology based on the optimization actions, thereby completing the optimization of the dynamic ontology model.
[0057] The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and are stored in the memory of the electronic device.
[0058] The various variations and specific examples in the dynamic ontology evolution triggering method based on semantic change intensity provided in the above embodiments are also applicable to the dynamic ontology evolution triggering system based on semantic change intensity in this embodiment. Through the foregoing detailed description of the dynamic ontology evolution triggering method based on semantic change intensity, those skilled in the art can clearly understand the implementation method of the dynamic ontology evolution triggering system based on semantic change intensity in this embodiment. For the sake of brevity, it will not be described in detail here.
[0059] This application also discloses an electronic device, such as Figure 4 The diagram shown is a schematic representation of an electronic device for a method for triggering dynamic ontology evolution based on the intensity of semantic change, according to an embodiment of the present invention. The electronic device may include at least one processor 10, a memory 11 communicatively connected to the at least one processor, a communication bus 12, and a communication interface 13. It may also include a computer program stored in the memory 11 and executable on the processor 10, such as a program for triggering dynamic ontology evolution based on the intensity of semantic change.
[0060] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., methods for triggering dynamic ontology evolution based on semantic change intensity) and calls data stored in the memory 11 to perform various functions of the electronic device and process data.
[0061] The memory 11 includes at least one type of readable storage medium, including flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of an electronic device, such as a portable hard drive. In other embodiments, the memory 11 can be an external storage device of the electronic device, such as a plug-in portable hard drive, smart media card (SMC), secure digital (SD) card, flash card, etc. Furthermore, the memory 11 can include both internal and external storage units of the electronic device. The memory 11 can be used not only to store application software and various types of data installed on the electronic device, such as code for methods triggered by dynamic ontology evolution based on semantic change intensity, but also to temporarily store data that has been output or will be output.
[0062] The communication bus 12 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into an address bus, a data bus, a control bus, etc. The bus is configured to enable communication between the memory 11 and at least one processor 10, etc.
[0063] Communication interface 13 is used for communication between the aforementioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, Bluetooth interface, etc.), typically used to establish communication connections between the electronic device and other electronic devices. The user interface may be a display, an input unit (such as a keyboard), and optionally, a standard wired or wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device and to display a visual user interface.
[0064] Figure 4 Only electronic devices with components are shown; those skilled in the art will understand that... Figure 4 The structure shown does not constitute a limitation on the electronic device and may include fewer or more components than shown, or combine certain components, or have different component arrangements.
[0065] For example, although not shown, the electronic device may also include a power supply (such as a battery) to power various components. Preferably, the power supply can be logically connected to at least one processor 10 via a power management device, thereby enabling functions such as charging management, discharging management, and power consumption management. The power supply may also include one or more DC or AC power supplies, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be elaborated further here.
[0066] It should be understood that the embodiments are for illustrative purposes only and are not limited to this structure in the scope of the patent application.
[0067] Furthermore, if the modules / units integrated into the electronic device are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile.
[0068] This application provides a computer-readable storage medium, including, for example, any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM). The computer-readable storage medium stores a computer program that can be loaded by a processor and execute the dynamic ontology evolution triggering method based on semantic change intensity described in the above embodiments.
[0069] In the description of this specification, the references to terms such as "an embodiment," "some embodiments," "example," "specific example," "a implementation," "a preferred implementation," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.
[0070] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.
Claims
1. A dynamic ontology evolution triggering method based on semantic change intensity, characterized in that, The method includes: Acquire new data in the current knowledge domain; Construct a dynamic ontology model and perform semantic mapping on the new data based on the dynamic ontology model to obtain standardized semantic elements; Semantic units are extracted from standardized semantic elements to obtain semantic change information of the new data. This semantic change information is used to represent the amount of semantic change at different levels of the new data. Obtain the weights corresponding to each semantic change quantity in the semantic change information, and perform weighted calculations on each type of semantic change measure according to the preset weights to obtain the overall semantic change intensity of the new data; The overall semantic change intensity is broken down into instance layer semantic change intensity and concept layer semantic change intensity. The instance layer semantic change intensity is compared with a preset instance layer threshold, and the concept layer semantic change intensity is compared with a preset concept layer threshold to obtain the comparison results. The optimization actions for the dynamic ontology model are determined based on the comparison results; Based on the optimization actions, the concept layer evolution and / or instance layer update operations of the ontology are performed to complete the optimization of the dynamic ontology model.
2. The dynamic ontology evolution triggering method based on semantic change intensity as described in claim 1, characterized in that, The step of determining the optimization action instructions for the dynamic ontology model based on the comparison results includes: If the semantic change intensity of the instance layer is greater than the instance layer threshold, then the instance layer update operation is triggered; If the intensity of semantic change at the conceptual layer exceeds the conceptual layer threshold, a conceptual layer evolution operation is triggered.
3. The dynamic ontology evolution triggering method based on semantic change intensity as described in claim 1, characterized in that, Semantic change information includes instance change measures, attribute change measures, relation change measures, and concept change measures.
4. The dynamic ontology evolution triggering method based on semantic change intensity as described in claim 3, characterized in that, The steps for calculating the instance change metric include: Calculate the semantic similarity between the newly added instance in the newly added data and each instance in the existing instance set to obtain a semantic similarity set, wherein the semantic similarity is a weighted sum of attribute similarity and relation similarity; If the maximum semantic similarity in the semantic similarity set is less than the instance change threshold, then the newly added instance is determined to be a new instance; The number of all new instances is counted, and the ratio of this count to the total number of new instances is used as a measure of instance change.
5. The dynamic ontology evolution triggering method based on semantic change intensity as described in claim 3, characterized in that, The calculation steps for attribute change measurement include: Attributes are categorized into numerical attributes and discrete attributes; The ratio of the number of numerical attributes that have changed significantly to the total number of numerical attributes is used as a measure of change in numerical attributes. Numerical attributes whose relative change exceeds a preset threshold are considered to be significant change attributes. The ratio of the number of discrete attributes that have changed to the total number of discrete attributes is used as a measure of the change in discrete attributes. The attribute change measure is obtained by weighted summation of the numerical attribute change measure and the discrete attribute change measure.
6. The dynamic ontology evolution triggering method based on semantic change intensity as described in claim 3, characterized in that, The calculation steps for the relational change metric include: Obtain the set of relations of the ontology before evolution, and the set of relations obtained by mapping the new data; Calculate the sum of the number of newly added relation types and the number of disappeared relation types; The ratio of the sum of the number of newly added relation types and the number of disappeared relation types to the total number of relation types in the ontology before evolution is used as the measure of relation change.
7. The dynamic ontology evolution triggering method based on semantic change intensity as described in claim 3, characterized in that, The calculation steps for the concept change metric include: Calculate the similarity between the newly added semantic unit and each existing concept in the ontology, where the similarity is a weighted sum of word similarity and attribute similarity; Obtain the maximum value among the similarities; If the maximum value is less than the concept coverage threshold, then the newly added semantic unit is determined to represent a new concept; The number of all new concepts is counted, and the ratio of this count to the total number of newly added semantic units is used as a measure of the change in the concept.
8. A dynamic ontology evolution triggering system based on semantic change intensity, used to implement the dynamic ontology evolution triggering method based on semantic change intensity as described in any one of claims 1 to 7, characterized in that, include: The acquisition module is used to acquire new data in the current knowledge domain; The semantic mapping module is used to construct a dynamic ontology model and perform semantic mapping on new data based on the dynamic ontology model to obtain standardized semantic elements. The semantic unit extraction module is used to extract semantic units from standardized semantic elements to obtain semantic change information of the new data. The semantic change information is used to represent the amount of semantic change at different levels of the new data. The semantic change intensity calculation module is used to obtain the weights corresponding to each semantic change quantity in the semantic change information, and to perform weighted calculations on each type of semantic change measure according to preset weights to obtain the overall semantic change intensity of the new data. The comparison module is used to break down the overall semantic change intensity into instance layer semantic change intensity and concept layer semantic change intensity, compare the instance layer semantic change intensity with a preset instance layer threshold, and compare the concept layer semantic change intensity with a preset concept layer threshold to obtain the comparison results. The first processing module is used to determine the optimization actions for the dynamic ontology model based on the comparison results. The second processing module is used to perform concept layer evolution and / or instance layer update operations on the ontology based on the optimization actions, thereby completing the optimization of the dynamic ontology model.
9. An electronic device, characterized in that, The electronic device includes: At least one processor (10); and, A memory (11) communicatively connected to the at least one processor (10); The memory (11) stores a computer program that can be executed by the at least one processor (10) to enable the at least one processor (10) to execute the dynamic ontology evolution triggering method based on semantic change intensity as described in any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program; when the computer program is executed by a processor, it implements the dynamic ontology evolution triggering method based on the semantic change intensity as described in any one of claims 1 to 7.